A Comparison of Predictive Modelling Techniques for Reducing Price Volatality in the Malaysia Sector
Keywords:
Forecasting, Fisheries prices, ARIMA, MLFFN, Hybrid ARIMA-MLFFNAbstract
Malaysia is one of the most important contributors in fisheries to the economy, as the country's GDP is rose to 12%. Hence, the fisheries price has always been an issue for Malaysian citizens. Recently, planning and decision-making in fisheries have been tough for the fisherman as they need to bear low prices despite the higher fishing cost. At the same time, the retailer receives higher fisheries prices. Thus, the fisheries prices have risen over time and are subjected to price fluctuation. This study aims to forecast the monthly price behaviour of many main varieties of fisheries that are commonly consumed by Malaysian using the method of ARIMA, MLFFN and hybrid ARIMA-MLFFN. The data used in this study is divided by two which in-sample data of 7 years from January 2010 to December 2018, while out-sample data of 2 years from January 2019 to December 2020 regards with the ex-vessel, wholesale and retail price of the fishery (Longtail tuna, Torpedo scad and Shortfin scad). Forecasts were made for the price of fisheries in the future for the next twelve months. According to the findings of this study, we concluded that all of three model: ARIMA, MLFFN and hybrid ARIMA-MLFFN are comparable models since 96% MAPE of out-sample forecast were less than 10%, which is highly accurate forecast.
References
Bhardwaj, S. P., Paul, R. K., Singh, D. R., & Singh, K. N. (2014). An empirical investigation of arima and garch models in agricultural price forecasting. Economic Affairs, 59(3), 415-428. https://doi.org/10.5958/0976-4666.2014.00009.6
Benzer, R., & Benzer, S. (2015). Application of artificial neural network into the freshwater fish caught in Turkey. International Journal of Fisheries and Aquatic Studies, 2(5), 341–346.
Ceccarelli, D. M., McKinnon, A. D., Andréfouët, S., Allain, V., Young, J., Gledhill, D. C.,... & Richardson, A. J. (2013). The coral sea: Physical environment, ecosystem status, and biodiversity assets. Advances in Marine Biology, 66, 213-290.
Devi, B. N., Krishnan, M., Venugopalan, R., & Mahapatra, B. K. (2013). Artificial neural network model for synergy analysis of input markets in ornamental fish trade in Mumbai. Agricultural Economics Research Review, 26(1), 83–90.
Rusiman, M. S., Mat Ali, N. F., & Abdullah, A. W. (2021). (2020). Time series analysis on Indian mackerel retail price in peninsular Malaysia. Enhanced Knowledge in Sciences and Technology, 1(1), 8-14. Retrieved from https://publisher.uthm.edu.my/periodicals/index.php/ekst/article/view/629
Floros, C., & Failler, P. (2006). Forecasting monthly fisheries prices: Model comparison using data from Cornwall (UK). European Journal of Scientific Research, 14(2), 613–624. https://core.ac.uk/download/pdf/52395339.pdf
Mahalingaraya, Rathod, S., Sinha, K., Shekhawat, R. S., & Chavan, S. (2018). Statistical modelling and forecasting of total fish production of India: A time series perspective. International Journal of Current Microbiology and Applied Science, 7(03), 1698–1707.
Mustapa, M., Ponnusamy, R. R., & Kang, H. M. (2019). Forecasting prices of fish and vegetable using web scraped price micro data. International Journal of Recent Technology and Engineering, 7(5), 251–256.
Perera, K. B. P., Herath, H. M. L. K., Jayasinghe-Mudalige, U. K., Edirisinghe, J. C., Udugama, J. M. M., & Wijesuriya, W. (2016). Price analysis of selected marine fish available in Colombo fish markets. Sri Lanka Journal of Economic Research, 4(1), 19. https://doi.org/10.4038/sljer.v4i1.69
Sazli, M. H. (2006). A brief review of feed-forward neural networks. Communications Faculty of Science University of Ankara Series, 50(1), 11–17. https://doi.org/10.1501/0003168
Sethi, S. A. (2010). Global fishery development patterns are driven by profit but not trophic level. Proceedings of the National Academy of Sciences, 107(27), 12163–12167. https://doi.org/10.1073/pnas
Shitan, M., Mah, P., Lim, Y. C., & Lim, Y. S. (2008). Arima and integrated arfima models for forecasting annual demersal and pelagic marine fish production in Malaysia. Malaysian Journal of Mathematical Sciences, 2(2), 41–54.
