Ensembled Time Series Deep Learning Framework for Stock Market Prediction

Abstract

Prediction and analysis of Stock Market plays a very important and crucial role in today's economic growth. Understanding the pattern of these financial activity and predicting its transformation and development are the most challenging areas of research in financial sectors and academic sectors. This paper explores the competency of sequential learning elements viz. long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM) and gated recurrent unit (GRU) with different depths and combinations in forecasting the share market trend from the Nifty50 dataset. The experimental assessment elucidates that the ensemble prediction model built using BiLSTM-LSTM and BiLSTM-GRU by the virtue of integrating the merits of BiLSTM and LSTM/GRU layers demonstrate a better performance closer to reality with least error.