Forecasting spot prices of agricultural commodities in India: Application of deep‐learning models

Manogna, R L; Mishra, Aswini Kumar

doi:10.1002/isaf.1487

Cited by 45 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the financialization of products, several studies have examined how products are linked together (Rl and Mishra, 2021)). Products markets need an understanding of oil and energy products fundamentals (Umar et al, 2021).…”

Section: Literature Reviewmentioning

confidence: 99%

Integrating the Role of Green Fiscal Policies With Energy Prices Volatility and Energy Efficiency: Presenting a COVID-19 Perspective

et al. 2022

View full text Add to dashboard Cite

Energy and other related sectors are changing in China. This study attempted to estimate the energy product price volatility with energy efficiency during COVID-19 with the role of green fiscal policies. For this, we applied unit-root tests, ADCC-GARCH, and CO-GARCH techniques to infer the study findings. The results showed that energy price volatility was significantly connected until 2018. More so, the green fiscal policies were significantly connected between energy product price volatility and energy efficiency during COVID-19 (2019–2020). From energy products, the crude oil price volatility was significant at 16.4%, heating oil volatility was significant at 18.2%, natural oil price volatility was 9.7%, gasoline price volatility was 28.7%, and diesel price volatility was 34.1% significant with energy efficiency, due to the intervening role of green fiscal policies. The findings of this study are robust in comparison to previous studies. Multiple stakeholders can take guidelines from the findings of the recent study. As per our best understanding and knowledge, if suggested recommendations are implemented effectively, these results will help to enhance energy efficiency through green fiscal policies in the post-COVID period.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Integrating the Role of Green Fiscal Policies With Energy Prices Volatility and Energy Efficiency: Presenting a COVID-19 Perspective

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Fishe et al (2014) analyze the daily data of several agricultural futures positions to confirm the positive correlation between price changes and the positions of managed money firms. Additionally, financial traders are seen to reduce long positions to absorb risk during crisis (Singleton, 2014; Manogna and Mishra, 2021b). Creti et al (2013) investigate the correlation between S&P 500 and commodities using Dynamic Conditional Correlation-Generalized AutoRegressive Conditional Heteroscedasticity (DCC-GARCH) model for 25 commodity spot prices to reveal the consolidated linkage between stock and commodity markets when financial markets are stressed.…”

Section: Review Of Literaturementioning

confidence: 99%

Financialization of Indian agricultural commodities: the case of index investments

Mishra

2021

IJSE

Self Cite

View full text Add to dashboard Cite

PurposeThe phenomenon known as financialization of commodities, arising from the speculation in commodity derivatives market, has raised serious concerns in the recent past. This has prompted distortion in agricultural commodity prices driving them away from rational levels of supply and demand shocks. In the backdrop of financialized commodities leading to increase in price of agricultural products and their interaction with equity markets, the authors examine the investment of institutional investors in impacting the agricultural returns. The paper aims to focus on the financial mechanism that drives extreme values and the mean of agricultural returns.Design/methodology/approachThe authors employ the Threshold AutoRegressive Quantile (TQAR) methodology to find evidence of linkages between the Indian agricultural and equity markets from January 2010 to May 2020 consistent with the rise in inflows of institutional investors in agricultural markets.FindingsThe results reveal that the investors impact the agricultural commodity markets strongly when the composite commodity index value (COMDEX) is low. Additionally, in the lower extreme quantiles (0.25) of agricultural returns, the integration between the equity index and agricultural returns is found to be highly significant compared to insignificant values in the higher quantiles (0.75 and 0.95) in both the regimes. The results suggest that low values of agricultural commodities are more closely linked to equity indices when composite commodity index value is low. This implies that, at the lower quantiles of COMDEX return (bad day), the investors move to the stock market. In that way, the commodity index returns are seen to be as a strong channel for the financialization of Indian agricultural commodities and suggesting potential involvement of investors during those regime.Research limitations/implicationsRegulators need to anticipate the price fluctuations in spot and futures markets. Investors in commodity markets need to strengthen risk awareness to carry out portfolio strategies.Practical implicationsFrom policy perspective, it is of pivotal importance to enhance the understanding of the financialization of agricultural products. The findings provide reference measures to stabilize the commodity markets, alleviate price distortions and carry out further evidence of price discovery and risk management in Indian commodity markets.Originality/valueTo the best of the authors’ knowledge, this study is the first to highlight the potential influence of financial markets on the financialization of agricultural commodities in an emerging economy like India.

