Method to Recommend the Investment Portfolio with the Mix of Various Schemes and Options Using Reinforcement Learning

Abstract

AbstractIn today’s scenario, everybody wants to invest their money wisely to get high returns. Unfortunately, a plan that gives you high returns with low risks does not exist. However, to minimize the overall risk and to maximize the chance of high returns, it is recommended to diversify your investment portfolio in such a way that investment is done in multiple asset classes and securities. Diversification does not always help because it ensures low risk but cannot predict returns. Nowadays, machine learning is widely used in stock trading to predict and recommend actions to buy, sell, or hold. This is mostly restricted to a particular asset type such as equity. In general, we are likely to invest in different types of investment options, such as fixed deposits, mutual funds, equity, house, and so on. Therefore, it is wise to build a machine learning model which can recommend an investment portfolio across all investment options for an investor based on his/her expected returns and risk level. In this paper, we propose a machine learning model based on reinforcement learning that can continuously learn the emerging trend of each investment type and recommend reallocation of assets to increase return on investment (ROI).KeywordsReallocate investment portfolioReinforcement learningRecommend investment portfolio