Journal ID : AMA-01-12-2022-11849
[This article belongs to Volume - 53, Issue - 12]
Total View : 428

Title : Univariate Time series Methods for Forecasting Cotton Prices: A Comparative Analysis

Abstract :

Cotton is a commodity, which is perhaps the most volatile among all the agricultural commodities traded. Due to high volatility in cotton prices, it is very difficult to predict the future market trend. Fluctuations in market arrivals largely contribute to price instability. Such an analysis is also useful for farmers in order to decide the suitable time to disposing off their produce to their best advantage. In view of this the present study was undertaken by collecting monthly prices of Cotton in major Cotton markets of Gujarat for a period of 18 years (2003 to 2022). The various forms of ARIMA (Box-Jenkins model), Artificial Neural Network (ANN) and Exponential Smoothing models were employed to predict the future prices of cotton in Amerali market of Gujarat. Among all the models tried, the Box-Jenkins ARIMA model was found best fit as compared to the other models. Thus, it was the most representative model for the price forecast of cotton in Amreli market of Gujarat. The developed model can be used as a policy instrument for the producers and sellers. And also, market Intelligence of Agri commodities was considered highly useful knowledge inputs for small and marginal farmers of India and strong need for exclusive Agri market intelligence through media channels was suggested.

Full article