Stock market data modelling using fitness-oriented JAYA algorithm-based deep belief network

Abstract

Purpose

Data mining plays a major role in forecasting the open price details of the stock market. However, it fails to address the dimensionality and expectancy of a naive investor. Hence, this paper aims to study a future prediction model named time series model is implemented.

Design/methodology/approach

In this model, the stock market data are fed to the proposed deep neural networks (DBN), and the number of hidden neurons is optimized by the modified JAYA Algorithm (JA), based on the fitness function. Hence, the algorithm is termed as fitness-oriented JA (FJA), and the proposed model is termed as FJA-DBN. The primary objective of this open price forecasting model is the minimization of the error function between the modeled and actual output.

Findings

The performance analysis demonstrates that the deviation of FJA–DBN in predicting the open price details of the Tata Motors, Reliance Power and Infosys data shows better performance in terms of mean error percentage, symmetric mean absolute percentage error, mean absolute scaled error, mean absolute error, root mean square error, L1-norm, L2-Norm and Infinity-Norm (least infinity error).

Research limitations/implications

The proposed model can be used to forecast the open price details.

Practical implications

The investors are constantly reviewing past pricing history and using it to influence their future investment decisions. There are some basic assumptions used in this analysis, first being that everything significant about a company is already priced into the stock, other being that the price moves in trends

Originality/value

This paper presents a technique for time series modeling using JA. This is the first work that uses FJA-based optimization for stock market open price prediction.

Citation

Swamy, A.K. and B., S. (2020), "Stock market data modelling using fitness-oriented JAYA algorithm-based deep belief network", Kybernetes, Vol. 49 No. 9, pp. 2309-2334. https://doi.org/10.1108/K-12-2018-0660