Chronological penguin Adam-based deep long short-term memory classifier for stock market prediction

Abstract

This paper proposes an effective method named chronological penguin Adam-based deep long short-term memory (CPAdam-based deep LSTM) to forecast the future prices in the stock market. Initially, the technical indicators are extracted from the stock market input data, and the wrapper approach is used to select the suitable features. Then, the deep long short-term memory (deep LSTM) classifier performs the stock market prediction based on the memory cell-associated, which acts as an accumulator to store the state information. The deep LSTM classifier is trained by the proposed CPAdam algorithm, which is developed by integrating the features of the chronological concept, PeSOA, and Adam optimisation algorithm. The experimentation is performed using two datasets, namely Reliance Communications, and Relaxo Footwear, in which the proposed CPAdam-based deep LSTM offers better performance using dataset 2 in terms of the metrics, like MSE, prediction accuracy, RMSE, return-per trade, and winning rate.