Unveiling India's Fertility Decline Trajectory: Hybrid ML Models for Accurate Long-Term Forecasts

Unveiling India's Fertility Decline Trajectory: Hybrid ML Models for Accurate Long-Term Forecasts | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Unveiling India's Fertility Decline Trajectory: Hybrid ML Models for Accurate Long-Term Forecasts Deepthi Ch, Mr. Naga Ravindra Babu M This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8829613/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract This research uses machine learning to anticipate fertility drop in India from 1950–2021, utilizing data from National Family Health Surveys, Census of India, and worldwide demographic datasets. The study focuses on fertility trends, regional differences, and socioeconomic variables in Andhra Pradesh. Fertility indicators such as total fertility rate, general fertility rate, and crude birth rate are studied with variables such as female education, urbanization, and contraception use. Four models (linear regression, random forest, support vector machines, and XGBoost) are trained on historical fertility data to forecast short-term until 2024. XGBoost is the most accurate forecaster, indicating a sustained drop in fertility, especially in low fertility states.The findings emphasize both the social and health benefits of decreased fertility, as well as emerging difficulties such as population aging, labor supply, and reliance. The study highlights the importance of integrating machine learning and demographic data for evidence-based policy planning in a constantly changing population context. fertility decline machine learning demographic forecasting total fertility rate India regional disparities Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 1. Introduction India is undergoing a revolutionary demographic transformation, characterized by a rapid and sustained decline in fertility. This transition has far-reaching consequences for the country's future socioeconomic structure, labor dynamics, and public policy priorities.The total fertility rate (TFR), defined as the average number of children born to a woman over her lifetime, has fallen from approximately 6.2 in 1950 to around 2.0 in 2019-21, much below the replacement level of 2.1 (NFHS [5], 2019-21; Times of India, 2023 ). This study looks into the diverse nature of India's fertility decline by charting its historical past, identifying major causes, and comparing variations among states.A specific case study of Andhra Pradesh gives more light on the dynamics of low fertility at the subnational level.Understanding these patterns is critical for creating evidence-based strategies that manage population aging while maintaining economic development. Existing research on India's fertility transition indicates that TFR has steadily declined as a result of changes in education, health, and family planning practices. According to studies, TFR has decreased from around 3.6 in 1991 to around 2.0 by 2021, but regional disparities remain: some northern and eastern states, such as Bihar and Meghalaya, continue to have more than three children per woman, whereas states like Kerala and Goa have far fewer than two, with women's empowerment and targeted government programs hastening the decline (Kumar, Devi, & Singh, 2023 ).According to Halli et al. (2019), TFR in Uttar Pradesh fell from more than five children per woman in the 1970s to roughly 2.7 in the mid-2010s. However, it is still 20% higher than the national average due to district-level differences and reliance on traditional contraception techniques. This study uses over 70 years of demographic, socioeconomic, and environmental data to forecast fertility trends at the national level. It also includes a thorough case study of Andhra Pradesh and evaluates the policy implications (Kumar et al., 2023 ). Many northern states lag behind, while southern states achieve replacement fertility earlier. 2. Methodology This study uses a mixed-methods approach to explore fertility patterns in India, combining demographic data analysis and machine learning-based predictions. The empirical strategy is divided into four stages: data preparation, model creation, model evaluation, and prediction of future fertility rates. 2.1 Data Sources The analysis includes secondary data from the National Family Health Survey (NFHS 1–5), the Census of India, and foreign demographic datasets from 1950–2021. The dataset includes national and subnational fertility indices such as total fertility rate (TFR), general fertility rate (GFR), and crude birth rate (CBR), as well as socioeconomic characteristics like women's educational attainment, contraception prevalence, and urbanization level. 2.2 Data Preparation The collected datasets were cleaned and harmonised to ensure temporal and conceptual consistency between sources. Missing values were addressed through imputation or deletion, variables were standardized for comparability, and the dataset was randomly divided into training and testing subsets for out-of-sample evaluation. 2.3 Modeling Approach Four supervised learning methods were used to anticipate future fertility patterns: linear regression, random forest, XGBoost, and support vector regression with a suitable kernel. To create projections up to 2024, each model was trained on historical TFR series from 1950 to 2021 (with associated covariates if relevant). 2.4 Evaluation Metrics Model performance was evaluated using root mean squared error (RMSE) and mean absolute error (MAE), which measure the average size of prediction errors in relation to observed fertility values.Visual comparisons of predicted and observed TFR trajectories assessed each model's ability to capture the long-term falling trend. 2.5 Predictive Performance After analyzing error measures and graphical diagnostics, XGBoost was shown to be the most effective model for short-term fertility forecasting, with the lowest RMSE and MAE among the examined algorithms.This model was used to project national and state-level TFR to 2024 and evaluate the forecasting framework's robustness. 2.6 Methodological Workflow The overall workflow consists of four steps: (1) data loading, cleaning, and variable construction; (2) train-test splitting and estimation of linear regression, random forest, XGBoost, and support vector regression models; (3) model performance evaluation using RMSE, MAE, and graphical checks; and (4) generation and interpretation of fertility forecasts for India and Andhra Pradesh. Figure 1 shows the corresponding sequence operations. 