Current Science

Open Access Open Access  Restricted Access Subscription Access

Agricultural Price Forecasting Using NARX Model for Soybean Oil


Affiliations
1 ICAR-Indian Agricultural Research Institute, PUSA, New Delhi 110 012, India
2 ICAR-Indian Agricultural Statistics Research Institute, PUSA, New Delhi 110 012, India
 

The non-linear, non-stationary and complicated nature of agricultural price series makes their accurate forecasting extremely challenging. In comparison to standard statistical methods, artificial neural networks (ANN) have demonstrated promising results for predicting such series. However, the incorporation of auxiliary information can improve prediction accuracy if it is closely linked to the target series. A dynamical neural architecture called a non-linear autoregressive model with exogenous input (NARX) carefully makes use of the auxiliary information to construct a data-dependent non-linear forecasting model. The study explores the performance of NARX model for the real price series of soybean oil (soybean) using soybean (soybean oil) price as exogenous inputs. NARX models outperform ARIMA, ARIMAX and ANN models in terms of RMSE, MAPE, MASE and directional statistics as evaluation criteria. Further, the Diebold-Mariano test confirms a significant improvement in its predictive accuracy.

Keywords

Artificial Neural Networks, Mean Absolute Scaled Error, NARX, Price Forecasting, Soybean Oil.
User
Notifications
Font Size

  • Wang, J., Wang, Z., Li, X. and Zhou, H., Artificial bee colony-based combination approach to forecasting agricultural commodity prices. Int. J. Forecast., 2022, 38, 21–34.

  • Wang, L., Feng, J., Sui, X., Chu, X. and Mu, W., Agricultural product price forecasting methods: research advances and trend. Br. Food J., 2020, 122(7), 2121–2138.

  • Box, G. E. P., Reinsel, G. C., Jenkins, M. and Ljung, G. M., Time Series Analysis: Forecasting and Control, Wiley, Hoboken, 2015, 5th edn.

  • Weron, R., Electricity price forecasting: a review of the state-of-the-art with a look into the future. Int. J. Forecast., 2014, 30, 1030–1081.

  • Zhang, G., Patuwo, B. E. and Hu, M. Y., Forecasting with artificial neural networks: the state of the art. Int. J. Forecast., 1998, 14, 35–62.

  • Makirdakis, S., Spiliotis, E. and Assimakopoulos, V., The accuracy of machine learning (ML) forecasting methods versus statistical ones: extending the results of the M3-competition. Working Paper, University of Nicosia, Institute for the Future, Greece, 2017.

  • Leontaritis, I. J. and Billings, S. A., Input-output parametric models for non-linear systems Part I: Deterministic non-linear systems. Int. J. Control, 1985, 41, 303–328.

  • Narendra, K. S. and Parthasarathy, K., Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Networks, 1990, I, 4–27.

  • Di Nunno, F., Granata, F., Gargano, R. and de Marinis, G., Prediction of spring flows using nonlinear autoregressive exogenous (NARX) neural network models. Environ. Monit. Assess., 2021, 193(6), 1–17.

  • Guzman, S. M., Paz, J. O. and Tagert, M. L. M., The use of NARX neural networks to forecast daily groundwater levels. Water Resour. Manage., 2017, 31(5), 1591–1603.

  • Marcjasz, G., Uniejewski, B. and Weron, R., On the importance of the long-term seasonal component in day-ahead electricity price forecasting with NARX neural networks. Int. J. Forecast., 2019, 35, 1520–1532.

  • Siegelmann, H. T., Horne, B. G. and Giles, C. L., Computational capabilities of recurrent NARX neural networks. IEEE Trans. Syst. Man Cybernet. Part B: Cybernetics, 1997, 27, 208–215.

  • Haykin, S., Neural Networks and Learning Machines Encyclopedia of Bioinformatics and Computational Biology: ABC of Bioinformatics, Pearson Education, India, 2018, 3rd edn.

  • Jha, G. K. and Sinha, K., Time-delay neural networks for time series prediction: an application to the monthly wholesale price of oilseeds in India. Neural Comput. Appl., 2014, 24, 563–571.

  • Hyndman, R. J. and Koehler, A. B., Another look at measures of forecast accuracy. Int. J. Forecast., 2006, 22, 679–688.

  • Diebold, F. X. and Mariano, R. S., Comparing predictive accuracy. J. Business Econ. Stat., 2002, 20, 134–144.

  • Jarque, C. M. and Bera, A. K., Efficient tests for normality, homoscedasticity and serial independence of regression residuals. Econ. Lett., 1980, 6, 255–259.

  • Said, S. E. and Dickey, D. A., Testing for unit roots in autoregressive-moving average models of unknown order. Biometrika, 1984, 71, 599–607.

  • Escobari, D., Garcia, S. and Mellado, C., Identifying bubbles in Latin American equity markets: Phillips-Perron-based tests and linkages. Emer. Markets Rev., 2017, 33, 90–101.

  • Cromwell, J., Labys, W. and Terraza, M., Univariate Tests for Time Series Models Univariate Tests for Time Series Models, Sage, California, USA, 2011.

  • Jaiswal, R., Jha, G. K., Kumar, R. R. and Choudhary, K., Deep long short-term memory based model for agricultural price forecasting. Neural Comput. Appl., 2022, 34, 4661–4676.

  • Jha, G. K. and Sinha, K., Agricultural price forecasting using neural network model: an innovative information delivery system. Agric. Econ. Res. Rev., 2013, 26, 229–239.


Abstract Views: 97

PDF Views: 60




  • Agricultural Price Forecasting Using NARX Model for Soybean Oil

Abstract Views: 97  |  PDF Views: 60

Authors

Ronit Jaiswal
ICAR-Indian Agricultural Research Institute, PUSA, New Delhi 110 012, India
Girish K. Jha
ICAR-Indian Agricultural Research Institute, PUSA, New Delhi 110 012, India
Rajeev Ranjan Kumar
ICAR-Indian Agricultural Statistics Research Institute, PUSA, New Delhi 110 012, India
Achal Lama
ICAR-Indian Agricultural Statistics Research Institute, PUSA, New Delhi 110 012, India

Abstract


The non-linear, non-stationary and complicated nature of agricultural price series makes their accurate forecasting extremely challenging. In comparison to standard statistical methods, artificial neural networks (ANN) have demonstrated promising results for predicting such series. However, the incorporation of auxiliary information can improve prediction accuracy if it is closely linked to the target series. A dynamical neural architecture called a non-linear autoregressive model with exogenous input (NARX) carefully makes use of the auxiliary information to construct a data-dependent non-linear forecasting model. The study explores the performance of NARX model for the real price series of soybean oil (soybean) using soybean (soybean oil) price as exogenous inputs. NARX models outperform ARIMA, ARIMAX and ANN models in terms of RMSE, MAPE, MASE and directional statistics as evaluation criteria. Further, the Diebold-Mariano test confirms a significant improvement in its predictive accuracy.

Keywords


Artificial Neural Networks, Mean Absolute Scaled Error, NARX, Price Forecasting, Soybean Oil.

References





DOI: https://doi.org/10.18520/cs%2Fv125%2Fi1%2F79-84