Design and Modeling of Stock Market Forecasting Using Hybrid Optimization Techniques

In this paper, an artificial neural network-based stock market prediction model was developed. Today, a lot of individuals are making predictions about the direction bond, currency, equity, and markets. Forecasting fluctuations in values is quite difficult for businesspeople industries. future value changes on markets exceedingly since there so many different economic, political, psychological factors at play. Stock forecasting also endeavour it depends various known unknown variables. There several ways used to try anticipate share price, including technical analysis, fundamental time series statistical analysis; however, none these approaches has been shown be consistently reliable tool. We built three alternative Adaptive Neuro-Fuzzy Inference System (ANFIS) models compare outcomes. The average tuned create ensemble model. Although comparable applications have attempted literature, data set extremely work with because only contains sharp peaks falls no seasonality. study, fuzzy c-means clustering, subtractive grid partitioning all used. experiments we ran were designed assess effectiveness construction techniques our ANFIS models. When evaluating outcomes, metrics R-squared mean standard error mostly taken into consideration. experiments, over.90 attained.