3. Results and Discussion Over the previous seven decades, a remarkable and consistent reduction in fertility has changed India's demographic environment. According to UN and national predictions, the total fertility rate has fallen by nearly two-thirds, from 5.7–6.2 children per woman in 1950 to 1.98 children per woman in 2024 (Times Now News, n.d.). Table 1 sums up the progression. Table 1 Total fertility rate in India, selected years, 1950–2024 Year TFR (children per woman) 1950 5.7–6.2 1980 4.8 2000 3.3 2015 2.3 2019 2.2 2021 2.0 2024 (est.) 1.98 Source: Compiled from Times Now News and international demographic databases Figure 2 depicts the long-term decline in fertility, with TFR falling from around 6.2 in 1950 to less than two children per woman in recent years (Times Now News). According to Arora ( 2021 ), India's fertility rate will approach replacement levels by 2020, signifying demographic stabilization. According to the Ministry of Health and Family Welfare (2021), the prevalence of contraception among married women aged 15 to 49 rose from 54% to 67% between 2015-16 and 2019-21. However, the proportion of women aged 20–24 who married before the age of 18 declined, showing a trend toward later marriage and greater reproductive agency. This study adds significant insights to earlier research on India's fertility transition. The study adopts a macro-demographic approach, examining country fertility trends from 1950 to 2021 and forecasting to 2024. Second, it considers a number of issues, including education, contraceptive use, urbanization, and environmental factors, proving, for example, that women with higher levels of education have fewer children.Third, the case study of Andhra Pradesh demonstrates a higher reduction (TFR about 1.5 and a 17% drop in general fertility rate), highlighting regional variances that are obscured by national averages. Fourth, the comparative machine learning technique extensively investigates linear regression, random forest, support vector machines, and XGBoost. XGBoost has the lowest error values (RMSE = 0.23, MAE ≈ 0.18), indicating significant promise for demographic forecasting. The paper discusses the policy implications for population aging, dependency, and future labor supply. Machine learning can assist in combining demographic studies with evidence-based policymaking at the national and subnational levels. 4. Factors Contributing to Declining Fertility in India The decline in India’s total fertility rate is not attributable to a single cause but reflects a complex interplay of socioeconomic, healthcare, cultural, and environmental factors. 4.1 Socio-Economic Factors Fertility drop is primarily driven by socioeconomic progress. Rapid urbanization has changed lifestyles and increased the expense of housing, schooling, and childcare, driving couples to choose smaller families (Womb IVF & Fertility Centre, n.d.). Increased female literacy and education have enabled women to postpone marriage and childbearing, engage in paid job, and make educated fertility decisions. NFHS-5 statistics demonstrate a strong educational gradient: women with 12 or more years of schooling have a TFR of about 1.7–1.8, compared to roughly 2.8-3.0 for women without education. (Roy, 2022 ).Earlier research has also found that higher levels of female education and lower child mortality are substantially linked to fertility drop throughout Indian districts (Chaudhury, 1996 ). At the same time, changing ambitions for greater living standards and job progress have diminished the perceived benefits of large family sizes (Vajiram & Ravi, 2025 ). 4.2 HealthCare and Family Planning Healthcare and family planning improvements have been particularly important. The national prevalence of modern contraceptives has increased from 54% in NFHS-4 to 67% in NFHS-5 (Ministry of Health and Family Welfare, 2021). According to Roy ( 2022 ), contemporary contraceptive use among Muslims increased from 37.9% to 47.4% between NFHS 4 and 5. Improved maternal and child health care have reduced infant and under-five mortality rates, reducing the need for multiple births to ensure survival (Chaudhury, 1996 ).The eSanjeevani telemedicine platform has enhanced access to counseling and reproductive health information, allowing for more educated family planning decisions (Press Information Bureau, 2023 ). 4.3 Social norms and government Policies Changes in social standards have also contributed to decreasing fertility. Rising gender equality and changing media depictions of work and family have led to an increasing acceptance of delayed marriage, smaller families, and child-free lives (Financial Times, 2025 ). Population strategies, which were formerly focused on slowing rapid development, are gradually shifting to concerns about both high and low fertility. Some governments have debated or implemented two-child norms for public office eligibility, citing concerns about demographics and labor availability (Roy, 2022 ; Vajiram & Ravi, 2025 ). 5. Regional Variations in fertility Rates The national decline in fertility masks substantial regional disparities, with Indian states broadly grouped into high- and low-fertility clusters. 5.1 States with high Fertility Rates According to recent NFHS 5 and official statistics (International Institute for Population Sciences, 2021; Ministry of Health and Family Welfare, 2021), states like Bihar (TFR about 3.0), Uttar Pradesh (2.4), Jharkhand (2.3), and Madhya Pradesh (2.0) continue to have fertility rates at or above replacement level.Chaudhury ( 1996 ) suggests that poorer female literacy, increased child mortality, cultural norms favoring early marriage, and restricted access to modern contraception all contribute to the continuance of this issue. 5.2 States with low fertility rates In contrast, states like Punjab (TFR around 1.6), West Bengal (1.6), Andhra Pradesh (around 1.7), Kerala (1.4), and Tamil Nadu (1.4) have fertility rates that are substantially below the replacement threshold. High female literacy, long-standing investments in health and education, successful family planning programs, increasing urbanization, and cultural preference for smaller families all contribute to early and prolonged fertility drop (Chaudhury, 1996 ).Low fertility states face significant demographic issues, including labor shortages, in-migration from higher fertility regions, and population aging. 6. Case Study: Declining Fertility Trends in Andhra Pradesh Andhra Pradesh exhibits the dramatic drop in birth rates in certain Indian states. The state's general fertility rate has plummeted by around 17% over the last decade, and the crude birth rate has dropped from 18.2 to 16.2 live births per thousand inhabitants; its total fertility rate, at about 1.5 in 2019–2020, is significantly lower than the national average (Times of India, 2022 ).Education is important: women with no formal schooling have a TFR of roughly 2.3, whereas those with higher secondary education and above have a TFR of around 1.2, demonstrating how educational empowerment effects reproductive choice. Proactive family planning efforts, increased urbanisation, rising living costs, and a trend toward later marriage are all contributing factors. This demographic achievement has resulted in significant policy issues. Authorities are now dealing with the consequences of decreasing population growth, an aging population structure, and a projected increase in dependence ratios. In response, state-level debates have emerged on revising earlier population control measures, including proposals to relax two-child conditions for electoral eligibility and introduce positive incentives for larger families, indicating a broader reorientation of population policy (The Economic Times, 2024 ). 7. Crude Birth Rate Trends in India The Crude Birth Rate (CBR) confirms the TFR trends. Nationally, the CBR declined from 29.5 in 1991 to 20.4 in 2016, with a large rural-urban disparity (rural: 22.1; urban: 17.0) (Womb IVF & Fertility Center. (n.d.)). States with high TFRs also have high CBRs, such as Bihar's rural CBR of 27.7. Conversely, states with low fertility have low CBRs, with Kerala's rural CBR at 14.3 and Himachal Pradesh's urban CBR as low as 10.5 (Census of India, 2011 ). This regional variance highlights the unevenness of India's demographic shift. 