Hybrid DTW-ARIMA Model for Rice Price Forecasting: An Indonesian Case Study
DOI:
https://doi.org/10.66472/isadd.v1i4.355Keywords:
Time Series Clustering, Dynamic Time Warping (DTW);, ARIMA, Rice Price Forecasting, Food Security.Abstract
Rice, as a strategic commodity in Indonesia, experiences significant fluctuations that affect economic stability and public welfare. This raises challenges in food policy planning, particularly in achieving accurate price forecasting. The research problem addressed is how to improve rice price forecasting accuracy using time series clustering capable of capturing complex interregional patterns. The study is limited to monthly rice price data over the past five years. To solve this problem, a hybrid model integrating Dynamic Time Warping (DTW) and Autoregressive Integrated Moving Average (ARIMA) is proposed. DTW measures similarity among time series patterns, while ARIMA constructs predictive models based on historical data. The objective is to produce more accurate and stable forecasts compared to single-method approaches. The urgency lies in its contribution to national food policy and food security. The novelty compared to previous studies is the integration of DTW-ARIMA within a time series clustering framework, rarely applied to food commodities in Indonesia. Experimental results indicate that the hybrid DTW-ARIMA model achieves lower mean absolute percentage error (MAPE) than conventional methods. The expected output is a predictive model that can be implemented as a data-driven decision support system for national food policy.
References
[1] G. Nguyen et al., “Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a survey,” Artif. Intell. Rev., vol. 52, no. 1, pp. 77–124, 2019, doi: 10.1007/s10462-018-09679-z.
[2] C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, 2019, doi: 10.1186/s40537-019-0197-0.
[3] R. Vinayakumar, M. Alazab, K. P. Soman, P. Poornachandran, A. Al-Nemrat, and S. Venkatraman, “Deep Learning Approach for Intelligent Intrusion Detection System,” IEEE Access, vol. 7, pp. 41525–41550, 2019, doi: 10.1109/ACCESS.2019.2895334.
[4] A. D. Dwivedi, G. Srivastava, S. Dhar, and R. Singh, “A decentralized privacy-preserving healthcare blockchain for IoT,” Sensors (Switzerland), vol. 19, no. 2, pp. 1–17, 2019, doi: 10.3390/s19020326.
[5] F. Al-Turjman, H. Zahmatkesh, and L. Mostarda, “Quantifying uncertainty in internet of medical things and big-data services using intelligence and deep learning,” IEEE Access, vol. 7, pp. 115749–115759, 2019, doi: 10.1109/ACCESS.2019.2931637.
[6] S. Kumar and M. Singh, “Big data analytics for healthcare industry: Impact, applications, and tools,” Big Data Min. Anal., vol. 2, no. 1, pp. 48–57, 2019, doi: 10.26599/BDMA.2018.9020031.
[7] L. M. Ang, K. P. Seng, G. K. Ijemaru, and A. M. Zungeru, “Deployment of IoV for Smart Cities: Applications, Architecture, and Challenges,” IEEE Access, vol. 7, pp. 6473–6492, 2019, doi: 10.1109/ACCESS.2018.2887076.
[8] B. P. L. Lau et al., “A survey of data fusion in smart city applications,” Inf. Fusion, vol. 52, pp. 357–374, 2019, doi: 10.1016/j.inffus.2019.05.004.
[9] Y. Wu et al., “Large scale incremental learning,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2019-June, pp. 374–382, 2019, doi: 10.1109/CVPR.2019.00046.
[10] A. Mosavi, S. Shamshirband, E. Salwana, K. wing Chau, and J. H. M. Tah, “Prediction of multi-inputs bubble column reactor using a novel hybrid model of computational fluid dynamics and machine learning,” Eng. Appl. Comput. Fluid Mech., vol. 13, no. 1, pp. 482–492, 2019, doi: 10.1080/19942060.2019.1613448.
[11] Box, G.E.P., Jenkins, G.M., Reinsel, G.C., & Ljung, G.M. (2015). Time Series Analysis: Forecasting and Control.
[12] Keogh, E., & Ratanamahatana, C.A. (2005). Exact indexing of dynamic time warping. Knowledge and Information Systems, 7(3), 358–386.
[13] Wang, X., et al. (2013). Experimental comparison of representation methods for time series classification. Data Mining and Knowledge Discovery, 26(2), 275–309.
[14] Hyndman, R.J., & Athanasopoulos, G. (2018). Forecasting: Principles and Practice. OTexts.
[15] Zhang, G.P. (2003). Time series forecasting using hybrid ARIMA and neural network model. Neurocomputing, 50, 159–175.
[16] Li, J., et al. (2021). Hybrid models for agricultural price forecasting. Computers and Electronics in Agriculture, 187, 106285.
[17] Wang, Y., et al. (2019). Hybrid time series forecasting model based on clustering and machine learning. Applied Soft Computing, 85, 105773.
[18] Box, G.E.P., Jenkins, G.M., Reinsel, G.C., & Ljung, G.M. (2015). Time Series Analysis: Forecasting and Control. Wiley.
[19] Keogh, E., & Ratanamahatana, C.A. (2005). Exact indexing of dynamic time warping. Knowledge and Information Systems, 7(3), 358–386.
[20] Wang, X., et al. (2013). Experimental comparison of representation methods for time series classification. Data Mining and Knowledge Discovery, 26(2), 275–309.
[21] Hyndman, R.J., & Athanasopoulos, G. (2018). Forecasting: Principles and Practice. OTexts.
[22] Zhang, G.P. (2003). Time series forecasting using hybrid ARIMA and neural network model. Neurocomputing, 50, 159–175.
[23] Li, J., et al. (2021). Hybrid models for agricultural price forecasting. Computers and Electronics in Agriculture, 187, 106285.
[24] Wang, Y., et al. (2019). Hybrid time series forecasting model based on clustering and machine learning. Applied Soft Computing, 85, 105773.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Information System Analysis, Design and Development
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
