Moth bean price forecasting in churu market of Rajasthan: A comparison of Arima and Ann models

Abstract

The fluctuations in market arrivals largely contribute to price instability. Analysis of price and market arrivals overtime is important for formulating a sound agricultural policy. Such an analysis is also helpful to farmers in deciding the suitable time for disposing off their farm produce to their best advantage. In view of this, the present study was undertaken by collecting monthly prices of moth bean [Vigna aconitifolia (Jacq.) Marechan] in Churu Regulated Market (a major moth bean market) of Rajasthan for a period of 11 years (2002 to 2012). Price of moth bean was found to be the highest during off season and the lowest during the harvest season. The purpose of this study was also to compare the forecasting performances of different time series methods for forecasting moth bean prices. The various forms of Auto Regressive Integrated Moving Average (ARIMA) Time Series Model and Artificial Neural Network (ANN) were employed to predict the future prices of moth bean in Churu market. On comparing the alternative models, it was observed that Mean Absolute Deviation, MAD (1.07), Mean Square Error, MSE (11974.53) and Mean Absolute Percent Error, MAPE (3.86) were the least for ARIMA (0, 1, 2) model. The validity of the forecasted price values of moth bean was checked by comparing them with their actual market price values during the post sample forecast period i.e. June, 2012 to December, 2012 for moth bean crop and observed an accuracy of 95 to 97 per cent between actual and forecasted value. Therefore, ARIMA (0, 1, 2) model was considered the most suitable model for price forecasting of moth bean in Churu Regulated Market of Rajasthan.