Andere Kunden interessierten sich auch für
![Neural Networks to predict Impact energy of functionally graded steels]( "Neural Networks to predict Impact energy of functionally graded steels")
Neural Networks to predict Impact energy of functionally graded steels32,99 €![Artificial Neural Networks for Modeling TWTAs in Satellites]( "Artificial Neural Networks for Modeling TWTAs in Satellites")
Artificial Neural Networks for Modeling TWTAs in Satellites46,99 €![Deep Insight Navigating the Neural Networks of Image Restoration]( "Deep Insight Navigating the Neural Networks of Image Restoration")
Deep Insight Navigating the Neural Networks of Image Restoration39,99 €![Nonlinear Correlation between Prime Indian and American Stock Market]( "Nonlinear Correlation between Prime Indian and American Stock Market")
Nonlinear Correlation between Prime Indian and American Stock Market26,99 €![Enhancing The Explainability of Neural Network]( "Enhancing The Explainability of Neural Network")
Enhancing The Explainability of Neural Network51,99 €![Artificial neural network model for prediction of crop evapotranspiration]( "Artificial neural network model for prediction of crop evapotranspiration")
Artificial neural network model for prediction of crop evapotranspiration36,99 €![Complex-Valued Neural Networks: Learning Algorithms and Applications]( "Complex-Valued Neural Networks: Learning Algorithms and Applications")
Complex-Valued Neural Networks: Learning Algorithms and Applications40,99 €
Since stock markets are volatile, dynamic and complicated, forecasting stock market return is considered as a challenging task. Nevertheless, researchers have developed various linear and nonlinear methods for effective forecasting. Among these neural networks are most suitable for forecasting non linear and chaotic relationships among variables. The current study attempts to forecast the future returns of B.S.E, highly volatile index, with the help of conventional method i.e. ARIMA (Auto Regression Integrated Moving Average) and Artificial Neural Network M.L.P (Multilayer Perceptron).To examine the efficiency of the models, MAD (Mean Absolute Deviation) and MSE (Mean Square Error) of the two models are compared. The study results revealed that neural network is better for forecasting in comparison to ARIMA.