Expropriation risks and innovation: Estimating the relationship between corruption and innovation inputs and outputs using machine learning

Expropriation risks and innovation: Estimating the relationship between corruption and innovation inputs and outputs using machine learning | 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 Expropriation risks and innovation: Estimating the relationship between corruption and innovation inputs and outputs using machine learning Claudio Bravo Ortega, Pablo Egana-delSol, Bronwyn Hall, Jose Miguel Benavente This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8147768/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 We develop a growth-theoretic framework to analyze how expropriation risk, exemplified by corruption, affects innovation incentives at the country level. Our model, building on Romer (1990), predicts that higher expropriation risk reduces R&D expenditure, diminishes the share of human capital engaged in R&D, lowers patenting and scientific publication rates, and slows technical progress and economic growth. We test these predictions using a novel dataset spanning nearly two decades and apply a machine learning-based instrumental variable approach – IV-LASSO – to address endogeneity in corruption. Our empirical results provide robust evidence that greater corruption (i.e., higher expropriation risk) significantly hampers innovation inputs (lower R&D spending and research personnel) and innovation outputs (fewer patent applications, scientific publications, and a lower Economic Complexity Index). These findings underscore the detrimental impact of corruption on innovation and highlight the importance of strong institutions and anti-corruption policies to foster innovation-led economic development. JEL Classification: O30, O43 innovation corruption R&D expropriation patents economic development Full Text Additional Declarations No competing interests reported. Supplementary Files AppendixNov2025.pdf 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-8147768","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":557872933,"identity":"481a15c3-17b1-470b-9c67-c69c018e96f3","order_by":0,"name":"Claudio Bravo Ortega","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYDACdiDmMWBgMADzKhgY2BgYGA/g1cKMouUMWAsDEVoYoFoY2yCCeLXwNzM/k3hTYMNgLn34mcTHeYfl+RiYH+DVInGYzUxyjkEag2VfmpnkzG2HDdsY2AzwajFgZjCT5jE4zGBwhsHYmHfbYaDbePA7zICZ/RtUC/tnY945h+2J0MIDs4XH8DFvw+FEglokDvMUWwL9wmPZw1P4cMax9OQ2ZgJ+4W9v33jjzR8bOXMe9g0HPtRY285vb374AJ8WGOBBMJmJUT8KRsEoGAWjAC8AAMTSPq1TmB5CAAAAAElFTkSuQmCC","orcid":"","institution":"Adolfo Ibáñez University","correspondingAuthor":true,"prefix":"","firstName":"Claudio","middleName":"Bravo","lastName":"Ortega","suffix":""},{"id":557872934,"identity":"83f4f99b-1798-4356-9d4c-baefef1a4bb2","order_by":1,"name":"Pablo Egana-delSol","email":"","orcid":"","institution":"Adolfo Ibáñez University","correspondingAuthor":false,"prefix":"","firstName":"Pablo","middleName":"","lastName":"Egana-delSol","suffix":""},{"id":557872935,"identity":"a6c33c91-8d52-4a1f-ae54-cc1168f55452","order_by":2,"name":"Bronwyn Hall","email":"","orcid":"","institution":"University of California, Berkeley","correspondingAuthor":false,"prefix":"","firstName":"Bronwyn","middleName":"","lastName":"Hall","suffix":""},{"id":557872936,"identity":"c3150a45-7f34-4d2e-bc90-c5761f0c96b5","order_by":3,"name":"Jose Miguel Benavente","email":"","orcid":"","institution":"Production Development Corporation","correspondingAuthor":false,"prefix":"","firstName":"Jose","middleName":"Miguel","lastName":"Benavente","suffix":""}],"badges":[],"createdAt":"2025-11-18 16:53:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8147768/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8147768/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97957405,"identity":"4e291074-9da2-40ee-9820-7f68d7a730f1","added_by":"auto","created_at":"2025-12-11 08:18:11","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":104069,"visible":true,"origin":"","legend":"","description":"","filename":"ExpropriatiowAuthorsNovfinalCLEAN.docx","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/2645afc32dc8f1f5c27bef06.docx"},{"id":97957406,"identity":"9327c53c-285f-4425-9825-0e8c6acc7659","added_by":"auto","created_at":"2025-12-11 08:18:11","extension":"json","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5997,"visible":true,"origin":"","legend":"","description":"","filename":"e1de6c72da074edc8e1b254a9dd2e351.json","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/e1879e72a1c2f61566df6068.json"},{"id":98422508,"identity":"bf6a23d0-c0f6-463b-8b7b-bc9e7f633693","added_by":"auto","created_at":"2025-12-17 16:31:10","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":375939,"visible":true,"origin":"","legend":"","description":"","filename":"AppendixNov2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/12a8d67d79f061a5c567ab06.pdf"},{"id":98422829,"identity":"09afc901-fbbe-4abe-acc8-babaefa4d058","added_by":"auto","created_at":"2025-12-17 