Price Forecasting of Gram and Black Gram across Major States of India: A Comparative Analysis of Deep Learning Models

Chiranjit Mazumder; Shubho Paul; Subrata Barman; Sukhendu Nandi; Pramod Kumar

doi:10.56093/ijas.v96i10.175346

Authors

Dr. Chiranjit Mazumder ICAR-IARI, New Delhi
Shubho Paul ICAR-IARI, New Delhi
Subrata Barman ICAR-IARI, New Delhi
Sukhendu Nandi ICAR-IARI, New Delhi
Dr. Pramod Kumar ICAR-IARI, New Delhi

https://doi.org/10.56093/ijas.v96i10.175346

Keywords:

Pulses price forecasting, machine learning, deep learning, gram, blackgram

Abstract

Precise price forecasting of pulse crops is essential in effective market interventions, price stabilisation and informed policy decisions. This paper compares the performance of some deep learning models in predicting wholesale prices of two key pulses, gram and black gram, across the major producing states. Four deep learning models, such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU), were employed and compared in terms of RMSE and MAPE to assess their performance. The RNN performed better than other models in most datasets. The projections indicate that the prices of the two crops will show a downward trend in 2026, with the exception of gram in Madhya Pradesh. The results highlight that deep learning models have the potential to improve the accuracy of crop price predictions and of evidence-based policy-making.

Downloads

Download data is not yet available.

Author Biographies

Dr. Chiranjit Mazumder, ICAR-IARI, New Delhi

Scientist at Department of Agricultural Economics, ICAR-Indian Agricultural Research Institute, New Delhi 110 012, India.
Shubho Paul, ICAR-IARI, New Delhi

Ph.D. Scholar at Department of Agricultural Economics, ICAR-Indian Agricultural Research Institute, New Delhi 110 012, India
Subrata Barman, ICAR-IARI, New Delhi

Phd Scholar at Department of Agricultural Economics, ICAR-Indian Agricultural Research Institute, New Delhi 110 012, India
Sukhendu Nandi, ICAR-IARI, New Delhi

PhD scholar at Department of Agricultural Economics, ICAR-Indian Agricultural Research Institute, New Delhi 110 012, India
Dr. Pramod Kumar, ICAR-IARI, New Delhi

Professor and Principal Scientist, Department of Agricultural Economics, ICAR-Indian Agricultural Research Institute, New Delhi 110 012, India.

References

Aditya, K.S., Jha, G.K. and Praveen, K.V. 2021. Soaring pulses: Is the spike in retail price of moong in 2020 a cause for concern? The Wire. https://thewire.in/agriculture/pulses-dal-moong-urad-price-rise-2020-covid-19

Akibode, S. and Maredia, M.K. 2012. Global and regional trends in production, trade and consumption of food legume crops. Staff Paper No. 2012-10, Michigan State University. https://ageconsearch.umn.edu/record/136293/files/StaffPaperMaredia2012-10F.pdf

Anand, S. 2025. With no finger on the pulse, crop and prices in disarray. The Economic Times, 19 November. https://economictimes.indiatimes.com/news/economy/agriculture/with-no-finger-on-the-pulse-crop-and-prices-in-disarray/articleshow/125419332.cms

Banerjee, S. and Mondal, A.C. 2023. An ingenious method for estimating future crop prices that emphasises machine learning and deep learning models. International Journal of Information Technology, 15: 4291–4313. https://doi.org/10.1007/s41870-023-01474-6

Bhat, S., Kumar, H., Kumar, R. and Singh, N.P. 2024. Application of machine learning techniques in time series analysis of prices of pulses. Journal of Food Legumes, 32(2): 109–112. https://doi.org/10.59797/jfl.v32i2.683

Bisht, A. and Kumar, A. 2019. Estimating volatility in prices of pulses in India: An application of GARCH model. Economic Affairs, 64(3): 513–516. https://doi.org/10.30954/0424-2513.3.2019.6

