Does managing a retirement portfolio via rate of return, Sharpe ratio and social interaction generate good returns? An analysis for the years 2017 to 2020

Motivated by the economic context, the social security reform in Brazil, and the behavior of Brazilian individual investors in the retirement-fund market, this study designs an algorithm to manage a real retirement-fund portfolio. In our model, the theoretical manager of the fund can allocate its resources among four securities belonging to the same financial institution: two fixed income funds; and two private credit funds. Innovatively, the machine learning algorithm optimizes the portfolio allocation using reinforcement learning, which rewards good decisions and punishes bad decisions based on individual and social criteria. The algorithm presented a consistent and stable performance in all the six scenarios of simulation, outperforming the actual portfolio and s random strategy by considerable and significant average returns.