Stock Prediction by Ensembling LSTM Using AdaBoost Algorithm

M. Mariprabhu, R. Niranjana, R. Praveen Kumar and V. Jananee

The stocks are the share of the ownership of a company. These stocks are evaluated in order to determine the future activities of an instrument, sector or market. In order to determine the growth of the company the stock analysis and prediction is done. Mostly the analysts are interested in research area of stock prediction. Prediction systems which are effective for stock market help traders and investors to provide information about the future of the stock markets. In this work, we present a Long Short-Term Memory (LSTM) a derivative of Recurrent Neural Network (RNN) approach in order to predict stock market indices. The prediction of the market value is important in order to help in maximize profit and it reduces risk. Recurrent neural networks (RNN) is one of the most powerful models for sequential data. Long Short-Term memory is one of the most successful derivatives of RNNs architectures. LSTM has the memory cell, a unit of computation that replaces old artificial data in the hidden layer of the network. These two are boosted with the AdaBoost algorithm so that the prediction can be more effective.

Volume 12 | 05-Special Issue

Pages: 977-980

DOI: 10.5373/JARDCS/V12SP5/20201844