STOCK MARKET PREDICTION SYSTEM USING ML

Abstract

The stock market is highly volatile and complex innature. Technical analysts often apply Technical Analysis (TA) to historical price data, which is an exhaustive task and might produce incorrect predictions. Machine learning coupled with fundamental and/or Technical Analysis also yields satisfactory results for stock market prediction. In this work, the effort is made to predict the price and price trend of stocks by applying optimal Long Short Term Memory (O- LSTM) deep learning and adaptive Stock Technical Indicators (STIs). We also evaluated the model for taking a buy-sell decision at the end of the day. To optimize the deep learning task we utilized the concept of Correlation-Tensor built with appropriate STIs. The tensor with adaptive indicators is passed to the model for better more and accurate prediction. The results are analyzed using popular metrics and comparedwith two benchmark ML classifiers and a recent classifier based on deep learning. The mean prediction accuracy achieved using the proposed model is 59.25%, over the number of stocks, which is much higher than benchmark approaches.