Gold-Price Forecasting Method Using Long Short-Term Memory and the Association Rule

Authors

  • Laor Boongasame 1)Department of Mathematics, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand 2)Business Innovation and Investment Laboratory: B2I-Lab, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand
  • Piboonlit Viriyaphol Gold Research Center, Gold Traders Association, Bangkok, Thailand
  • Kriangkrai Tassanavipas Faculty of Engineering and Technology, Panyapiwat Institute of Management, Nonthaburi 11120, Thailand
  • Punnarumol Temdee Computer and Communication Engineering for Capacity Building Research Center, School of Information Technology, Mae Fah Luang University, Chiang Rai 57100, Thailand

DOI:

https://doi.org/10.13052/jmm1550-4646.1919

Keywords:

LSTM, Gold Forecasting, Association Rule, Artificial Neural Network

Abstract

Since gold prices influence international economic and monetary systems, numerous studies have been conducted to forecast gold prices. Nonetheless, studies employing the linear relationship method usually fail to explain the change in the pattern of the gold price. This study introduces a new paradigm that incorporates association rules and long short-term memory (LSTM) as a nonlinear-based method. For simulation, the proposed method was analyzed with data from Yahoo Finance from January 2010 to December 2020. The association rule was used to choose features relevant to the gold spot (GS) in the US Dollar Index (DXY). The LSTM forecast the gold price with a range of hyperparameter settings. The simulation results showed that the proposed method—the LSTM with GS and DXY, or LSTM-GS-DXY—resulted in low mean absolute percentage error (MAPE) metrics. In addition, the proposed LSTM-GS-DXY system outperformed the simple moving average (SMA), weight moving average (WMA), exponential moving average (EMA), and auto-regressive integrated moving average (ARIMA).

Downloads

Download data is not yet available.

Author Biographies

Laor Boongasame, 1)Department of Mathematics, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand 2)Business Innovation and Investment Laboratory: B2I-Lab, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand

Laor Boongasame is currently a Lecturer with the School of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, Thailand. She received the Ph.D. degree in computer engineering from the King Mongkut’s University of Technology Thonburi, Thailand. Her research interests involve buyer coalitions, n-person game theory, and investment. She has published several research papers in internationally refereed journals and has presented several papers at several international conferences.

Piboonlit Viriyaphol, Gold Research Center, Gold Traders Association, Bangkok, Thailand

Piboonlit Viriyaphol is currently a Director of Gold Research Center, a research and development unit at Gold Traders Association, Bangkok, Thailand. He received the B.Eng. degree in computer engineering in 1996 from Kasetsart University, Thailand. He received the M.Sc. degree in computer information system, in 2000, and the Ph.D. degree in telecommunication science, in 2006, from Assumption University, Thailand. He has been working with many universities in Thailand, such as Bangkok University, Assumption University, and King Mongkut’s Institute of Technology Ladkrabang, Bangkok Thailand, for both communication-based and financial-market-related research. His areas of research interests include traffic engineering, routing techniques, approximation techniques, and price modeling and forecasting in commodity market.

Kriangkrai Tassanavipas, Faculty of Engineering and Technology, Panyapiwat Institute of Management, Nonthaburi 11120, Thailand

Kriangkrai Tassanavipas is currently the Director of Innovation and Invention Excellence Center (IIEC), Faculty of Engineering and Technology, Panyapiwat Institute of Management, Bangkok, Thailand. He received the B.Eng. degree in computer engineering, the M.Eng. degree in electrical engineering, respectively, from the Prince of Songkla University, and the Ph.D. degree in robotics and automation from the King Mongkut’s University of Technology Thonburi, Thailand. His research interests include robotic and automation, computer vision, IoT (Internet of Things), artificial intelligence, and biomedical engineering fields. He has experience working with large companies in Thailand such as CPALL, FORD, ABB, etc. Also, he has been a guest speaker for Thailand’s universities including King Mongkut’s Institute of Technology Ladkrabang, Prince of Songkla University, Maidol University, etc.

Punnarumol Temdee, Computer and Communication Engineering for Capacity Building Research Center, School of Information Technology, Mae Fah Luang University, Chiang Rai 57100, Thailand

Punnarumol Temdee received the B.Eng. degree in electronic and telecommunication engineering, the M.Eng. degree in electrical engineering, and the Ph.D. degree in electrical and computer engineering from the King Mongkut’s University of Technology Thonburi. She is currently a Lecturer with the School of Information Technology, Mae Fah Luang University, Thailand. Her research expertise is in artificial intelligence-based application, context-aware computing, and pattern classification.

References

Adrangi B, Chatrath A, Raffiee K. Economic activity, inflation, and hedging: the case of gold and silver investments. The Journal of Wealth Management. 2003 Jul 31;6(2):60–77.

Wang W, Xia W. Empirical Modeling for the Spot Price of Gold Based on Influencing Factors. Applied Economics and Finance. 2017;4(3):129–40.

Napaaun P. The Analysis of Factors Influencing Gold Bar Price in Thailand. Thesis, Bangkok University, 2015.

Board of Governors of the Federal Reserve System. (n.d.) Federal Reserve Board. Retrieved December 1, 2021, from https://www.federalreserve.gov/aboutthefed.htm.

West Texas Intermediate (WTI). (n.d.) Investopedia. Retrieved March 31, 2021, from https://www.investopedia.com/terms/w/wti.asp.

Who or What Is Dow Jones? (n.d.) Investopedia. Retrieved March 31, 2021, from https://www.investopedia.com/ask/answers/who-or-what-is-dow-jones/.

