Authors : Basen Marndi; Mamita Majhi; Bharati Induar; Surekha Patra

Volume/Issue : Volume 11 - 2026, Issue 5 - May

Google Scholar : https://tinyurl.com/2k638zj2

Scribd : https://tinyurl.com/yx3h94xa

DOI : https://doi.org/10.38124/ijisrt/26May1750

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Stock market forecasting has become an important research area in financial engineering because market prices are influenced by uncertain, nonlinear, and highly dynamic factors. Conventional statistical forecasting approaches often experience limitations when dealing with complex financial datasets containing volatility and irregular fluctuations. To overcome these challenges, intelligent computational models have gained significant attention in recent years. This paper presents an intelligent stock market prediction framework using the Adaptive Neuro-Fuzzy Inference System (ANFIS), which integrates the adaptive learning capability of Artificial Neural Networks (ANN) with the uncertainty-handling mechanism of Fuzzy Logic Systems (FLS). The proposed model utilizes historical stock market indicators including opening price, closing price, highest price, lowest price, and trading volume for prediction analysis. The collected data are preprocessed and supplied to the ANFIS architecture for training and testing operations. Gaussian membership functions and hybrid learning algorithms are employed to optimize the fuzzy inference parameters and improve forecasting performance. The prediction efficiency of the developed system is evaluated using statistical performance metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). Experimental observations indicate that the ANFIS-based forecasting model can effectively learn nonlinear financial patterns and provide improved prediction accuracy compared with conventional statistical techniques. The adaptive nature of the system enables efficient handling of uncertainty, noise, and market volatility present in stock market datasets. The study demonstrates that ANFIS can serve as a reliable computational intelligence tool for financial forecasting, investment analysis, and decision-support applications in dynamic market environments.

Keywords : Stock Market Prediction, ANFIS, Artificial Intelligence, Fuzzy Logic, Neural Networks, Financial Forecasting, MATLAB, Time-Series Analysis.

References :

1. S. Haykin, Neural Networks and Learning Machines, 3rd ed. New York, NY, USA: Pearson Education, 2009.
2. C. M. Bishop, Pattern Recognition and Machine Learning. New York, NY, USA: Springer, 2006.
3. L. A. Zadeh, “Fuzzy sets,” Information and Control, vol. 8, no. 3, pp. 338–353, 1965.
4. J.-S. R. Jang, “ANFIS: Adaptive-network-based fuzzy inference system,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, no. 3, pp. 665–685, 1993.
5. T. Takagi and M. Sugeno, “Fuzzy identification of systems and its applications to modeling and control,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-15, no. 1, pp. 116–132, 1985.
6. G. E. P. Box, G. M. Jenkins, and G. C. Reinsel, Time Series Analysis: Forecasting and Control, 4th ed. Hoboken, NJ, USA: Wiley, 2008.
7. A. Abraham, “Neuro-fuzzy systems: State-of-the-art modeling techniques,” in Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence, Berlin, Germany: Springer, 2001, pp. 269–276.
8. R. Eberhart and J. Kennedy, “Particle swarm optimization,” in Proc. IEEE Int. Conf. Neural Networks, Perth, WA, Australia, 1995, pp. 1942–1948.