Enhanced ANN training model to smooth and time series forecast

Abstract

In the present era most of the researchers has done extensive research in forecasting the time series data using distinct "linear, nonlinear and hybrid linear models"that combines models like "Auto Regressive Integrated Moving Average (ARIMA)"using "Artificial Neural Networks (ANN)"by combining the "Time Series Forecasting (TSF)". In this paper we proposed a new algorithm which will smooth the data and evaluate the error rate to obtain time series predictions by considering Telangana state rainfall dataset. Our experimental illustrations propose that the results attained are statistically promising with the datasets that are used for generating the acceptable prediction result set.