An Improved Arima Model Using Ann and Svm for Forecasting Rapeseed & Mustard Production


  • Borsha Neog, Bipin Gogoi, A. N. Patowary


ARIMA, ANN, SVM, Forecasting, Rapeseed & Mustard.


Forecasting of agricultural crop production is the art of predicting production before harvest and is crucial for planning and policy making at various stages. “Rapeseed & Mustard (R & M) is the predominant oilseed crop of Assam because of its short duration. To know about futures estimates, planning is much importance to make fruitful decisions. In this context, the present study was undertaken to develop proper forecasting models for R & M of Assam. Here we have been used yearly data on production of Rapeseed & Mustard for forecasting from the year 1951 to 2018. For model building, we have used data from 1951-1998 and for model testing data from 1999 - 2018 were used for forecasting performance of the model. In this study, to analyse the past behaviour of the production of Rapeseed & Mustard to make interpretations about its future behaviour using different models Autoregressive integrated moving average (ARIMA), Artificial neural network (ANN), support vector machine (SVM) and hybrid of both ARIMA-ANN, ARIMA-SVM.  For the selected crops, ARIMA (0,1,0) model was selected as a suitable model. In training, mean absolute error (MAE) for hybrid ARIMA (0,1,0)-SVM was found to be 8216.169 as compare to 8813.731 of ARIMA-ANN; 10620.825 of ARIMA (0,1,0); 10242.319 of ANN; 9831.046 of SVM. In testing, MAE for hybrid ARIMA (0,1,0)-SVM was found to be 8174.671 as compare to as compare to 9263.464 of ARIMA-ANN; 10606.565 of ARIMA (0,1,0); 10384.249 of ANN; 10139.604 of SVM. Henceforth, the performances of hybrid ARIMA-ANN and ARIMA-SVM were found to be better than that of ARIMA for both under training as well as testing data sets. So from the results we can recommend hybrid approach gives better results for forecasting of Rapeseed & Mustard production.


Download data is not yet available.


Alexandridis, A.K. ; Zapranis, A.D. (2013). Wavelet neural networks: A practical guide. Neural Networks, 42, 1-27.

Alam, M.W.; Sinha, K.; Ranjan, R.K.; Ray, M; Rathod, S.; Singh, K.N. (2018). Development of Hybrid time series models using Machine learning techniques for forecasting crop yield with covariates. Indian Agricultural Statistics Research Institute, New Delhi.

Banakar, A.; Azeem, M.F. (2008). Artificial wavelet network and its application to neuro-fuzzy models. Appl. Soft. Computing, 8 (4) , 1463-1485.

Banik, A; G. Raju; S. Shukla (2021). Rice yield forecasting in West Bengal using hybrid model. Data Science and security, Proceedings of IDSCS 2021. PP. 222-231

Box, G. E. P.; Pierce, D. A. (1970). Distribution of Residual Autocorrelations in Autoregressive-Integrated Moving Average Time Series Models. Journal of the American StatisticalAssociation. 65 (332):1509-1526. doi:10.1080/01621459.1970.10481180.

Box, G.E.P.; Jenkins, G.M.; Reinsel, G.C. (1994), Time Series Analysis: Forecasting and Control (3rd ed.). Holden-Day, San Francisco.

Broock, W.; Scheinkman, J.A.; Dechert, W.D.; LeBaron, B. (1996). A test for independence based on the correlation dimension. Econ. Rev., 15, 197-235.

Cao, L.J.; E.H. Tay, 2003. Support vector with adaptive parameters in financial time series forecasting. IEEE Trans. Neural Network, 14:1506-1518. DOI: 10.1109/TNN.2003.820556

Flake, G.W.; S. Lawrence, 2002. Efficient SVM regression training with SMO. Machine learning, 46:271-290

Filippi, P., Jones, E.J., Wimalathunge, N.S., Somarathna, P.D.S.N., Pozza, L.E., Ugbaje, S.U., Bishop, T.F.A., 2019a. An approach to forecast grain crop yield using multilayered, multi-farm data sets and machine learning. Precis. Agric. 1–15. https://doi. org/10.1007/s11119-018-09628-4.

G. M. Ljung, G. E. P. Box (1978). On a Measure of a Lack of Fit in Time Series Models. Biometrika. 65 (2): 297–303. doi:10.1093/biomet/65.2.297

Hervai, S.; Osborn, DR.; Birchenhall, CR. (2004). Linear versus neural network forecast for European industrial production series. Int J Forecast 20:435-446.

Jha, G.K.; Sinha, K. (2014). Time-delay neural networks for time series prediction: an application to the monthly wholesale price of oilseeds in India. Neural Comput. Appl., 24(3).

Kohzadi, N.; Boyd, MS.; Kermanshahi, B.; Kaastra, I. (1995). A comparison of artificial neural network and time series models for forecasting commodity prices. Neurocomputing 10:169-181.

Makridakis, S.; Wheelwright, S.C.; Hyndman, R.J. (1998). Forecasting: Methods and Applications (3rd ed.). Wiley, Chichester.

Neog, B.; Gogoi, B.; Barua, S.; Mahanta, S.; Sarmah, K. (2023). Development of hybrid time series models for forecasting autumn rice production in Assam. The Pharma Innovation,12(2): 3376-3384. ISSN (E): 2277-7695

Thoranin, Sujjaviriyasup.; Komkrit, Pitiruek. (2013). Hybrid ARIMA-Support Vector Machine Model for Agricultural Production Planning. Applied Mathematical Sciences, 7(57), 2833 – 2840.

Vapnik, V.N. (1995). The nature of Statistical learning Theory. 1st edn., Springer-Verlog, New York, ISBN: 0-387-94559-8.

Xu, X., Gao, P., Zhu, X., Guo, W., Ding, J., Li, C., Wu, X. (2019). Design of an integrated climatic assessment indicator (ICAI) for wheat production: a case study in Jiangsu Province, China. Ecol. Ind. 101, 943–953. 01.0591

Zhang, G. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.

Zhao, C. Y.; H.X. Zhang; M.C.; Liu, Z.; D. Hu; B.T. Fan. (2006). Application of support vector machine (SVM) for prediction toxic activity of different data sets. Toxicology, 217: 105-119.




How to Cite

Borsha Neog,. (2024). An Improved Arima Model Using Ann and Svm for Forecasting Rapeseed & Mustard Production . International Journal of Intelligent Systems and Applications in Engineering, 12(21s), 3152–3162. Retrieved from



Research Article