Background
Price forecasting of perishable crop like vegetables has importance implications to the farmers, traders as well as consumers. Timely and accurate forecast of the price helps the farmers switch between the alternative nearby markets to sale their produce and getting good prices. The farmers can use the information to make choices around the timing of marketing. For forecasting price of agricultural commodities, several statistical models have been applied in past but those models have their own limitations in terms of assumptions.
Methods
In recent times, Machine Learning (ML) techniques have been much successful in modeling time series data. Though, numerous empirical studies have shown that ML approaches outperform time series models in forecasting time series, but their application in forecasting vegetables prices in India is scared. In the present investigation, an attempt has been made to explore efficient ML algorithms e.g. Generalized Neural Network (GRNN), Support Vector Regression (SVR), Random Forest (RF) and Gradient Boosting Machine (GBM) for forecasting wholesale price of Brinjal in seventeen major markets of Odisha, India.
Results
An empirical comparison of the predictive accuracies of different models with that of the usual stochastic model i.e. Autoregressive integrated moving average (ARIMA) model is carried out and it is observed that ML techniques particularly GRNN performs better in most of the cases. The superiority of the models is established by means of Model Confidence Set (MCS), and other accuracy measures such as Mean Error (ME), Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Prediction Error (MAPE). To this end, Diebold-Mariano test is performed to test for the significant differences in predictive accuracy of different models.
Conclusions
Among the machine learning techniques, GRNN performs better in all the seventeen markets as compared to other techniques. RF performs at par with GRNN in four markets. The accuracies of other techniques such as SVR, GBM and ARIMA are not up to the mark.
The COVID-19 pandemic has impacted almost all the sectors including agriculture in the country. The present paper investigates the impact of COVID-19 induced lockdown on both wholesale and retail prices of major pulses in India. The daily wholesale and retail price data on five major pulses namely Lentil, Moong, Arhar, Urad and Gram are collected for five major markets in India namely Delhi, Mumbai, Kolkata, Chennai and Hyderabad during the period January, 2019 to September, 2020 from Ministry of Consumer Affairs, Food & Public Distribution, Government of India. The Government of India declared nationwide lockdown since March, 24, to May, 31, 2020 in different phases in order to restrict the spread of the infection due to COVID-19. To see the impact of lockdown on price and price volatility, time series model namely Autoregressive integrated moving average (ARIMA) model with error following Generalized autoregressive conditional heteroscedastic (GARCH) model incorporating exogenous variable as lockdown dummy in both mean as well variance equations. It is observed that in almost all the markets, lockdown has significant impact on price of the pulses whereas in few cases, it has significant impact on price volatility.
Wavelet decomposition in signal processing has been widely used in the literature. The popularity of machine learning (ML) algorithms is increasing day by day in agriculture, from irrigation scheduling and yield prediction to price prediction. It is quite interesting to study wavelet-based stochastic and ML models to appropriately choose the most suitable wavelet filters to predict agricultural commodity prices. In the present study, some popular wavelet filters, such as Haar, Daubechies (D4), Coiflet (C6), best localized (BL14), and least asymmetric (LA8), were considered. Daily wholesale price data of onions from three major Indian markets, namely Bengaluru, Delhi, and Lasalgaon, were used to illustrate the potential of different wavelet filters. The performance of wavelet-based models was compared with that of benchmark models. It was observed that, in general, the wavelet-based combination models outperformed other models. Moreover, wavelet decomposition with the Haar filter followed by application of the random forest (RF) model gave better prediction accuracy than other combinations as well as other individual models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.