Chen, C., Xue, L. and Xing, W. 2023. Research on improved GRU-based stock price prediction method. Applied Sciences, 13(15): Article 8813. https://doi.org/10.3390/app13158813

Chung, J., Gulcehre, C., Cho, K.H. and Bengio, Y. 2014. Empirical evaluation of gated recurrent neural networks on sequence modelling. arXiv preprint. https://arxiv.org/abs/1412.3555

Darekar, A. and Reddy, A.A. 2017. Price forecasting of pulses: Case of pigeonpea. Journal of Food Legumes, 30(3): 212–216. https://pub.isprd.in/index.php/jfl/article/download/485/319

Directorate of Pulses Development 2024. Annual Progress Report 2022–23. DPD, Bhopal. https://dpd.gov.in/Final%20%20Annual%20Report%20(2022-23)%20with%20Preface%20(As%20on%2020.02.2024).pdf

Directorate of Pulses Development 2025. Annual Progress Report 2023–24. DPD, Bhopal. https://www.dpd.gov.in/Annual%20Report%20%202023-24%2014.01.2025.pdf

Divisekara, R.W., Jayasinghe, G.J.M.S.R. and Kumari, K.W.S.N. 2021. Forecasting the red lentils commodity market price using SARIMA models. SN Business & Economics, 1: Article 20. https://doi.org/10.1007/s43546-020-00020-x

GKToday 2024. Pulse prices in India. 15 May. https://www.gktoday.in/pulse-prices/

Goodfellow, I., Bengio, Y. and Courville, A. 2016. Deep learning. MIT Press, Cambridge. https://synapse.koreamed.org/pdf/10.4258/hir.2016.22.4.351

Greff, K., Srivastava, R.K., Koutník, J., Steunebrink, B.R. and Schmidhuber, J. 2017. LSTM: A search space odyssey. IEEE Transactions on Neural Networks and Learning Systems, 28(10): 2222–2232. https://doi.org/10.1109/TNNLS.2016.2582924

Gupta, A.K., Rao, V.S. and Singh, A.K. 2018. Forecasting of arrivals and prices of chickpea in Chhattisgarh. International Journal of Agricultural Statistics Sciences, 14(Suppl. 1): 421-426. https://www.researchgate.net/publication/331687234

Hastie, T., Tibshirani, R. and Friedman, J. 2009. The elements of statistical learning: Data mining, inference, and prediction. Springer, New York. https://www.researchgate.net/publication/319770542

Haykin, S. 1999. Neural networks: A comprehensive foundation. Prentice Hall, Upper Saddle River, New Jersey. https://docs.preterhuman.net/Neural_Networks:_A_Comprehensive_Foundation

Hossain, M.Z., Samad, Q.A. and Ali, M.Z. 2006. ARIMA model and forecasting with three types of pulse prices in Bangladesh. International Journal of Social Economics, 33(4): 344–353. https://doi.org/10.1108/03068290610651652

Huang, C.S. and Sayed, A. 2025. Novel forecasting of white maize futures volatility: A hybrid GARCH-based bi-directional LSTM model. Cogent Economics & Finance, 13(1): Article 2484422. https://doi.org/10.1080/23322039.2025.2484422

Jha, G.K. and Sinha, K. 2014. Time-delay neural networks for time series prediction. Neural Computing and Applications, 24: 563–571. https://doi.org/10.1007/s00521-012-1264-z

Joshi, D., Deshpande, D., Tandon, P. and Parambalathu, K. 2017. Pulses & rhythms: Analysing volatility, cyclicality and the cobweb phenomenon in prices. CRISIL Ltd., Mumbai. https://www.crisil.com/content/dam/crisil/our-analysis/reports/Research/CRISIL-Research-Report-Pulses-and-Rhythms-11Sept2017.pdf

