Analysis and Prediction of Elderly Sports Participation using Artificial Neural Networks and Logistic Regression Models

Abstract Background Korea's aging population and the lack of participation in sports by the elderly are increasing medical expenses. This study aimed to segment elderly sports participants based on their demographic characteristics and exercise practice behavior and applies artificial neural network and logistic regression models to these segments in order to best predict the effect of medical cost reduction. It presents strategies for elderly sports participation. Methods A sample comprising data on 1,770 elderly people aged 50 years and above, drawn from the 2019 National Sports Survey were used. The data were analyzed through frequency analysis, hierarchical and K-means clustering, artificial neural network, logistic regression, and cross-tabulation analyses, as well as one-way ANOVA using SPSS 23 and Modeler 14.2. The participants were divided into five clusters. Results The artificial neural network and logistic analysis models showed that the cluster comprising married women in their 60s who participated in active exercise had the highest possibility of reducing medical expenses. Conclusions Targeting women in their 60s who actively participate in sports The government should expand the supply of local gymnasiums, community centers, and sports programs. Thus, if local gymnasiums and community centers run sports programs and appoint appropriate sports instructors, the most effective medical cost reduction effect can be obtained.