Journal Article

Stock Market Trading Based on Market Sentiments and Reinforcement Learning

S. Kumar, Ashok, Sankar, Syam, M. Ameen Suhail, K., E. Abd El-Samie, Fathi, F. Soliman, Naglaa, D. Algarni, Abeer, El-Shafai, Walid, Nestor, Tsafack

2022

Overview

Stock market is a place, where shares of different companies are traded. It is a collection of buyers’ and sellers’ stocks. In this digital era, analysis and prediction in the stock market have gained an essential role in shaping today's economy. Stock market analysis can be either fundamental or technical. Technical analysis can be performed either with technical indicators or through machine learning techniques. In this paper, we report a system that uses a Reinforcement Learning (RL) network and market sentiments to make decisions about stock market trading. The system uses sentiment analysis on daily market news to spot trends in stock prices. The sentiment analysis module generates a unified score as a measure of the daily news about sentiments. This score is then fed into the RL module as one of its inputs. The RL section gives decisions in the form of three actions: buy, sell, or hold. The objective is to maximize long-term future profits. We have used stock data of Apple from 2006 to 2016 to interpret how sentiments affect trading. The stock price of any company rises, when significant positive news become available in the public domain. Our results reveal the influence of market sentiments on forecasting of stock prices.

• Publisher: Tech Science Press
• Subject: Data mining / Decision analysis / Economic forecasting / Machine learning / Modules / News / Pricing / Public domain / Securities markets / Sentiment analysis