Lama, A., Jha, G.K., Gurung, B., Paul, R.K., Bharadwaj, A. and Parsad, R. 2016. A comparative study on time-delay neural network and GARCH models for forecasting agricultural commodity price volatility. Journal of the Indian Society of Agricultural Statistics, 70(1): 7–18. https://www.researchgate.net/publication/305316558

LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11): 2278–2324. https://doi.org/10.1109/5.726791

Makridakis, S. et al. 2023. Statistical, machine learning and deep learning forecasting methods. Journal of the Operational Research Society, 74(3): 840–859. https://doi.org/10.1080/01605682.2022.2118629

Manogna, R.L., Dharmaji, V. and Sarang, S. 2025. A novel hybrid neural network-based volatility forecasting of agricultural commodity prices: empirical evidence from India. Journal of Big Data, 12: Article 85. https://doi.org/10.1186/s40537-025-01131-8

McCulloch, W.S. and Pitts, W. 1943. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5(4): 115–133. https://doi.org/10.1007/BF02478259

Lama, A., Jha, G.K., Gurung, B., Paul, R.K., Bharadwaj, A. and Parsad, R. 2016. A comparative study on time-delay neural network and GARCH models for forecasting agricultural commodity price volatility. Journal of the Indian Society of Agricultural Statistics, 70(1): 7–18. https://www.researchgate.net/publication/305316558

Manogna, R.L., Dharmaji, V. and Sarang, S. 2025. A novel hybrid neural network-based volatility forecasting of agricultural commodity prices: empirical evidence from India. Journal of Big Data, 12: Article 85. https://doi.org/10.1186/s40537-025-01131-8

Mishra, P., Al Khatib, A.M.G., Lal, P., Anwar, A., Nganvongpanit, K., Abotaleb, M., Ray, S. and Punyapornwithaya, V. 2023. An overview of pulses production in India: Retrospect and prospects of the future food with an application of hybrid models. National Academy Science Letters, 46(5): 367–374. https://doi.org/10.1007/s40009-023-01267-2

Murugananthi, D., Shivakumar, K.M., Palanichamy, N.V., Aruna Prabha, S., Somasundaram, E., Rohini, A., Parimala Devi, R., Selvanayaki, S. and Kavitha, P.G. 2024. Demand and supply projections for pulses in India. Legume Research, 47(8): 1335–1341. https://doi.org/10.18805/LR-5346

Nayak, G.H.H., Alam, M.W., Singh, K.N., Avinash, G., Kumar, R.R., Ray, M. and Deb, C.K. 2024. Exogenous variable driven deep learning models for improved price forecasting of TOP crops in India. Scientific Reports, 14: Article 17203. https://doi.org/10.1038/s41598-024-68040-3

Paliwala, M. 2022. Import of tur, urad and pigeon peas from Myanmar, Malawi, Mozambique: DGFT issues notification on quota. LiveLaw, 22 July. https://www.livelaw.in/news-updates/director-general-of-foreign-trade-dgft-memorandum-of-understanding-mous-public-notice-204456

Paul, R.K. 2014. Forecasting wholesale price of pigeon pea using long memory time-series models. Agricultural Economics Research Review, 27(2): 167–176. https://doi.org/10.22004/ag.econ.196661

Paul, R.K., Das, T. and Yeasin, M. 2023. Ensemble of time series and machine learning model for forecasting volatility in agricultural prices. National Academy Science Letters, 46(3):185–188. https://doi.org/10.1007/s40009-023-01218-x

Paul, R.K., Yeasin, M., Kumar, P., Kumar, P., Balasubramanian, M., Roy, H.S., Paul, A.K. and Gupta, A. 2022. Machine learning techniques for forecasting agricultural prices: A case of brinjal in Odisha, India. PLOS ONE, 17(7): Article e0270553. https://doi.org/10.1371/journal.pone.0270553

