Modelling and Forecasting of Tomato Prices in Jabalpur District of India
363 / 271
Keywords:
Tomato prices; Hybrid SARIMA-GARCH; Forecasting; Box-Cox transformation; Agricultural Market Volatility; ARIMA.Abstract
Tomato price volatility exerts a substantial influence on food inflation and poses significant challenges for agricultural market volatility management.
This study employs a hybrid SARIMA–GARCH modeling framework with Root Mean Square Error (RMSE) 0.3011, Mean Absolute Percentage
Error (MAPE) 3.1754, and Mean Absolute Error (MAE) 0.2356,to forecast monthly tomato prices for a horizon of 12 months in the Jabalpur market,
capturing both seasonal patterns and volatility clustering in the price series. The SARIMA(1,1,1)(1,0,0)12 model effectively captures seasonal dynamics,
yielding a RMSE of 0.385, MAPE of 3.812, and MAE of 0.286. The GARCH(1,1) component addresses conditional heteroskedasticity in the residuals.
To enhance model robustness, a Box–Cox transformation is applied on the price series to stabilize the variance and mitigate heteroscedastic effects.
Parameters are estimated using Maximum Likelihood (ML) and a two-stage Conditional Sum of Squares followed by ML (CSS–ML) procedure.
Comparative evaluation demonstrates that the hybrid SARIMA(1,1,1)(1,0,0)12–GARCH(1,1) model outperforms both SARIMA models with varying
specifications and ARFIMA (1,0.4916,1) models in terms of predictive accuracy. The hybrid model is further validated through residual diagnostics.
An exploratory extension incorporating log-transformed arrivals as exogeneous variables in a SARIMAX framework yields marginal improvements,
reinforcing the preference for model parsimony. The proposed hybrid approach offers a scalable and empirically validated tool for improving short
term price forecasts, with practical implications for production planning, inventory management, and policy formulation in volatile tomato markets.
Downloads
References
1. Adanacioglu H. and Yercan M. (2012). An analysis of tomato prices
2. at wholesale level in Turkey: An application of SARIMA model.
3. Custos e Agronegocio, 8, 52-75.
4. Badal, P.S., Kamalvanshi, V., Goyal, A., Kumar, P., and Mondal, B.
5. (2022). Forecasting potato prices: Application of ARIMA model.
6. Economic Affairs, 67(4), 491-496.
7. Boateng, F.O., John, A.M., Martin, A., Lot, O., and Paul, D. (2017).
8. Modeling of tomato prices in Ashanti region, Ghana, using
9. seasonal autoregressive integrated moving average model. British
10. Journal of Mathematics & Computer Science, 20(1), 1-13.
11. Bollerslev, T. (1986). Generalized autoregressive conditional
12. heteroskedasticity. Journal of Econometrics, 31(3), 307-327.
13. https://doi.org/10.1016/0304-4076(86)90063-1
14. Box, G.E.P., and Jenkins, G.M. (1970). Time series analysis:
15. Forecasting and control. San Francisco: Holden-Day.
16. Casolaro, A., Capone, V., Iannuzzo, G., and Camastra, F. (2023).
17. Deep Learning for Time Series Forecasting: Advances and Open
18. Problems. Information, 14(11), 598.
19. Dickey, D.A., & Fuller, W.A. (1979). Distribution of the estimators
20. for autoregressive time series with a unit root. Journal of the
21. American Statistical Association, 74(366), 427-431. https://doi.
22. org/10.2307/2286348
23. Engle, R.F. (1982). Autoregressive conditional heteroscedasticity
24. with estimates of the variance of United Kingdom inflation.
25. Econometrica, 50(4), 987-1007. https://doi.org/10.2307/1912773
26. Fisher, R.A. (1922). On the mathematical foundations of theoretical
27. statistics. Philosophical Transactions of the Royal Society
28. of London. Series A, Containing Papers of a Mathematical
29. or Physical Character, 222(594-604), 309-368. https://doi.
30. org/10.1098/rsta.1922.0009
31. Government of India, Ministry of Finance, Department of Economic
32. Affairs. (2025). Economic Survey 2024–25 Chapter 4 – Prices and
33. Inflation: Understanding the Dynamics. https://www.indiabudget.
34. gov.in/economicsurvey/doc/eschapter/echap04.pdf
35. Jain, A., Marvaniya, S., Godbole, S., and Munigala, V. (2022). Towards
36. context-based model selection for improved crop price forecasting.
37. In Proceedings of the ACM Conference.
38. Kamu, A., Ahmed, A., and Yusoff, R. (2010). Forecasting cocoa bean
39. prices using univariate time series models. Journal of Arts Science
40. & Commerce, 1, 71.
