Investigating the Impact of Age and Education on Delay Discounting: A Predictive Random Forest Model for Personalized Marketing and Mental Health Risk Detection

This study uses a random forest model to predict delay discounting rates, aiming to support mental health interventions and personalized marketing strategies. Delay discounting refers to the tendency to prefer smaller immediate rewards over larger delayed rewards, a behavior closely linked to impulsivity and relevant in both psychological and commercial contexts. Data from Garofalo et al., including 357 healthy Italian adults categorized by age and education level, were used. Two-way ANOVA showed that education significantly influences delay discounting rates, while age does not. The model was utilized to anticipate delay discounting behaviors influenced by various factors. The random forest algorithm reached an impressive accuracy rate of 92%, showing particular proficiency in forecasting both high and low delay discounting classifications. Additionally, the model successfully pinpointed individuals whose actual discounting rates diverged significantly from the predictions, offering crucial insights for proactive mental health interventions. Based on the predictions, personalized strategies were recommended for individuals with different delay discounting rates, demonstrating the value of this predictive model in the fields of mental health and commercial marketing.