Song, H., & Li, G. (2008). Tourism demand modelling and forecasting—A review of recent research. Tourism management, 29(2), 203-220.
Stawitz, C. C., Siple, M. C., Munsch, S. H., & Lee, Q. (2017). Financial and ecological implications of global seafood mislabeling. Conservation Letters, 10(6), 681–689. https://doi.org/10.1111/conl.12328
Tai, T. C., Cashion, T., Lam, V. W. Y., Swartz, W., & Sumaila, U. R. (2017). Ex-vessel fish price database: Disaggregating prices for low-priced species from reduction fisheries. Frontiers in Marine Science, 4(NOV), 1-11. https://doi.org/10.3389/fmars.2017.00363
Villasante, S., Rodríguez-González, D., Antelo, M., Rivero-Rodríguez, S., & Lebrancón-Nieto, J. (2013). Why are prices in wild catch and aquaculture industries so different? Royal Swedish Academy of Sciences, 42(8), 937–950. https://doi.org/10.1007/s13280-013-0449-8
Cryer, J. D., & Chan, K. (2008). Time series analysis with application in R (2nd ed.). Springer New York.
Nurfarahin, I., & Norizan, M. (2020). Forecasting the number of airplane passengers using box-jenkins and artificial neural network In Malaysia. Universiti Malaysia Terengganu Journal of Undergeraduate Research, 2(4), 89-100.
Maharani, A. B., Norizan, M., Danang A. P., M. Fawwaz, A. Y., Nor Azlida, A., Z., Yanuar, & L., Niken. (2021). Modelling lock-down strictness for the COVID-19 pandemic in ASEAN countries by using hybrid ARIMA-SVR and hybrid SEIR-ANN. Arab Journal of Basic and Applied Sciences, 28(1), 204-224.
Siti Nor Zulaika, A., & Norizan, M. (2021). Forecasting electricity supplied in Turkey using holtwinters’ multiplicative method and Artificial Neural Network (ANN) models. Universiti Malaysia Terengganu Journal of Undergeraduate Research, 3(3), 131-142.
Maharani, A. B., Norizan, M., Danang, A. P., M. Fawwaz, A. Y., Nor Azlida, A. M., & L. Niken (2022). A year COVID-19 outbreak prediction in ASEAN countries by using machine learning. In Andriani, Y., Abdullah, M. T., & Amir, H. (Eds.), Preventive medicine of COVID-19 traditional local knowledge in Indonesia and Malaysia (pp. 149-174). Penerbit UMT.
Amira, F. A., Zaperi, N. H. A. M., Maharani, A, B., Norizan, M., & Nor Azlida, A. (2023). Machine learning on the post-vaccination COVID-19 prediction and on the vaccination sentiment analysis. AIP Conference Proceedings, 2746, 040005. https://doi.org/10.1063/5.0152820
Norizan, M., Maharani, A. B., Siti Nurfarahanim, M. R., Nur Khalisa, M., Nurfarahin, I., Nor Azlida, A., & Yusnita Yusof (2023). Tourism forecasting using box-Jenkins SARIMA and Artificial Neural Network (ANN) models: Case for outbound and inbound tourist in Malaysia. The 15th Universiti Malaysia Terengganu Annual Symposium 2021 (UMTAS 2021).
Tseng, F.-M., Yu, H.-C., & Tzeng, G.-H. (2002). Combining neural network model with seasonal time series ARIMA model. Technological Forecasting & Social Change, 69, 71-87.
Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Journal of Mathematical Sciences and Informatics
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