41. Kitworawut, P., and Rungreunganun, V. (2019). Corn price modeling
42. and forecasting using Box-Jenkins model. Applied Science and
43. Engineering Progress.
44. Knotters, M., Brus, D.J., and van der Ploeg, M.J. (2010). A disposition
45. of interpolation techniques. Wageningen UR — Alterra / Report
46. (chapter on state-space approach).
47. Kumar, T.L., and Mohan, S. (2011). Holt-Winters exponential
48. smoothing and seasonal ARIMA time-series technique for
49. forecasting of onion price in Bangalore market.
50. Priya, L.K., Suresh, P., Yeturu, N., Bhargavi, N., Mathew, M., Mansingh,
51. P.J., and Nisha, A. (2024). Price behaviour and price forecasting of
52. tomato in Koyambedu Market, Tamil Nadu. International Journal
53. of Religion, 5(10), 2954-2962.
54. Li, W.K., and Mak, T.K. (1994). On the squared residual autocorrelations
55. in non-linear time series with conditional heteroscedasticity.
56. Journal of Time Series Analysis, 15(6), 627-636.
57. Limpert, E., Stahel, W.A., and Abbt, M. (2001). Log-normal
58. distributions across the sciences: Keys and clues. BioScience,
59. 51(5), 341-352.
60. Ljung, G. M., and Box, G.E.P. (1978). On a measure of a lack of fit in
61. time series models. Biometrika, 65(2), 297-303.
62. National Bank for Agriculture and Rural Development (NABARD).
63. (2023). Volatility in TOP and role of agri value chain (Ecofocus,
64. Issue No. 02, June). https://www.nabard.org/auth/writereaddata/
65. tender/pub_270623091211322.pdf
66. Patra M.D., J John and George, A.T. (2023), Recent Regime Reversal in
67. Inflation: The Indian Experience, RBI Bulletin, April.
68. Paul, R., Rana, S., and Saxena, R. (2016). Effectiveness of price
69. forecasting techniques for capturing asymmetric volatility
70. for onion in selected markets of Delhi. The Indian Journal of
71. Agricultural Sciences, 86, 303-309.
72. Pramanik, R., Alam, M.W., Ray, M., Nayak, H., Kumar, R.R., and
73. Chaturvedi, K.K. (2023). A comparative study of advanced
74. forecasting models on volatile time-series price data. Journal of
75. the Indian Society of Agricultural Statistics, 77(2), 155-170.
76. Pratap, B., Ranjan, A., and Kishore, V. (2021). Forecasting food
77. inflation using news-based sentiment indicators. Reserve Bank of
78. India Occasional Papers, 42(2). Rajpoot, K., Singla, S., Singh, A.,
79. & Shekhar, S. (2021). Impact of COVID-19 lockdown on prices
80. of potato and onion in metropolitan cities of India. Journal of
81. Agribusiness in Developing and Emerging Economies.
82. Reddy, A.A., Raju, S.S., Suresh, A., and Kumar, P. (2018). Analysis of
83. pearl millet market structure and value chain in India. Journal of
84. Agribusiness in Developing and Emerging Economies, 8, 00-00.
85. Sanjeev, Pushpa, Vikram, Preeti, and Pawan Kumar. (2025).
86. Comparative Study of ARIMA, SARIMA and Hybrid (ARIMA
87. + ANN and SARIMA + ANN) Models for Wholesale Monthly
88. Average Price of Tomato and Onion. Journal of the Indian Society
89. of Agricultural Statistics, 77(03), 275-284.
90. Sarkar, S., Das, S., Dutta, S., Bera, B., Bera, M., Roy, D., Middya, M.,
91. and Choudhury, M. (2024). Economic analysis of the behavior
92. of prices and market arrivals of tomatoes: A case study of West
93. Bengal, India. Agricultural & Rural Studies, 2, 1-12.
94. Singh, U., Singh, R.B., and Rajendra, B.L. (2015). Econometric
95. simulation model of dal industries for forecasting and policy
96. decision. Journal of The Indian Society of Agricultural Statistics,
97. 69(3), 301-305.
98. Sonvanee, O., and Bhargav, P. (2024). Forecasting tomato price and
99. arrival patterns in Krishi Upaj Mandis, Rajnandgaon, Chhattisgarh
100. using ARIMA models. Asian Journal of Agricultural Extension
101. Economics & Sociology, 42, 25-36.
102. Vinay, H.T., Basak, P., Ghosh, A., Ojha, S., and Sahu, C.R. (2024).
103. Forecasting of tomato price in Karnataka using BATS model.
104. Journal of the Indian Society of Agricultural Statistics, 78(2),
105. 107-113