AN IMPROVISED METHOD USING NEURO-FUZZY SYSTEM FOR FINANCIAL TIME SERIES FORECASTING
Abstract
Financial time series forecasting is crucial for making informed investment decisions. This study proposes an improvised method utilizing a Neuro-Fuzzy System (NFS) for enhanced forecasting accuracy. Traditional forecasting methods often struggle with the nonlinear and dynamic nature of financial time series data. NFS integrates neural network and fuzzy logic techniques, offering a robust framework for modeling complex relationships within financial data. The proposed method employs NFS to adaptively learn and model the intricate patterns present in financial time series data. It combines the strengths of neural networks in learning complex patterns and fuzzy logic in handling uncertainty and imprecision. This study contributes by introducing an innovative approach to financial time series forecasting, leveraging the capabilities of NFS to improve forecasting accuracy and reliability. Experimental results demonstrate the effectiveness of the proposed method in accurately forecasting financial time series data. The method outperforms traditional forecasting techniques, showcasing its potential for practical applications in financial markets.

Authors
Mohd. Asif Gandhi1, S.M. Lekshmi Sri2, Bhanu Pratap Singh3, Zahir Aalam4, Subharun Pal5
Anjuman-I-Islam’s Kalsekar Technical Campus, India1, Dr. J.J. Magdum College of Engineering, India2, Auro University, India3, Thakur College of Engineering and Technology, India4, Indian Institute of Technology, Jammu, India5

Keywords
Financial Time Series Forecasting, Neuro-Fuzzy System, Forecasting Accuracy, Adaptive Learning, Complex Patterns
Yearly Full Views
JanuaryFebruaryMarchAprilMayJuneJulyAugustSeptemberOctoberNovemberDecember
000250000000
Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 14 , Issue: 4 , Pages: 3328 - 3333 )
Date of Publication :
April 2024
Page Views :
49
Full Text Views :
7

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.