8. ML-Based Fertility Prediction and Model Evaluation In addition to demographic and survey analysis, this study uses machine learning (ML) to anticipate fertility trends in India. A linear regression model was initially constructed using historical total fertility rate (TFR) data from 1950 to 2021 to generate baseline forecasts for 2024. Three non-linear algorithms—random forest, XGBoost, and support vector regression—were tested to see if more flexible models increase predictive performance. Model accuracy was assessed using root mean squared error (RMSE) and mean absolute error (MAE), which calculate the average size of prediction errors between observed and anticipated fertility levels. These metrics are commonly employed in regression and demographic forecasting since they are expressed in the same units as the outcome and are susceptible to systematic prediction biases. Figure 5 .1 demonstrates that the XGBoost model outperformed linear regression, random forest, and support vector regression in terms of prediction accuracy, with an RMSE of roughly 0.23 and MAE of about 0.18. To help validate the model, projected TFR values from XGBoost were compared to observed fertility rates over time. XGBoost, a more advanced machine learning algorithm, outperforms linear regression as a baseline for short-term fertility forecasts. Recent demographic applications have shown that gradient-boosting algorithms may accurately anticipate birth numbers and related population indices. XGBoost and comparable models are thus interesting tools for policy planning and demographic scenario analysis in rapidly changing situations such as India. 9. Conclusion and Future Implications India's demographic transition is a watershed moment, representing significant advances in health, education, and women's empowerment. The TFR's decrease to below replacement level represents a shift toward population stabilization, which could boost per-capita resource allocation and economic growth. However, this achievement has ushered in a new set of obstacles. The rapid drop will undoubtedly result in an older population, a diminishing workforce over time, and an increasing old-age dependence ratio, all of which will put a strain on pension systems and healthcare facilities. Future policy must be nuanced and adaptive. It is recommended that India: Invest in Human Capital : Enhance education and skill development to maximize the productivity of the current working-age population. Strengthen Social Security Systems : Develop robust, inclusive pension and healthcare systems to support a growing elderly population. Promote Gender Equality : Further increase female labour force participation to offset a shrinking working- age cohort. Adopt Region-Specific Strategies : Tailor policies to address the specific needs of states, from strengthening family planning in high-fertility regions to designing aged-care policies in low-fertility regions. Uphold Reproductive Rights : Ensure that any pronatalist discussions, as seen in Andhra Pradesh, remain focused on choice and incentives rather than coercive measures. In conclusion, India's demographic future is no longer defined by the challenge of runaway growth but by the complex task of managing the consequences of its success. Navigating this new demographic reality will require foresight, strategic planning, and a commitment to inclusive development. Abbreviations AI Artificial Intelligence AP Andhra Pradesh CBR Crude Birth Rate CPR Contraceptive Prevalence Rate GFR General Fertility Rate IVF/IUI In Vitro Fertilization / Intrauterine Insemination LR Linear Regression MAE Mean Absolute Error ML Machine Learning NFHS National Family Health Survey RF Random Forest RMSE Root Mean Squared Error SVM Support Vector Machine TFR Total Fertility Rate XGBoost Extreme Gradient Boosting Declarations Competing interests The authors have declared that they have no competing interests. Ethics approval and consent to participate Not relevant. This study did not require ethics approval or informed consent as it used secondary, publically available, and de-identified data. Data Availability The data utilized in this study were obtained from publically available sources, such as the National Family Health Survey, the Indian Census, and international demographic databases indicated in the References. References Arora A (2021), November 25 In a first, India’s fertility rate falls below replacement level: What it means. India Today. Retrieved from https://www.indiatoday.in/india/story/india-fertility-rate-declines-replacement-level-meaning-nfhs-survey-1880894-2021-11-25 Census of India (2011) Vital statistics. Office of the Registrar General & Census Commissioner, India Chaudhury RH (1996) Factors affecting variations in fertility by states of India: A preliminary investigation. Asia-Pacific Popul J 11(2):59–68 Financial Times (2025), February 23 Why are birth rates falling? With Alice Evans. Financial Times. Retrieved from https://www.ft.com/content/cef1c8b4-b278-425a-88b4-99d37bd4439b Gunnal GS, Akhil PM, Gharge S (2020), December 21 Contraceptive use among women rises in western states, Goa tops the charts: NFHS-5 data. Down To Earth. Retrieved from https://www.downtoearth.org.in/health/contraceptive-use-among-women-rises-in-western-states-goa-tops-the-charts-nfhs-5-data-7471 Halli SS, Madise NJ (2019) & others. Fertility and family planning in Uttar Pradesh: Trends and determinants International Institute for Population Sciences (IIPS) (2021) National Family Health Survey (NFHS-5), 2019–21: Andhra Pradesh fact sheet. IIPS, Mumbai Kumar A, Devi R, Singh M (2023) Spatial and temporal variations in fertility in India: An analysis of NFHS-5 and SRS data Press Information Bureau (2023), February 16 Union Health Minister Dr. Mansukh Mandaviya hails the eSanjeevani landmark milestone of providing telemedicine services to more than 10 crore patients. Government of India. Retrieved from https://www.pib.gov.in/PressReleasePage.aspx?PRID=1899855 Roy E (2022), May 8 NFHS-5 data: Total fertility rate dips, steepest decline among Muslims. The Indian Express. Retrieved from https://indianexpress.com/article/india/fertility-falling-in-all-communities-steepest-decline-among-muslims-nfhs-data-7906994/ The Economic Times (2024), February 16 Andhra Pradesh plans cash reward for having more children, says CM Chandrababu Naidu. The Economic Times. Retrieved from https://economictimes.indiatimes.com/news/india/andhra-pradesh-plans-cash-reward-for-having-more-children-says-cm-chandrababu-naidu/articleshow/121726486.cms Times Now News. (n.d.). India’s fertility rate drops from 6.2 to under 2 since 1950: Lancet study. Times Now. Retrieved August 27 (2025) from https://www.timesnownews.com/health/indias-fertility-rate-drops-from-6-2-to-under-2-since-1950-lancet-study-article-10870592 Times of India (2022), October 8 Fertility rate decreases by 17% in a decade in Andhra Pradesh. The Times of India. Retrieved from https://timesofindia.indiatimes.com/city/visakhapatnam/fertility-rate-decreases-by-17-in-a-decade-in-andhra-pradesh/articleshow/94715026.cms Times of India (2023), February 29 India’s declining fertility rate: Is it a cause of concern? The Times of India. Retrieved from https://timesofindia.indiatimes.com/life-style/health-fitness/health-news/indias-declining-fertility-rate-is-it-a-cause-of-concern/articleshow/115936225.cms Vajiram, Ravi (2025), January 19 Why are fertility levels declining in India? Vajiram & Ravi Current Affairs. Retrieved August 27, 2025, from https://vajiramandravi.com/current-affairs/fertility-rate-in-india/ Wikipedia contributors. (n.d.). List of states and union territories of India by fertility rate. In Wikipedia, The Free Encyclopedia. Retrieved August 27 (2025) from https://en.wikipedia.org/wiki/List_of_states_and_union_territories_of_India_by_fertility_rate Womb IVF (2025) & Fertility Center. (n.d.). Decline in fertility rate in India: Causes & solutions. Retrieved August 27, from https://www.wombivf.com/decline-in-fertility-rate-causes-and-solutions/ Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8829613","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":588213102,"identity":"7ab4565b-787f-4232-b9c1-44750b968be9","order_by":0,"name":"Deepthi Ch","email":"data:image/png;base64,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","orcid":"","institution":"B.V.Raju College","correspondingAuthor":true,"prefix":"","firstName":"Deepthi","middleName":"","lastName":"Ch","suffix":""},{"id":588213516,"identity":"008609a3-19cd-4c76-983c-a1f1a483a75e","order_by":1,"name":"Mr. Naga Ravindra Babu M","email":"data:image/png;base64,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","orcid":"","institution":"B.V.Raju College","correspondingAuthor":true,"prefix":"Mr.","firstName":"Naga","middleName":"Ravindra Babu","lastName":"M","suffix":""}],"badges":[],"createdAt":"2026-02-09 11:09:12","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8829613/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8829613/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102288606,"identity":"fd74d4a7-4371-4a7b-80bf-0cd4aeaa233f","added_by":"auto","created_at":"2026-02-10 08:46:07","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":122685,"visible":true,"origin":"","legend":"\u003cp\u003eWorkflow of the Methodology\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-8829613/v1/7baf1a71366fc510bb6a620a.png"},{"id":102288607,"identity":"cbba50c7-d625-4375-bc58-aefb5abd4cdd","added_by":"auto","created_at":"2026-02-10 08:46:08","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":367181,"visible":true,"origin":"","legend":"\u003cp\u003eTime series of India’s total fertility rate, 1950–2024.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-8829613/v1/0ce97a0d9f91fa768f68124c.png"},{"id":102297868,"identity":"59ad2c10-941a-4c39-9fd7-e9e8dbf0610b","added_by":"auto","created_at":"2026-02-10 10:29:28","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":68988,"visible":true,"origin":"","legend":"\u003cp\u003eCorrelation Heatmap for the fertility determinants dataset for india\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-8829613/v1/d6be4b811a83d5604489d77b.png"},{"id":102297946,"identity":"afb255e0-20c6-493a-9a92-20a357f146f6","added_by":"auto","created_at":"2026-02-10 10:29:48","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":240001,"visible":true,"origin":"","legend":"\u003cp\u003eHorizontal Bar Chart of state level total fertility rates in india\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-8829613/v1/e6ebae76747bfb5bc3223094.png"},{"id":102397075,"identity":"77f0a27b-fe0e-4c60-ac73-fbcaa6466f78","added_by":"auto","created_at":"2026-02-11 09:55:07","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":349481,"visible":true,"origin":"","legend":"\u003cp\u003eBar and line charts showing education‑specific TFR and the TFR time series for Andhra Pradesh.\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-8829613/v1/19275553cf5b581c8be06498.png"},{"id":102288611,"identity":"c7c8b54b-c2bf-4ff0-a862-4244edb1d1d9","added_by":"auto","created_at":"2026-02-10 08:46:08","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":209543,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFigure 5.2 \u003c/strong\u003eshows that the projections closely match the observed downward trajectory, implying that the ML-based technique accurately reflects the long-term drop in fertility.\u003c/p\u003e","description":"","filename":"5.12.png","url":"https://assets-eu.researchsquare.com/files/rs-8829613/v1/a34793791b383f85f7c1404b.png"},{"id":102400210,"identity":"41a74d8b-c755-482c-81af-dac0c11152ec","added_by":"auto","created_at":"2026-02-11 10:38:46","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2004887,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8829613/v1/6fc2fbee-2b0c-4caa-b4cc-f2128ef76fb8.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eUnveiling India's Fertility Decline Trajectory: Hybrid ML Models for Accurate Long-Term Forecasts\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eIndia is undergoing a revolutionary demographic transformation, characterized by a rapid and sustained decline in fertility. This transition has far-reaching consequences for the country's future socioeconomic structure, labor dynamics, and public policy priorities.The total fertility rate (TFR), defined as the average number of children born to a woman over her lifetime, has fallen from approximately 6.2 in 1950 to around 2.0 in 2019-21, much below the replacement level of 2.1 (NFHS [5], 2019-21; Times of India, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). This study looks into the diverse nature of India's fertility decline by charting its historical past, identifying major causes, and comparing variations among states.A specific case study of Andhra Pradesh gives more light on the dynamics of low fertility at the subnational level.Understanding these patterns is critical for creating evidence-based strategies that manage population aging while maintaining economic development.\u003c/p\u003e \u003cp\u003eExisting research on India's fertility transition indicates that TFR has steadily declined as a result of changes in education, health, and family planning practices. According to studies, TFR has decreased from around 3.6 in 1991 to around 2.0 by 2021, but regional disparities remain: some northern and eastern states, such as Bihar and Meghalaya, continue to have more than three children per woman, whereas states like Kerala and Goa have far fewer than two, with women's empowerment and targeted government programs hastening the decline (Kumar, Devi, \u0026amp; Singh, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2023\u003c/span\u003e).According to Halli et al. (2019), TFR in Uttar Pradesh fell from more than five children per woman in the 1970s to roughly 2.7 in the mid-2010s. However, it is still 20% higher than the national average due to district-level differences and reliance on traditional contraception techniques.\u003c/p\u003e \u003cp\u003eThis study uses over 70 years of demographic, socioeconomic, and environmental data to forecast fertility trends at the national level. It also includes a thorough case study of Andhra Pradesh and evaluates the policy implications (Kumar et al., \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Many northern states lag behind, while southern states achieve replacement fertility earlier.\u003c/p\u003e"},{"header":"2. Methodology","content":"\u003cp\u003eThis study uses a mixed-methods approach to explore fertility patterns in India, combining demographic data analysis and machine learning-based predictions. The empirical strategy is divided into four stages: data preparation, model creation, model evaluation, and prediction of future fertility rates.