Deep Learning Based Models: Basic LSTM, Bi LSTM, Stacked LSTM, CNN LSTM and Conv LSTM to Forecast Agricultural Commodities Prices

The literature argues that an accurate price prediction of agricultural goods is a quintessence to assure a good functioning of the economy all over the world. Research reveals that studies with application of deep learning in the tasks of agricultural price forecast on short historical agricultural prices data are very scarce and insist on the use of different methods of deep learning to predict and to this reaction of filling the gap, this study employs five versions of LSTM deep learning techniques for the task of five agricultural commodities prices prediction on univariate time series dataset of Rice, Wheat, Gram, Banana, and Groundnut spanning January 2000 to July 2020. The study obtained good forecasting results for all five commodities employing all the five LSTM models. The study validated the results with lower values of error metrics, MAE, MAPE, MSE, and RMSE and two paired t-test with hypothesis and confidence level of 95% as a measure of robustness. The study predicted the one month ahead future price for all the five commodities and compared it with actual prices using said LSTM models and obtained promising results.

Assessing the Sensitivity of Global Maize Price to Regional Productions Using Statistical and Machine Learning Methods

Agricultural price shocks strongly affect farmers' income and food security. It is therefore important to understand and anticipate their origins and occurrence, particularly for the world's main agricultural commodities. In this study, we assess the impacts of yearly variations in regional maize productions and yields on global maize prices using several statistical and machine-learning (ML) methods. Our results show that, of all regions considered, Northern America is by far the most influential. More specifically, our models reveal that a yearly yield gain of +8% in Northern America negatively impacts the global maize price by about –7%, while a decrease of –0.1% is expected to increase global maize price by more than +7%. Our classification models show that a small decrease in the maize yield in Northern America can inflate the probability of maize price increase on the global scale. The maize productions in the other regions have a much lower influence on the global price. Among the tested methods, random forest and gradient boosting perform better than linear models. Our results highlight the interest of ML in analyzing global prices of major commodities and reveal the strong sensitivity of maize prices to small variations of maize production in Northern America.

Has Agricultural Price Policy Benefitted Paddy Farmers?

This chapter looks at the impact of support price policy on the income from paddy crop. Markets for agricultural produces in India are mostly unorganized and distorted where farmers are often scrupulously exploited. Also since the elasticity of demand for agricultural commodities particularly foodgrains is less than unit, increased production during bumper harvest brings down the prices of agricultural commodities sharply. But, the support price provided to paddy has come under severe scrutiny for various reasons in recent years. Farmers have been demanding for higher support price for paddy but some economists argue that increase in paddy price is ‘dirty economics and dirtier politics’. With the help of time series data, chapter 4 provides an elegant analysis whether the support price scheme has helped paddy cultivating farmers in terms of increasing their income.

Systemic Risk in Global Agricultural Markets and Trade Liberalization under Climate Change: Synchronized Crop-Yield Change and Agricultural Price Volatility

Climate change will increase simultaneous crop failures or too abundant harvests, creating global synchronized yield change (SYC), and may decrease stability in the portfolio of food supply sources in agricultural trade. This study evaluated the influence of SYC on the global agricultural market and trade liberalization. The analysis employed a global computable general equilibrium model combined with crop models of four major grains (i.e., rice, wheat, maize, and soybeans), based on predictions of five global climate models. Simulation results show that (1) the SYC structure was statistically robust among countries and four crops, and will be enhanced by climate change, (2) such synchronicity increased the agricultural price volatility and lowered social welfare levels more than expected in the random disturbance (non-SYC) case, and (3) trade liberalization benefited both food-importing and exporting regions, but such effects were degraded by SYC. These outcomes were due to synchronicity in crop-yield change and its ranges enhanced by future climate change. Thus, SYC is a cause of systemic risk to food security and must be considered in designing agricultural trade policies and insurance systems.

International price volatility transmission and structural change: a market connectivity analysis in the beef sector

Despite the abundance of literature on agricultural price transmissions and unexpectedly disrupted value chains from infectious disease outbreaks such as bovine spongiform encephalopathy and COVID-19, the importance of research on price connectivity in the international beef markets has largely been ignored. To assess agricultural price transmission issues, error correction-type models (ECMs) have been predominantly employed. These models, however, suffer a deficiency in that the method is incapable of depicting time-variant linkages between prices. This article examines the connections between global and local prices, as well as price volatility in the beef sector. Our analysis uses a generalised autoregressive conditional heteroscedasticity (GARCH) model with the dynamic conditional correlation (DCC) specification that enables us to identify market connection intensity dynamics. We pay assiduous attention to structural changes in the overall research processes to enhance the reliability of estimation. For the first time in meat or grain price transmission research, our autoregressive models have been developed with structural break dummy variables for DCC. The principal findings are that (1) local retail prices for Azerbaijan, Georgia, Japan, Kazakhstan, Kyrgyzstan, Tajikistan and the UK showed a structural change in mean or variance, all of which were identified after the global food crisis from 2007–2009, (2) international prices unidirectionally Granger-cause regional prices in Georgia, Tajikistan and the United States in both mean and volatility (accordingly, no country exhibited price or price-volatility transmission from regional to international markets), and (3) volatility liaisons between global and local beef markets are generally weak, but price volatility exhibited closer synchronisation around the 2008 global food crisis, which created structural changes during the period. This finding implies that national governments should shield domestic from global markets by implementing trade restrictions such as quotas or taxes in a global emergency.