Abstract Forecasting stock index prices is a key indicator that helps investors and financial analysts make better decisions that maximize profits while minimizing risks. In order to succeed, a robust engine with the capacity to distribute important information is necessary. In this study, a grasshopper-optimized integrated deep convolutional feedforward neural network (IDCFNN+GOA) is employed to increase stock market forecasting accuracy. Using performance indicator and a hypothesis test (paired t-test), the effect of the IDCFNN+GOA model on forecasting the subsequently day's closing price of several stock indices is examined. By combining data from the COVID-19 epidemic, the stock indexes are taken into account. The efficacy of the suggested strategy is evaluated in comparison to current stock market price prediction systems. The simulation results show that the IDCFNN+GOA model may be used to forecast the next day's finishing price.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|