A FLANN and RBF with PSO Viewpoint to Identify a Model for Competent Forecasting Bombay Stock Exchange

Asif Perwej, Yusuf Perwej (), Nikhat Akhtar and Firoj Parwej
Additional contact information
Yusuf Perwej: Al-Baha University
Nikhat Akhtar: BBD University
Firoj Parwej: Singhania University

Post-Print from HAL

Abstract: Forecasting is the process of computation in unknown situations from the historical data. Financial forecasting and planning is usually an essential part of the business plan, and would be done as part of setting up the organization and receive funds. Financial forecasting and planning is also an essential activity to confirm a good management, keeping the organization financially sound is a key objective. The prediction of stock market has been a long time tempting topic for researchers from different fields. Stock analysts use various forecasting methods to determine how a stock's price will move in the ensuing day. The purpose of this paper is to explore the radial basis function (RBF) and function linked artificial neural network (FLANN) algorithms for forecasting of financial data. We have based our models on data taken and compared those using historical data from the Bombay Stock Exchange (BSE). The RBF and FLANN parameters updated by Particle swarm optimization (PSO). In this paper, we have examined this algorithm on a number of various parameters including error convergence and the Mean Average Percentage Error (MAPE) and comparative assessment of the RBF and FLANN algorithms is done. The proposed method indeed can help investors consistently receive gains. Finally, a simple merchandise model is established to study the accomplishment of the proposed prediction algorithm against other criterion.

Keywords: Function Linked Artificial Neural Network (FLANN); Multi Branch Neural Network (MBNN); Forecasting; Particle Swarm optimization (PSO); Bombay Stock Exchange (BSE); Radial Basis Function (RBF) (search for similar items in EconPapers)
Date: 2015
Note: View the original document on HAL open archive server: https://hal.science/hal-03362994
References: View complete reference list from CitEc
Citations:

Published in COMPUSOFT An international journal of advanced computer technology, 2015, IV (I), pp.1454-1461

Downloads: (external link)
https://hal.science/hal-03362994/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-03362994

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().