show abstract

“…Common econometric models for commodity price forecasting include the autoregressive moving average, vector autoregressive, and vector error correction models. Recently, machine learning techniques (Bayona‐Oré et al, 2021), such as the neural network (Fang et al, 2020; Ribeiro & Oliveira, 2011), deep learning (Manogna & Mishra, 2021), extreme learning (Kouadio et al, 2018), genetic programming (Ali et al, 2018), support vector regression (Harris, 2017; Li, Chen, et al, 2020), K‐nearest neighbor (Gómez et al, 2021), multivariate adaptive regression splines (Dias & Rocha, 2019), random forest (Gómez et al, 2021), decision tree (Harris, 2017), ensemble (Fang et al, 2020), and boosting methods (Gómez et al, 2021), have shown great potential for forecasting of prices and yields of coffee (Kouadio et al, 2018), corn (Xu & Zhang, 2021), cotton (Ali et al, 2018; Fang et al, 2020), oats (Harris, 2017), soybeans (Li et al, 2020; Ribeiro & dos Santos Coelho, 2020), soybean oil (Li, Chen, et al, 2020), sugar (Ribeiro & Oliveira, 2011), and wheat (Fang et al, 2020; Gómez et al, 2021). In particular, previous studies show that the neural network has great potential to forecast economic and financial time series, which tend to have certain nonlinearities (Wang & Yang, 2010; Yang et al, 2008).…”

Section: Introductionmentioning

confidence: 99%

“…Parot et al (2019) suggest the combination of the neural network model, vector autoregressive model, and vector error correction model for improving forecast accuracy from an individual model for EUR/USD exchange rate returns. R. L. Manogna and A. K. Mishra (2021) examine the price forecasting problem for the cotton seed, castor seed, rape mustard seed, soybean seed, and guar seed traded in National Commodity and Derivatives Exchange in India through deep‐learning neural networks. They find that the long short‐term memory neural network outperforms the time‐delay neural network and ARMA model.…”

Section: Introductionmentioning

confidence: 99%

Commodity price forecasting via neural networks for coffee, corn, cotton, oats, soybeans, soybean oil, sugar, and wheat

Zhang

2022

Intell Sys Acc Fin Mgmt

View full text Add to dashboard Cite

Agricultural commodity price forecasting represents a key concern for market participants. We explore the usefulness of neural network modeling for forecasting problems in datasets of daily prices over periods of greater than 50 years for coffee, corn, cotton, oats, soybeans, soybean oil, sugar, and wheat. By investigating different model settings across the algorithm, delay, hidden neuron, and data-splitting ratio, we arrive at models leading to a decent performance for each commodity, with the overall relative root mean square error ranging from 1.70% to 3.19%. These results have small advantages over no-change models due to particular price adjustments in the prices considered here. Our results can be used on a standalone basis or combined with fundamental forecasts in forming perspectives of commodity price trends and conducting policy analysis. Our empirical framework should not be diffucult to implement, which is a critical consideration for many decision-makers and has the potential to be generalized for price forecasts of more commodities.

show abstract

Forecasting spot prices of agricultural commodities in India: Application of deep‐learning models

Abstract: Food price fluctuations can impact both producers and consumers. Forecasting the prices of the agricultural commodities is of prime concern not only to the government but also to farmers and agribusiness firms. In developing countries like India, manage

Cited by 45 publications

References 27 publications

Integrating the Role of Green Fiscal Policies With Energy Prices Volatility and Energy Efficiency: Presenting a COVID-19 Perspective

Integrating the Role of Green Fiscal Policies With Energy Prices Volatility and Energy Efficiency: Presenting a COVID-19 Perspective

Financialization of Indian agricultural commodities: the case of index investments

Commodity price forecasting via neural networks for coffee, corn, cotton, oats, soybeans, soybean oil, sugar, and wheat

Contact Info

Product

Resources

About