Abstract: In this paper, recent years neural networks have received an increasing amount of attention among macroeconomic forecasters. India has experienced persistently high inflation in recent years, despite a period of below-trend economic growth. The two main factors of inflation in India are the Wholesale Price Index (WPI) and the Consumer Price Index (CPI). Inflation rates in India are usually quoted as changes in the Wholesale Price Index for all commodities. The WPI and CPI data used for estimating the models for the period Jan 2016 to Dec 2020. However, various tests indicate that there is little evidence that the improvement in forecasting accuracy is statistically significant. The absolute mean error and mean absolute percent error were also lower for the neural network models. RMSE, MAE and MAPE are used for the comparison of the models. Result of this study shows that RNN is performing better than the other models ARIMA in forecasting the Inflation rate in India.

Keywords: ARIMA, Neural networks, RNN, Inflation, WPI, CPI, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE).

| DOI: 10.17148/IARJSET.2021.8616