Improving the effectiveness of financial education programs. A targeting approach

We investigate whether targeting algorithms can improve the effectiveness of financial education programs by identifying ex-ante the most appropriate recipients. To this end, we use micro-data from around 3800 individuals who participated in a financial education campaign conducted in Italy in late 2021. First, we employ machine learning (ML) tools to devise a targeting rule that identifies individuals who should be primarily targeted by a financial education campaign based on easily observable characteristics. Second, we simulate a policy scenario, using a random sample of individuals who took part in the campaign but were not employed to devise the targeting rule. We find that pairing a financial education campaign with an ML-based targeting rule leads to greater effectiveness. Finally, we discuss the policy implications of our findings, and the conditions that must be met for ML-based targeting to be effectively implemented.