Title: An empirical hybrid DBN-EL system model for stock market prediction with big data

Authors: Ishwarappa; J. Anuradha

Addresses: School of Computer Science and Engineering, Vellore Institute of Technology, Vellore – 632014, Tamil Nadu, India ' School of Computer Science and Engineering, Vellore Institute of Technology, Vellore – 632014, Tamil Nadu, India

Abstract: Recent years, big data analytics have become the prominent aspect for different sectors for the prediction of large datasets. The stock market is also the important exertions in the field of business in which big data play an important role for the prediction of stocks. For this reason, the big data and hybrid deep belief network-ensemble learning (DBN-EL) model is proposed for analysis of large stock market data in order to improve the performance of its prediction. Here, the Hive based distributed database with MapReduce technique for storing and mapping of data into other for fast processing. Furthermore, the hybrid DBN-EL system model will be used as classifier for stock market prediction. The stock futures dataset is used for analysis. The simulation results shows that the proposed model outperforms by predicting the stock futures trend upto 98% when compared with other existing techniques in terms of precision, recall, and F-measure.

Keywords: stock market prediction; DBN; deep belief network; EL; ensemble learning; NSE; National Stock Exchange; big data; MapReduce.

DOI: 10.1504/IJSSE.2021.121433

International Journal of System of Systems Engineering, 2021 Vol.11 No.3/4, pp.284 - 300

Received: 06 Jul 2020
Accepted: 21 Sep 2020
Published online: 14 Mar 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article