Deep-Reinforcement Learning-Based Architecture for Multi-Objective Optimization of Stock Prediction

Abstract

Artificial Intelligence has been established to predict the future performance of the trading in modern era including Statistics, Computer Science, and economics, especially the stack market. By analyzing the big data, making the financial decision is important for investors in the stock market. As records, several techniques like Back Propagation Neural Network (BPNN) Recurrent Neural Network (RNN) are used to predict the stock price but due to its computation complexity is major challenging of time serious financial data in the decision-making process. In this paper, we have proposed the Recurrent Q Network Learning (RQNL) to make the right decision according to movements of stock prices as reliable attention. To overcome the computational complexity shortcoming, the forgotten memory is developed in a neural network. In this way, the error arousal is pruned in a significant manner. In addition, Enhancing the prediction ability is outstanding, and reinforcement learning is demonstrated to reduce the correlations in time series data. Discussion and evaluation were based on the NSE dataset are experimented with three different learning approaches, with the proposed method for stock prediction of financial markets. The experiment result carried out that our proposed Recurrent Q Network Learning (RQNL) performs the perfect prediction compared with other existing learning.