\u003c/p\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Data Sources\u003c/h2\u003e \u003cp\u003eThe analysis includes secondary data from the National Family Health Survey (NFHS 1\u0026ndash;5), the Census of India, and foreign demographic datasets from 1950\u0026ndash;2021. The dataset includes national and subnational fertility indices such as total fertility rate (TFR), general fertility rate (GFR), and crude birth rate (CBR), as well as socioeconomic characteristics like women's educational attainment, contraception prevalence, and urbanization level.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Data Preparation\u003c/h2\u003e \u003cp\u003eThe collected datasets were cleaned and harmonised to ensure temporal and conceptual consistency between sources. Missing values were addressed through imputation or deletion, variables were standardized for comparability, and the dataset was randomly divided into training and testing subsets for out-of-sample evaluation.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Modeling Approach\u003c/h2\u003e \u003cp\u003eFour supervised learning methods were used to anticipate future fertility patterns: linear regression, random forest, XGBoost, and support vector regression with a suitable kernel. To create projections up to 2024, each model was trained on historical TFR series from 1950 to 2021 (with associated covariates if relevant).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Evaluation Metrics\u003c/h2\u003e \u003cp\u003eModel performance was evaluated using root mean squared error (RMSE) and mean absolute error (MAE), which measure the average size of prediction errors in relation to observed fertility values.Visual comparisons of predicted and observed TFR trajectories assessed each model's ability to capture the long-term falling trend.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e2.5 Predictive Performance\u003c/h2\u003e \u003cp\u003eAfter analyzing error measures and graphical diagnostics, XGBoost was shown to be the most effective model for short-term fertility forecasting, with the lowest RMSE and MAE among the examined algorithms.This model was used to project national and state-level TFR to 2024 and evaluate the forecasting framework's robustness.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e2.6 Methodological Workflow\u003c/h2\u003e \u003cp\u003eThe overall workflow consists of four steps: (1) data loading, cleaning, and variable construction; (2) train-test splitting and estimation of linear regression, random forest, XGBoost, and support vector regression models; (3) model performance evaluation using RMSE, MAE, and graphical checks; and (4) generation and interpretation of fertility forecasts for India and Andhra Pradesh. Figure\u0026nbsp;1 shows the corresponding sequence operations.\u003c/p\u003e "},{"header":"3. Results and Discussion","content":"\u003cp\u003eOver the previous seven decades, a remarkable and consistent reduction in fertility has changed India's demographic environment. According to UN and national predictions, the total fertility rate has fallen by nearly two-thirds, from 5.7\u0026ndash;6.2 children per woman in 1950 to 1.98 children per woman in 2024 (Times Now News, n.d.). Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e sums up the progression.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eTotal fertility rate in India, selected years, 1950\u0026ndash;2024\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYear\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTFR (children per woman)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1950\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5.7\u0026ndash;6.2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1980\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4.8\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2000\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3.3\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2015\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.3\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2024 (est.)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.98\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eSource: Compiled from Times Now News and international demographic databases\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e2\u003c/span\u003e depicts the long-term decline in fertility, with TFR falling from around 6.2 in 1950 to less than two children per woman in recent years (Times Now News). According to Arora (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2021\u003c/span\u003e), India's fertility rate will approach replacement levels by 2020, signifying demographic stabilization. According to the Ministry of Health and Family Welfare (2021), the prevalence of contraception among married women aged 15 to 49 rose from 54% to 67% between 2015-16 and 2019-21. However, the proportion of women aged 20\u0026ndash;24 who married before the age of 18 declined, showing a trend toward later marriage and greater reproductive agency.\u003c/p\u003e \u003cp\u003eThis study adds significant insights to earlier research on India's fertility transition. The study adopts a macro-demographic approach, examining country fertility trends from 1950 to 2021 and forecasting to 2024. Second, it considers a number of issues, including education, contraceptive use, urbanization, and environmental factors, proving, for example, that women with higher levels of education have fewer children.Third, the case study of Andhra Pradesh demonstrates a higher reduction (TFR about 1.5 and a 17% drop in general fertility rate), highlighting regional variances that are obscured by national averages. Fourth, the comparative machine learning technique extensively investigates linear regression, random forest, support vector machines, and XGBoost. XGBoost has the lowest error values (RMSE\u0026thinsp;=\u0026thinsp;0.23, MAE\u0026thinsp;\u0026asymp;\u0026thinsp;0.18), indicating significant promise for demographic forecasting. The paper discusses the policy implications for population aging, dependency, and future labor supply. Machine learning can assist in combining demographic studies with evidence-based policymaking at the national and subnational levels.\u003c/p\u003e"},{"header":"4. Factors Contributing to Declining Fertility in India","content":"\u003cp\u003eThe decline in India\u0026rsquo;s total fertility rate is not attributable to a single cause but reflects a complex interplay of socioeconomic, healthcare, cultural, and environmental factors.\u003c/p\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003e4.1 Socio-Economic Factors\u003c/h2\u003e \u003cp\u003eFertility drop is primarily driven by socioeconomic progress. Rapid urbanization has changed lifestyles and increased the expense of housing, schooling, and childcare, driving couples to choose smaller families (Womb IVF \u0026amp; Fertility Centre, n.d.). Increased female literacy and education have enabled women to postpone marriage and childbearing, engage in paid job, and make educated fertility decisions. NFHS-5 statistics demonstrate a strong educational gradient: women with 12 or more years of schooling have a TFR of about 1.7\u0026ndash;1.8, compared to roughly 2.8-3.0 for women without education. (Roy, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2022\u003c/span\u003e).Earlier research has also found that higher levels of female education and lower child mortality are substantially linked to fertility drop throughout Indian districts (Chaudhury, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e1996\u003c/span\u003e). At the same time, changing ambitions for greater living standards and job progress have diminished the perceived benefits of large family sizes (Vajiram \u0026amp; Ravi, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2025\u003c/span\u003e).