Indian Commodity Market Price Comparative Study of Forecasting Methods - A Case Study on Onion, Potato and Tomato

Abstract

In this study several characteristics are taken into account so that the crop price forecast is accurate. Forecasting the price of agriculture commodities based on Volume, diesel price helps the agriculturist and also the agriculture mandi’s in India. We look at onion, tomato, and potato trading in India and present the evaluation of a price forecasting model, and anomaly detection and compared differently Supervised, Unsupervised and Forecasting prediction models. We prefer to use wholesale prices, retail prices, arrival volumes of the agricultural commodities and Diesel prices in India. We also provide an in-depth forecasting analysis of the effect on these retail prices. Our results are encouraging and point towards the likelihood of building pricing models for agricultural commodities and to detect anomalies. These data can then be stored and analyzed. The empirical comparison of the chosen methods on the various data showed that some methods are more suitable than others for this type of problem. In this research, we did a comparative study of Auto ARIMA (Autoregressive Integrated Moving Average), RNN (Recurrent Neural Network), LSTM, VAR (vector autoregressive model), and Random Forest Regression, XGBoost in their ability to predict Retail prices of potatoes, onions and tomatoes.