DEVELOPING A DIAGNOSTIC TOOL AND TIME SERIES ANALYSIS IN RESPECT OF SOYBEAN ARRIVALS AND PRICES

Abstract

“India is an agriculture based country, so appropriate distribution of marketing related information of agricultural commodities throughout the nation is essential in today’s scenario. The AGMARKNET portal is the leading step taken by the Directorate of Marketing and Inspection, Ministry of Agriculture and Farmer Welfare, Government of India, with the target of collecting, cleaning and distributing marketing related information of agricultural commodities throughout the country. This information is of utmost importance in nature as it can be used by various stakeholders, such as farmers, traders and policy makers among others, to make important decisions at individual as well as national level. It also aims to strengthen the economic position of farmers as well as consumers by providing them with marketing related information of agricultural commodities spanning over all the markets in the country”. Such information will let the farmers get fair returns on their crops. “For consumers, it means that they will be able to obtain agricultural commodities at fair and affordable prices”. Two main objectives of this study. “First, to develop a diagnostic for major markets where Soybean arrivals are high. This diagnostic tool will help the concerned stakeholders to have various checks on the entire process of data entry. Thereby, improving the data quality by monitoring the data reporting process continuously. Statistical Process Control (SPC) can help the correct reporting of data”. Microsoft Excel 2013 was used for diagnostic tool development.The second objective of the study is to forecast the modal prices of Soybean for a particular variety using time series modelling. “Data filtering, sorting and cleaning are the essential tasks conducted as part of this process. The time series modelling has been attempted to forecast Soybean prices in 2017. Microsoft Excel 2013 and ETS forecasting in R (language) have been used for time series analysiS.