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003e4.2 HealthCare and Family Planning\u003c/h2\u003e \u003cp\u003eHealthcare and family planning improvements have been particularly important. The national prevalence of modern contraceptives has increased from 54% in NFHS-4 to 67% in NFHS-5 (Ministry of Health and Family Welfare, 2021). According to Roy (\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2022\u003c/span\u003e), contemporary contraceptive use among Muslims increased from 37.9% to 47.4% between NFHS 4 and 5. Improved maternal and child health care have reduced infant and under-five mortality rates, reducing the need for multiple births to ensure survival (Chaudhury, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e1996\u003c/span\u003e).The eSanjeevani telemedicine platform has enhanced access to counseling and reproductive health information, allowing for more educated family planning decisions (Press Information Bureau, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2023\u003c/span\u003e).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003e4.3 Social norms and government Policies\u003c/h2\u003e \u003cp\u003eChanges in social standards have also contributed to decreasing fertility. Rising gender equality and changing media depictions of work and family have led to an increasing acceptance of delayed marriage, smaller families, and child-free lives (Financial Times, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). Population strategies, which were formerly focused on slowing rapid development, are gradually shifting to concerns about both high and low fertility. Some governments have debated or implemented two-child norms for public office eligibility, citing concerns about demographics and labor availability (Roy, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Vajiram \u0026amp; Ravi, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2025\u003c/span\u003e).\u003c/p\u003e \u003c/div\u003e"},{"header":"5. Regional Variations in fertility Rates","content":"\u003cp\u003eThe national decline in fertility masks substantial regional disparities, with Indian states broadly grouped into high- and low-fertility clusters.\u003c/p\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003e5.1 States with high Fertility Rates\u003c/h2\u003e \u003cp\u003eAccording to recent NFHS 5 and official statistics (International Institute for Population Sciences, 2021; Ministry of Health and Family Welfare, 2021), states like Bihar (TFR about 3.0), Uttar Pradesh (2.4), Jharkhand (2.3), and Madhya Pradesh (2.0) continue to have fertility rates at or above replacement level.Chaudhury (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e1996\u003c/span\u003e) suggests that poorer female literacy, increased child mortality, cultural norms favoring early marriage, and restricted access to modern contraception all contribute to the continuance of this issue.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003e5.2 States with low fertility rates\u003c/h2\u003e \u003cp\u003eIn contrast, states like Punjab (TFR around 1.6), West Bengal (1.6), Andhra Pradesh (around 1.7), Kerala (1.4), and Tamil Nadu (1.4) have fertility rates that are substantially below the replacement threshold. High female literacy, long-standing investments in health and education, successful family planning programs, increasing urbanization, and cultural preference for smaller families all contribute to early and prolonged fertility drop (Chaudhury, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e1996\u003c/span\u003e).Low fertility states face significant demographic issues, including labor shortages, in-migration from higher fertility regions, and population aging.\u003c/p\u003e \u003c/div\u003e"},{"header":"6. Case Study: Declining Fertility Trends in Andhra Pradesh","content":"\u003cp\u003eAndhra Pradesh exhibits the dramatic drop in birth rates in certain Indian states. The state's general fertility rate has plummeted by around 17% over the last decade, and the crude birth rate has dropped from 18.2 to 16.2 live births per thousand inhabitants; its total fertility rate, at about 1.5 in 2019\u0026ndash;2020, is significantly lower than the national average (Times of India, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2022\u003c/span\u003e).Education is important: women with no formal schooling have a TFR of roughly 2.3, whereas those with higher secondary education and above have a TFR of around 1.2, demonstrating how educational empowerment effects reproductive choice. Proactive family planning efforts, increased urbanisation, rising living costs, and a trend toward later marriage are all contributing factors.\u003c/p\u003e \u003cp\u003eThis demographic achievement has resulted in significant policy issues. Authorities are now dealing with the consequences of decreasing population growth, an aging population structure, and a projected increase in dependence ratios. In response, state-level debates have emerged on revising earlier population control measures, including proposals to relax two-child conditions for electoral eligibility and introduce positive incentives for larger families, indicating a broader reorientation of population policy (The Economic Times, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2024\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"7. Crude Birth Rate Trends in India","content":"\u003cp\u003eThe Crude Birth Rate (CBR) confirms the TFR trends. Nationally, the CBR declined from 29.5 in 1991 to 20.4 in 2016, with a large rural-urban disparity (rural: 22.1; urban: 17.0) (Womb IVF \u0026amp; Fertility Center. (n.d.)). States with high TFRs also have high CBRs, such as Bihar's rural CBR of 27.7. Conversely, states with low fertility have low CBRs, with Kerala's rural CBR at 14.3 and Himachal Pradesh's urban CBR as low as 10.5 (Census of India, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2011\u003c/span\u003e). This regional variance highlights the unevenness of India's demographic shift.\u003c/p\u003e"},{"header":"8. ML-Based Fertility Prediction and Model Evaluation","content":"\u003cp\u003eIn addition to demographic and survey analysis, this study uses machine learning (ML) to anticipate fertility trends in India. A linear regression model was initially constructed using historical total fertility rate (TFR) data from 1950 to 2021 to generate baseline forecasts for 2024. Three non-linear algorithms\u0026mdash;random forest, XGBoost, and support vector regression\u0026mdash;were tested to see if more flexible models increase predictive performance.\u003c/p\u003e \u003cp\u003eModel accuracy was assessed using root mean squared error (RMSE) and mean absolute error (MAE), which calculate the average size of prediction errors between observed and anticipated fertility levels. These metrics are commonly employed in regression and demographic forecasting since they are expressed in the same units as the outcome and are susceptible to systematic prediction biases. Figure\u0026nbsp;5\u003cb\u003e.1\u003c/b\u003e demonstrates that the XGBoost model outperformed linear regression, random forest, and support vector regression in terms of prediction accuracy, with an RMSE of roughly 0.23 and MAE of about 0.18. To help validate the model, projected TFR values from XGBoost were compared to observed fertility rates over time.