Time Series forecasting global price of bananas using Hybrid ARIMA-NARNN model

Yeong Nain Chi; Orson Chi; Yeong Nain Chi; Orson Chi

doi:10.3934/DSFE.2022013

Data Science in Finance and Economics

2022, Volume 2, Issue 3: 254-274. doi: 10.3934/DSFE.2022013

Previous Article Next Article

Research article Special Issues

Time Series forecasting global price of bananas using Hybrid ARIMA-NARNN model

Yeong Nain Chi ^{1
,
,},
Orson Chi ²

1.
Department of Agriculture, Food and Resource Sciences, University of Maryland Eastern Shore, Princess Anne, MD 21853, USA
2.
Cybersecurity Engineering Technology Program, University of Maryland Eastern Shore, Princess Anne, MD 21853, USA

Received: 30 June 2022 Revised: 28 July 2022 Accepted: 09 August 2022 Published: 12 August 2022
JEL Codes: C22, C45, C53

This study tried to demonstrate the role of Time Series models in a modeling and forecasting process using publicly available long-term records of monthly global price of bananas during the period of January 1990 to November 2021 reported in the International Monetary Fund. Following the Box–Jenkins methodology, an ARIMA (2,1,4) with a drift model was selected as the best-fit model for the Time Series, according to its lowest AIC value. Using the Levenberg-Marquardt algorithm, the results revealed that the NARNN model with 12 neurons in the hidden layer and 6 times delays provided the best performance in the nonlinear autoregressive neural network models at its smaller MSE value. The ARIMA and NARNN models are good at modelling linear and nonlinear problems for the Time Series, respectively. However, using the HYBRID model, a combination of the ARIMA and NARNN models that has both linear and nonlinear modeling capabilities can be a better choice for modeling the Time Series. The comparative results revealed that the HYBRID model with 11 neurons in the hidden layer and 3 times delays yielded higher accuracy than the NARNN model with 12 neurons in the hidden layer and 6 times delays, and the ARIMA (2,1,4) with a drift model, according to its lowest MSE in this study.
- Time Series,
- Global price of bananas,
- Forecasting,
- ARIMA,
- NARNN,
- HYBRID ARIMA-NARNN,
- Levenberg-Marquardt algorithm
Citation: Yeong Nain Chi, Orson Chi. Time Series forecasting global price of bananas using Hybrid ARIMA-NARNN model[J]. Data Science in Finance and Economics, 2022, 2(3): 254-274. doi: 10.3934/DSFE.2022013

Related Papers:

Abstract

This study tried to demonstrate the role of Time Series models in a modeling and forecasting process using publicly available long-term records of monthly global price of bananas during the period of January 1990 to November 2021 reported in the International Monetary Fund. Following the Box–Jenkins methodology, an ARIMA (2,1,4) with a drift model was selected as the best-fit model for the Time Series, according to its lowest AIC value. Using the Levenberg-Marquardt algorithm, the results revealed that the NARNN model with 12 neurons in the hidden layer and 6 times delays provided the best performance in the nonlinear autoregressive neural network models at its smaller MSE value. The ARIMA and NARNN models are good at modelling linear and nonlinear problems for the Time Series, respectively. However, using the HYBRID model, a combination of the ARIMA and NARNN models that has both linear and nonlinear modeling capabilities can be a better choice for modeling the Time Series. The comparative results revealed that the HYBRID model with 11 neurons in the hidden layer and 3 times delays yielded higher accuracy than the NARNN model with 12 neurons in the hidden layer and 6 times delays, and the ARIMA (2,1,4) with a drift model, according to its lowest MSE in this study.

