A Jaya Algorithm Trained Neural Network for Stock Market Prediction
Puspanjali Mohapatra1, Reeva Mishra2, Tapas Kumar Patra3
1Puspanjali Mohapatra, Department of Computer Science and Engineering, International Institute of Information Technology (IIIT), Bhubaneswar (Odisha), India.
2Reeva Mishra, Department of Computer Science and Engineering, International Institute of Information Technology (IIIT), Bhubaneswar (Odisha), India.
3Tapas Kumar Patra, Department of Electronics and Instrumentation Engineering, College of Engineering and Technology (CET), Bhubaneswar (Odisha), India.
Manuscript received on 15 August 2018 | Revised Manuscript received on 27 August 2018 | Manuscript published on 30 November 2018 | PP: 9-13 | Volume-7 Issue-11, August 2018 | Retrieval Number: K25170871118/18©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper demonstrates how the two types of FLANN models (Functional link artificial neural network models) i.e. Chebyshev-FLANN (CFLANN) and Trigonometric-FLANN (TFLANN) are trained using Jaya algorithm to predict the Stock Market Indices. The intention of the current paper is putting forward a contrast between popular training algorithms such as Back Propagation (BP) and Jaya algorithm. The BP and Jaya algorithm trained FLANN models are examined for predicting stock indices for a day and a week ahead. The stock indices BSE500, DJIA and NASDAQ with few technical indicators are taken as inputs in this experimental time series data. The study confirms the superiority of Jaya algorithm trained FLANN models to the traditional BP trained FLANN models. The Mean Square Error (MSE) and Mean Absolute Percentage Error (MAPE) are used for performance evaluation. The simulation study is done using python3 in Anaconda environment.
Keyword: Stock Market Prediction, BP, Jaya algorithm, MAPE, MSE
Scope of the Article: Marketing and Social Sciences