\u003c/p\u003e \u003cp\u003eXGBoost, a more advanced machine learning algorithm, outperforms linear regression as a baseline for short-term fertility forecasts. Recent demographic applications have shown that gradient-boosting algorithms may accurately anticipate birth numbers and related population indices. XGBoost and comparable models are thus interesting tools for policy planning and demographic scenario analysis in rapidly changing situations such as India.\u003c/p\u003e"},{"header":"9. Conclusion and Future Implications","content":"\u003cp\u003eIndia's demographic transition is a watershed moment, representing significant advances in health, education, and women's empowerment. The TFR's decrease to below replacement level represents a shift toward population stabilization, which could boost per-capita resource allocation and economic growth.\u003c/p\u003e \u003cp\u003eHowever, this achievement has ushered in a new set of obstacles. The rapid drop will undoubtedly result in an older population, a diminishing workforce over time, and an increasing old-age dependence ratio, all of which will put a strain on pension systems and healthcare facilities.\u003c/p\u003e \u003cp\u003eFuture policy must be nuanced and adaptive. It is recommended that India:\u003c/p\u003e \u003cp\u003e \u003col\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eInvest in Human Capital\u003c/b\u003e: Enhance education and skill development to maximize the productivity of the current working-age population.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eStrengthen Social Security Systems\u003c/b\u003e: Develop robust, inclusive pension and healthcare systems to support a growing elderly population.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003ePromote Gender Equality\u003c/b\u003e: Further increase female labour force participation to offset a shrinking working- age cohort.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eAdopt Region-Specific Strategies\u003c/b\u003e: Tailor policies to address the specific needs of states, from strengthening family planning in high-fertility regions to designing aged-care policies in low-fertility regions.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eUphold Reproductive Rights\u003c/b\u003e: Ensure that any pronatalist discussions, as seen in Andhra Pradesh, remain focused on choice and incentives rather than coercive measures.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003c/ol\u003e \u003c/p\u003e \u003cp\u003eIn conclusion, India's demographic future is no longer defined by the challenge of runaway growth but by the complex task of managing the consequences of its success. Navigating this new demographic reality will require foresight, strategic planning, and a commitment to inclusive development.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eAI\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eArtificial Intelligence\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eAP\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eAndhra Pradesh\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eCBR\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eCrude Birth Rate\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eCPR\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eContraceptive Prevalence Rate\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eGFR\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eGeneral Fertility Rate\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eIVF/IUI\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eIn Vitro Fertilization / Intrauterine Insemination\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eLR\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eLinear Regression\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eMAE\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eMean Absolute Error\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eML\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eMachine Learning\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eNFHS\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eNational Family Health Survey\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eRF\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eRandom Forest\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eRMSE\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eRoot Mean Squared Error\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eSVM\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eSupport Vector Machine\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eTFR\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eTotal Fertility Rate\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003eXGBoost\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eExtreme Gradient Boosting\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors have declared that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot relevant. This study did not require ethics approval or informed consent as it used secondary, publically available, and de-identified data.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data utilized in this study were obtained from publically available sources, such as the National Family Health Survey, the Indian Census, and international demographic databases indicated in the References.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eArora A (2021), November 25 In a first, India\u0026rsquo;s fertility rate falls below replacement level: What it means. India Today. Retrieved from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.indiatoday.in/india/story/india-fertility-rate-declines-replacement-level-meaning-nfhs-survey-1880894-2021-11-25\u003c/span\u003e\u003cspan address=\"https://www.indiatoday.in/india/story/india-fertility-rate-declines-replacement-level-meaning-nfhs-survey-1880894-2021-11-25\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCensus of India (2011) Vital statistics. Office of the Registrar General \u0026amp; Census Commissioner, India\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChaudhury RH (1996) Factors affecting variations in fertility by states of India: A preliminary investigation. Asia-Pacific Popul J 11(2):59\u0026ndash;68\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFinancial Times (2025), February 23 Why are birth rates falling? With Alice Evans. Financial Times. Retrieved from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.ft.com/content/cef1c8b4-b278-425a-88b4-99d37bd4439b\u003c/span\u003e\u003cspan address=\"https://www.ft.com/content/cef1c8b4-b278-425a-88b4-99d37bd4439b\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGunnal GS, Akhil PM, Gharge S (2020), December 21 Contraceptive use among women rises in western states, Goa tops the charts: NFHS-5 data. Down To Earth. Retrieved from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.downtoearth.org.in/health/contraceptive-use-among-women-rises-in-western-states-goa-tops-the-charts-nfhs-5-data-7471\u003c/span\u003e\u003cspan