Paul, S., Nandi, S., Naik, P.B., Naorem, Y. and Hemanth, D.B. 2025. Study of India’s pulses sector in context of production shifts, trade patterns, and policy initiatives. Journal of Scientific Research and Reports, 31(12): 492–504. https://doi.org/10.9734/jsrr/2025/v31i123792

Perumal, A., Mazumdar, C., Srinatha, T.N., Rath, S. and Likhitha, S. 2024. Mitigating climate impact: A machine learning approach to forecast methane emissions from Indian livestock. Indian Journal of Agricultural Economics, 79(3): 610–620. https://doi.org/10.63040/25827510.2024.03.020

Praveenkumar, A., Varma, M., Srinatha, T.N., Verma, S., Naveen, G.P., Singh, A.K. and Sarkar, A. 2024. From traditional to advanced models: A comparative study between time series and machine learning models in agriculture. Journal of Scientific Research and Reports, 30(9): 314–325. https://doi.org/10.9734/jsrr/2024/v30i92356

Press Information Bureau 2024. Department of Agriculture and Farmers’ Welfare releases final estimates of major agricultural crops for 2023–24. [Press Release], 25 September. https://www.pib.gov.in/PressReleasePage.aspx?PRID=2058534

Pundlik, W.V. 2020. Market integration and price volatility of pulses in Maharashtra. Doctoral dissertation, Dr. Panjabrao Deshmukh Krishi Vidyapeeth, Akola. https://krishikosh.egranth.ac.in/server/api/core/bitstreams/3bca5b07-1419-4e67-b6da-8ef7e348ebde/content

Purohit, S.K., Panigrahi, S., Sethy, P.K. and Behera, S.K. 2021. Time series forecasting of price of agricultural products using hybrid methods. Applied Artificial Intelligence, 35(15): 1388–1406. https://doi.org/10.1080/08839514.2021.1981659

Rosenblatt, F. 1958. The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65(6): 386-408. https://doi.org/10.1037/h0042519

Sarangi, P.K., Sinha, D., Sinha, S. and Mittal, N. 2021. Machine learning approach for the prediction of consumer food price index. (In) Proceedings of the 2021 9th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO), pp. 1–6. https://doi.org/10.1109/ICRITO51393.2021.9596527

Savadatti, P.M. 2017. Trend and forecasting analysis of area, production and productivity of total pulses in India. Indian Journal of Economics and Development, 5(12): 1–10. https://www.academia.edu/download/59991165/121169-288117-1-SM20190712-27593-u2l1h1.pdf

Sonvanee, O.P. and Koshta, A.K. 2019. A study on arrivals and price behavior and forecasting of chickpea in krishi upaj mandis of Chhattisgarh plains. Plant Archives, 19(2): 3231–3237. https://www.cabidigitallibrary.org/doi/full/10.5555/20219950652

Srivastava, S.K., Sivaramane, N. and Mathur, V.C. 2010. Diagnosis of pulses performance of India. Agricultural Economics Research Review, 23: 137–148. https://ageconsearch.umn.edu/record/92161/files/15-SK-Srivasatava.pdf

Vivek, S. 2025. Pulse crisis: Why are prices crashing below MSP despite high demand, low production trouble farmers. India Today, 7 October. https://www.indiatoday.in/business/story/pulse-daal-crisis-msp-low-despite-high-demand-low-production-trouble-farmer-report-2799193-2025-10-07

Zhang, L., Wang, S. and Liu, B. 2018. Deep learning for sentiment analysis: A survey. WIREs Data Mining and Knowledge Discovery, 8(4): Article e1253. https://doi.org/10.1002/widm.1253

Zhou, K., Wang, W.Y., Hu, T. and Wu, C.H. 2020. Comparison of time series forecasting based on statistical ARIMA model and LSTM with attention mechanism. Journal of Physics: Conference Series, 1631(1): Article 012141. https://doi.org/10.1088/1742-6596/1631/1/012141