Development of Stock Market Price Application to Predict Purchase and Sales Decisions Using Proximal Policy Optimization Method

Abstract

Stocks are an investment that many investors choose because stocks are able to provide attractive returns. Stock market prices experience fluctuating changes in stock prices from one time to another. Stocks use indicators from technical analysis to evaluate stocks in order to predict stock market price movements. The fluctuation of stock market price fluctuations affects the decision to buy and sell shares where these decisions do not occur every day. In this research, we used deep reinforcement learning algorithm called as the Proximal Policy Optimization method to predict stock buying and selling decisions. The decision to buy and sell shares affects profits. The data used are indicators of technical analysis and historical data. The Proximal Policy Optimization method allows to develop automatic buy and sell decision via iterative policy optimization based on previous sample data to reduce sample complexity. Proximal Policy Optimization method generates rewards to maximize profit. The results of this research indicate that the cumulative profit during the last one year from the results of our deep reinforcement learning approach is an increase compared to the cumulative profit by manual decision approach.