16:31:33","extension":"xml","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":162026,"visible":true,"origin":"","legend":"","description":"","filename":"e1de6c72da074edc8e1b254a9dd2e3511enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/922c52bc10ac11937556d08e.xml"},{"id":98423346,"identity":"407950ad-33bb-41b7-a58c-d932f4a8cd98","added_by":"auto","created_at":"2025-12-17 16:32:08","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":402288,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/e97c217fedde49921c0f11fb.jpeg"},{"id":98423407,"identity":"61fa2a89-b922-4b0e-9b7a-5ab5c6cd8938","added_by":"auto","created_at":"2025-12-17 16:32:11","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16458,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/edadd779d7f23b73bfd06d5b.png"},{"id":98422573,"identity":"b51a669c-ff38-4ec7-9c75-9e1ae15899e4","added_by":"auto","created_at":"2025-12-17 16:31:12","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":74730,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/0cc092a95be71ae8a124864f.png"},{"id":97957413,"identity":"c59fd5b7-1aba-4399-b5f8-d8eec79ea0f4","added_by":"auto","created_at":"2025-12-11 08:18:11","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8452,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/a8606db9d194ee732634c1a9.png"},{"id":97957409,"identity":"dd76ee24-dc46-4638-9a7c-1d9a47817b78","added_by":"auto","created_at":"2025-12-11 08:18:11","extension":"xml","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":156230,"visible":true,"origin":"","legend":"","description":"","filename":"e1de6c72da074edc8e1b254a9dd2e3511structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/72c12e5bac7975eb3f43233f.xml"},{"id":97957416,"identity":"66322edb-2b78-4356-a70d-b06af5521006","added_by":"auto","created_at":"2025-12-11 08:18:11","extension":"html","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":175368,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/f4f0ccc637a8caa5edb506ff.html"},{"id":102296047,"identity":"6f4c5cdf-170b-4118-97d0-754be581c08a","added_by":"auto","created_at":"2026-02-10 10:16:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":677063,"visible":true,"origin":"","legend":"","description":"","filename":"ExpropriatiowAuthorsNovfinalCLEAN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1_covered_2c050f58-9473-4b2c-ae09-dce1098534a6.pdf"},{"id":98422752,"identity":"6f89aec0-9b12-4f05-8f8f-9ec18a6ff6e5","added_by":"auto","created_at":"2025-12-17 16:31:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":375939,"visible":true,"origin":"","legend":"","description":"","filename":"AppendixNov2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8147768/v1/139b6d02f4f3ac2e56c16b3e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Expropriation risks and innovation: Estimating the relationship between corruption and innovation inputs and outputs using machine learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"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":"innovation, corruption, R\u0026D, expropriation, patents, economic development","lastPublishedDoi":"10.21203/rs.3.rs-8147768/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8147768/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWe develop a growth-theoretic framework to analyze how expropriation risk, exemplified by corruption, affects innovation incentives at the country level. Our model, building on Romer (1990), predicts that higher expropriation risk reduces R\u0026amp;D expenditure, diminishes the share of human capital engaged in R\u0026amp;D, lowers patenting and scientific publication rates, and slows technical progress and economic growth. We test these predictions using a novel dataset spanning nearly two decades and apply a machine learning-based instrumental variable approach – IV-LASSO – to address endogeneity in corruption. Our empirical results provide robust evidence that greater corruption (i.e., higher expropriation risk) significantly hampers innovation inputs (lower R\u0026amp;D spending and research personnel) and innovation outputs (fewer patent applications, scientific publications, and a lower Economic Complexity Index). These findings underscore the detrimental impact of corruption on innovation and highlight the importance of strong institutions and anti-corruption policies to foster innovation-led economic development.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eJEL Classification: \u003c/strong\u003eO30, O43\u003c/p\u003e","manuscriptTitle":"Expropriation risks and innovation: Estimating the relationship between corruption and innovation inputs and outputs using machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-11 08:18:06","doi":"10.21203/rs.3.rs-8147768/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":"8f7a59b3-222f-4175-b7fd-091296745ae6","owner":[],"postedDate":"December 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-07T08:24:59+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-11 08:18:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8147768","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8147768","identity":"rs-8147768","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}