Novel Adaptive Neuro Fuzzy Inference Modeling Algorithms for Predicting Equity Prices and Indices

Computer Science

Equity markets are considered as dynamic entities behaving in complex manner posing a challenging problem to equity forecasters. Traditional equity market forecasting is based on fundamental and technical analysis. Adoption of neural networks to forecast equity prices have been applied by many, however with shortcomings Recent studies focus on the use of artificial intelligence and machine learning; deploying methods such as artificial neural networks or genetic algorithms. Deployment of ensemble models, which combine the outputs of different machine learning algorithms, is also a common approach in machine learning. Adaptive Neuro fuzzy inference system (ANFIS) is a hybrid technique that integrates the advantage of learning in an Artificial Neural Network (ANN) and using a set of fuzzy if-then rules with appropriate membership functions to generate input-output pairs with a high degree of accuracy which is built on top of Fuzzy Sets and Fuzzy Modelling. ANFIS is a powerful tool for prediction, and this method has applications in prediction of stock prices. The study was done between 4/2017 to 5/2022.ANFIS model is used to predict closing prices of a few stocks and NIFTY index.

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