References

[1]	Altendorf S (2019) Banana Fusarium Wilt Tropical Race 4: A mounting threat to global banana markets? In 2019 Food Outlook - Biannual Report on Global Food Markets, FAO, Rome, 13–20. Available from: http://www.fao.org/3/ca6911en/CA6911EN_TR4EN.pdf.
[2]	Beale MH, Hagan MT, Demuth HB (2019) Deep Learning Toolbox^TM: Getting Started Guide. Deep Learn Natick, MA: The MathWorks, Inc.
[3]	Benrhmach G, Namir K, Namir A, et al. (2020) Nonlinear autoregressive neural network and extended Kalman filters do prediction of financial Time Series. J Appl Math 2020: 1–6. https://doi.org/10.1155/2020/5057801 doi: 10.1155/2020/5057801
[4]	Box GEP, Jenkins GM, Reinsel GC, et al. (2015) Time Series Analysis: Forecasting and Control (5^th ed.). John Wiley and Sons Inc.
[5]	Eyduran SP, Akın M, Eyduran E, et al. (2020) Forecasting banana harvest area and production in Turkey using Time Series analysis. Erwerbs-Obstbau 62: 281–291. https://doi.org/10.1007/s10341-020-00490-1 doi: 10.1007/s10341-020-00490-1
[6]	Fatin ZN, Titik E, Mulyatno SB (2020) The analysis of price and market integration of banana commodities in Lampung, Indonesia. Russ J Agric Socio-Econ Sci 3: 61–68. https://doi.org/10.18551/rjoas.2020-03.07 doi: 10.18551/rjoas.2020-03.07
[7]	Gardner M, Dorling SR (1998) Artificial neural networks (the multilayer perceptron) - a review of applications in the atmospheric sciences. Atmos Environ 32: 2627–2636. https://doi.org/10.1016/S1352-2310(97)00447-0 doi: 10.1016/S1352-2310(97)00447-0
[8]	Gavin HP (2013) The Levenberg-Marquardt algorithm for nonlinear least squares curve-fitting problems. Department of Civil and Environmental Engineering Duke University, 19. Available from: http://people.duke.edu/~hpgavin/ce281/lm.pdf.
[9]	Hamjah MA (2014) Forecasting major fruit crops productions in Bangladesh using Box-Jenkins ARIMA Model. J Econ Sustainable Dev 5: 96–107. Available from: https://core.ac.uk/download/pdf/234646336.pdf.
[10]	Hossain MM, Abdulla F, Majumder AK (2016) Forecasting of banana production in Bangladesh. Am J Agric Biol Sci 11: 93–99. https://doi.org/10.3844/ajabssp.2016.93.99 doi: 10.3844/ajabssp.2016.93.99
[11]	Levenberg K (1944) A method for the solution of certain non-linear problems in least squares. Q Appl Math 2: 164–168. https://doi.org/10.1090/qam/10666 doi: 10.1090/qam/10666
[12]	Ljung GM, Box GEP (1978) On a measure of lack of fit in Time Series models. Biometrika 65: 297–303. https://doi.org/10.2307/2335207 doi: 10.2307/2335207
[13]	MacKay DJC (1992) Bayesian Interpolation. Neural Comput 4: 415–447. https://doi.org/10.1162/neco.1992.4.3.415 doi: 10.1162/neco.1992.4.3.415
[14]	Market Reports World (2019) Banana market size, share, analysis - segmented by geography - growth, trends, and forecast (2019–2024). Global Banana Market Research Report, Market Reports World, 94. Available from: https://www.marketreportsworld.com/banana-market-13487750.
[15]	Marquardt DW (1963) An algorithm for least-squares estimation of nonlinear parameters. J Soc Ind and Appl Math 11: 431–441. https://doi.org/10.1137/0111030 doi: 10.1137/0111030
[16]	Moller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks 6: 525–533. https://doi.org/10.1016/S0893-6080(05)80056-5 doi: 10.1016/S0893-6080(05)80056-5
[17]	Montgomery DC, Jennings CL, Kulahci M (2008) Introduction to Time Series Analysis and Forecasting. Hoboken, John Wiley & Sons. Inc.
[18]	Omar MI, Dewan MF, Hoq MS (2014) Analysis of price forecasting and spatial co-integration of banana in Bangladesh. Eur J Bus Manage 6: 244–255. Available from: https://www.iiste.org/Journals/index.php/EJBM/article/view/11463.
[19]	Rathod S, Mishra GC, Singh KN (2017) Hybrid Time Series models for forecasting banana production in Karnataka State, India. J Indian Soc Agric Stat 71: 193–200. Available from: https://www.researchgate.net/publication/322165651_Hybrid_Time_Series_Models_for_Forecasting_Banana_Production_in_Karnataka_State_India.
[20]	Rathod S, Mishra GC (2018) Statistical models for forecasting mango and banana yield of Karnataka, India. J Agric Sci Technol 20: 803–816. Available from: http://jast.modares.ac.ir/article-23-19768-en.html.
[21]	Rebortera MA, Fajardo AC (2019) An enhanced deep learning approach in forecasting banana harvest yields. Int J Adv Comput Sci Appl 10: 275–280. https://doi.org/10.14569/IJACSA.2019.0100935 doi: 10.14569/IJACSA.2019.0100935
[22]	Ruiz A, Fobelets V, Grosscurt C, et al. (2017) The external costs of banana production: A global study. Research Report Prepared for Fairtrade International, True Price Trucost. Available from: http://makefruitfair.org/wp-content/uploads/2017/07/170224_Research_Report_External_Cost_ of_Bananas_-_final.pdf.
[23]	Voora V, Larrea C, Bermudez S (2020) Sustainable Commodities Marketplace Series 2019, The International Institute for Sustainable Development, Global market report: Bananas 12. Available from: https://www.iisd.org/system/files/publications/ssi-global-market-report-banana.pdf.
[24]	Sariev E, Germano G (2020) Bayesian regularized artificial neural networks for the estimation of the probability of default. Quant Financ 20: 311–328. https://doi.org/10.1080/14697688.2019.1633014 doi: 10.1080/14697688.2019.1633014
[25]	Young WL (1977) The Box-Jenkins approach to Time Series analysis and forecasting: principles and applications. RAIRO. Rech opérationnelle, 11: 129–143. Available from: http://www.numdam.org/article/RO_1977__11_2_129_0.pdf.
[26]	Zhang GP, Patuwo BE, Hu MY (1998) Forecasting with artificial neural networks: The state of the art. Int J Forecast 14: 35–62. https://doi.org/10.1016/S0169-2070(97)00044-7 doi: 10.1016/S0169-2070(97)00044-7
[27]	Zhang GP (2003) Time Series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50: 159–175. https://doi.org/10.1016/S0925-2312(01)00702-0 doi: 10.1016/S0925-2312(01)00702-0

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)