address=\"https://www.downtoearth.org.in/health/contraceptive-use-among-women-rises-in-western-states-goa-tops-the-charts-nfhs-5-data-7471\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHalli SS, Madise NJ (2019) \u0026amp; others. Fertility and family planning in Uttar Pradesh: Trends and determinants\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eInternational Institute for Population Sciences (IIPS) (2021) National Family Health Survey (NFHS-5), 2019\u0026ndash;21: Andhra Pradesh fact sheet. IIPS, Mumbai\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKumar A, Devi R, Singh M (2023) Spatial and temporal variations in fertility in India: An analysis of NFHS-5 and SRS data\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePress Information Bureau (2023), February 16 Union Health Minister Dr. Mansukh Mandaviya hails the eSanjeevani landmark milestone of providing telemedicine services to more than 10 crore patients. Government of India. Retrieved from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.pib.gov.in/PressReleasePage.aspx?PRID=1899855\u003c/span\u003e\u003cspan address=\"https://www.pib.gov.in/PressReleasePage.aspx?PRID=1899855\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRoy E (2022), May 8 NFHS-5 data: Total fertility rate dips, steepest decline among Muslims. The Indian Express. Retrieved from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://indianexpress.com/article/india/fertility-falling-in-all-communities-steepest-decline-among-muslims-nfhs-data-7906994/\u003c/span\u003e\u003cspan address=\"https://indianexpress.com/article/india/fertility-falling-in-all-communities-steepest-decline-among-muslims-nfhs-data-7906994/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThe Economic Times (2024), February 16 Andhra Pradesh plans cash reward for having more children, says CM Chandrababu Naidu. The Economic Times. Retrieved from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://economictimes.indiatimes.com/news/india/andhra-pradesh-plans-cash-reward-for-having-more-children-says-cm-chandrababu-naidu/articleshow/121726486.cms\u003c/span\u003e\u003cspan address=\"https://economictimes.indiatimes.com/news/india/andhra-pradesh-plans-cash-reward-for-having-more-children-says-cm-chandrababu-naidu/articleshow/121726486.cms\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTimes Now News. (n.d.). India\u0026rsquo;s fertility rate drops from 6.2 to under 2 since 1950: Lancet study. Times Now. Retrieved August 27 (2025) from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.timesnownews.com/health/indias-fertility-rate-drops-from-6-2-to-under-2-since-1950-lancet-study-article-10870592\u003c/span\u003e\u003cspan address=\"https://www.timesnownews.com/health/indias-fertility-rate-drops-from-6-2-to-under-2-since-1950-lancet-study-article-10870592\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTimes of India (2022), October 8 Fertility rate decreases by 17% in a decade in Andhra Pradesh. The Times of India. Retrieved from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://timesofindia.indiatimes.com/city/visakhapatnam/fertility-rate-decreases-by-17-in-a-decade-in-andhra-pradesh/articleshow/94715026.cms\u003c/span\u003e\u003cspan address=\"https://timesofindia.indiatimes.com/city/visakhapatnam/fertility-rate-decreases-by-17-in-a-decade-in-andhra-pradesh/articleshow/94715026.cms\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTimes of India (2023), February 29 India\u0026rsquo;s declining fertility rate: Is it a cause of concern? The Times of India. Retrieved from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://timesofindia.indiatimes.com/life-style/health-fitness/health-news/indias-declining-fertility-rate-is-it-a-cause-of-concern/articleshow/115936225.cms\u003c/span\u003e\u003cspan address=\"https://timesofindia.indiatimes.com/life-style/health-fitness/health-news/indias-declining-fertility-rate-is-it-a-cause-of-concern/articleshow/115936225.cms\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVajiram, Ravi (2025), January 19 Why are fertility levels declining in India? Vajiram \u0026amp; Ravi Current Affairs. Retrieved August 27, 2025, from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://vajiramandravi.com/current-affairs/fertility-rate-in-india/\u003c/span\u003e\u003cspan address=\"https://vajiramandravi.com/current-affairs/fertility-rate-in-india/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWikipedia contributors. (n.d.). List of states and union territories of India by fertility rate. In Wikipedia, The Free Encyclopedia. Retrieved August 27 (2025) from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://en.wikipedia.org/wiki/List_of_states_and_union_territories_of_India_by_fertility_rate\u003c/span\u003e\u003cspan address=\"https://en.wikipedia.org/wiki/List_of_states_and_union_territories_of_India_by_fertility_rate\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWomb IVF (2025) \u0026amp; Fertility Center. (n.d.). Decline in fertility rate in India: Causes \u0026amp; solutions. Retrieved August 27, from \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.wombivf.com/decline-in-fertility-rate-causes-and-solutions/\u003c/span\u003e\u003cspan address=\"https://www.wombivf.com/decline-in-fertility-rate-causes-and-solutions/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"B V Raju College","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"fertility decline, machine learning, demographic forecasting, total fertility rate, India, regional disparities","lastPublishedDoi":"10.21203/rs.3.rs-8829613/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8829613/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis research uses machine learning to anticipate fertility drop in India from 1950\u0026ndash;2021, utilizing data from National Family Health Surveys, Census of India, and worldwide demographic datasets. The study focuses on fertility trends, regional differences, and socioeconomic variables in Andhra Pradesh. Fertility indicators such as total fertility rate, general fertility rate, and crude birth rate are studied with variables such as female education, urbanization, and contraception use. Four models (linear regression, random forest, support vector machines, and XGBoost) are trained on historical fertility data to forecast short-term until 2024. XGBoost is the most accurate forecaster, indicating a sustained drop in fertility, especially in low fertility states.The findings emphasize both the social and health benefits of decreased fertility, as well as emerging difficulties such as population aging, labor supply, and reliance. The study highlights the importance of integrating machine learning and demographic data for evidence-based policy planning in a constantly changing population context.\u003c/p\u003e","manuscriptTitle":"Unveiling India's Fertility Decline Trajectory: Hybrid ML Models for Accurate Long-Term Forecasts","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-10 08:45:56","doi":"10.21203/rs.3.rs-8829613/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"83011948-56bf-4366-bb1e-a75e3191c3b4","owner":[],"postedDate":"February 10th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-10T08:45:57+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-10 08:45:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8829613","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8829613","identity":"rs-8829613","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}