Understanding Older Adults’ Intention to Adopt Digital Leisure Services: The Role of Psychosocial Factors and AI-Based Prediction Models

<b>Background/Objective</b>: As the global aging population grows, digital leisure services have emerged as a potential solution to improve older adults' social engagement, cognitive stimulation, and overall well-being. However, their adoption remains limited because of digital literacy gaps, psychological barriers, and varying levels of adaptability. This study aims to analyze and predict older adults' intention to adopt digital leisure services by integrating psychosocial factors, demographic characteristics, and digital adaptability using artificial intelligence (AI)-based predictive models. <b>Methods:</b> This study utilized data from the 2022 Urban Policy Indicator Survey conducted in Seoul, South Korea, selecting 2239 individuals aged 50 years and above. A two-step clustering approach was employed: hierarchical clustering estimated the optimal number of clusters, and K-means clustering finalized the segmentation. An artificial neural network (ANN) model was applied to predict the likelihood of digital leisure adoption by incorporating demographic and psychosocial variables. Logistic regression was used for validation, and model performance was assessed through accuracy, precision, recall, and F1-score. <b>Results:</b> Four distinct clusters were identified based on digital adaptability and social media engagement. Cluster 3 (highly educated males in their 60s with family support) showed the highest probability (84.35%) of digital leisure adoption despite low social media engagement. Cluster 4 (older women with high social media usage) exhibited lower adaptability to structured digital services. The ANN model achieved an overall classification accuracy of 85.2%, highlighting digital adaptability as a key determinant for adoption. <b>Conclusions</b>: These findings underscore the need for targeted policy interventions, including tailored digital education programs, intergenerational digital training, and simplified platform designs to enhance digital accessibility. Future research should further explore psychological factors influencing digital adoption and validate AI-based predictions using real-world behavioral data.