An Efficient Model for Stock Price Prediction Using Soft Computing Approach

Abstract

The analysis and prediction of stock market
trends play a pivotal role in financial decision-making
and profit generation. In this paper, we explore the
efficacy of an Adaptive Neuro-Fuzzy Inference System
(ANFIS) model for stock market prediction and compare
its results with existing methodologies.
The design of ANFIS can be viewed as an optimization
problem aimed at minimizing error functions by
identifying optimal parameters. To enhance the
performance of ANFIS, we propose a novel approach
that combines the Firefly Algorithm with the Adaptive
Neuro-Fuzzy Inference System. This integrated scheme
involves training the fuzzy neural network model using
the Firefly Algorithm and applying it to predict stock
prices within the Vietnam Stock Market.
Experimental evaluations entail comparing the
performance of our proposed system against ANFIS
models trained using alternative optimization algorithms
such as the Hybrid Algorithm, Back Propagation, and
Particle Swarm Optimization (PSO). Through rigorous
experimentation, we demonstrate the efficiency of our
proposed system in predicting stock market trends.
Moreover, in this thesis, we conduct an empirical
analysis using the Adaptive Neuro-Fuzzy Inference
System (ANFIS) model for stock market prediction,
followed by a comparative assessment of its
performance against other techniques. The evaluation
utilizes published stock market data from the National
Stock Exchange of India Ltd. for validation purposes.