U.S. Dollar Index (USDX). Retrieved March 31, 2021, from https://www.investopedia.com/terms/u/usdx.asp.

Kroner KF, Kneafsey KP, Claessens S. Forecasting volatility in commodity markets. Journal of Forecasting. 1995 Mar;14(2):77–95.

Kristjanpoller W, Minutolo MC. Gold price volatility: A forecasting approach using the Artificial Neural Network–GARCH model. Expert systems with applications. 2015 Nov 15;42(20):7245–51.

Tealab, A., 2018. Time series forecasting using artificial neural networks methodologies: A systematic review. Future Computing and Informatics Journal, 3(2), pp. 334–340.

Tully E, Lucey BM. A power GARCH examination of the gold market. Research in International Business and Finance. 2007 Jun 1;21(2):316–25.

Trück S, Liang K. Modelling and forecasting volatility in the gold market. International Journal of Banking and Finance. 2012 Mar 22;9(1):48–80.

Xu Q, Deng K, Jiang C, Sun F, Huang X. Composite quantile regression neural network with applications. Expert Systems with Applications. 2017 Jun 15;76:129–39.

Hafezi R, Akhavan A. Forecasting gold price changes: Application of an equipped artificial neural network. AUT Journal of Modeling and Simulation. 2018 Jun 1;50(1):71–82.

Schmidhuber J. Deep learning in neural networks: An overview. Neural networks. 2015 Jan 1;61:85–117.

Zhou S, Lai KK, Yen J. A dynamic meta-learning rate-based model for gold market forecasting. Expert Systems with Applications. 2012 May 1;39(6):6168–73.

Zhang P, Ci B. Deep belief network for gold price forecasting. Resources Policy. 2020 Dec 1;69:101806.

Fischer T, Krauss C. Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research. 2018 Oct 16;270(2):654–69.

Livieris IE, Pintelas E, Pintelas P. A CNN–LSTM model for gold price time-series forecasting. Neural computing and applications. 2020 Dec;32(23):17351–60.

Khani MM, Vahidnia S, Abbasi A. A Deep Learning-Based Method for Forecasting Gold Price with Respect to Pandemics. SN Computer Science. 2021 Jul;2(4):1–2.

Agrawal R, Imieliñski T, Swami A. Mining association rules between sets of items in large databases. In Proceedings of the 1993 ACM SIGMOD international conference on Management of data 1993 Jun 1 (pp. 207–216).

Karabatak M, Ince MC. A new feature selection method based on association rules for diagnosis of erythemato-squamous diseases. Expert Systems with Applications. 2009 Dec 1;36(10):12500–5.

Huang C, Huang X, Fang Y, Xu J, Qu Y, Zhai P, Fan L, Yin H, Xu Y, Li J. Sample imbalance disease classification model based on association rule feature selection. Pattern Recognition Letters. 2020 May 1;133:280–6.

Qu Y, Fang Y, Yan F. Feature selection algorithm based on association rules. In Journal of Physics: Conference Series 2019 Feb 1 (Vol. 1168, No. 5, p. 052012). IOP Publishing.

Kaur M, Kang S. Market Basket Analysis: Identify the changing trends of market data using association rule mining. Procedia computer science. 2016 Jan 1;85:78–85.

Gupta S, Mamtora R. A survey on association rule mining in market basket analysis. International Journal of Information and Computation Technology. 2014;4(4):409–14.

Sagin AN, Ayvaz B. Determination of association rules with market basket analysis: application in the retail sector. Southeast Europe Journal of Soft Computing. 2018 May 10;7(1).

Na SH, Sohn SY. Forecasting changes in Korea composite stock price index (KOSPI) using association rules. Expert Systems with Applications. 2011 Jul 1;38(7):9046–9.

Cheng CH, Chen CH. Fuzzy time series model based on weighted association rule for financial market forecasting. Expert Systems. 2018 Aug;35(4):e12271.

Lee SI, Yoo SJ. Multimodal deep learning for finance: integrating and forecasting international stock markets. The Journal of Supercomputing. 2020 Oct;76(10):8294–312.

Xia X. Learning behavior mining and decision recommendation based on association rules in interactive learning environment. Interactive Learning Environments. 2020 Aug 4:1–6.

Dahdouh K, Dakkak A, Oughdir L, Ibriz A. Association rules mining method of big data for e-learning recommendation engine. InInternational Conference on Advanced Intelligent Systems for Sustainable Development 2018 Jul 12 (pp. 477–491). Springer, Cham.

Intayoad W, Becker T, Temdee P. Social context-aware recommendation for personalized online learning. Wireless Personal Communications. 2017 Nov;97(1):163–79.

Smagulova K, James AP. Overview of long short-term memory neural networks. InDeep Learning Classifiers with Memristive Networks 2020 (pp. 139–153). Springer, Cham.

Hochreiter S, Schmidhuber J. Long short-term memory. Neural computation. 1997 Nov 15;9(8):1735–80.

Sivalingam KC, Mahendran S, Natarajan S. Forecasting gold prices based on extreme learning machine. International Journal of Computers Communications & Control. 2016 Mar 24;11(3):372–80.

He Z, Zhou J, Dai HN, Wang H. Gold price forecast based on LSTM-CNN model. In2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) 2019 Aug 5 (pp. 1046–1053). IEEE.

Livieris IE, Pintelas E, Pintelas P. A CNN–LSTM model for gold price time-series forecasting. Neural computing and applications. 2020 Dec;32(23):17351–60.

Lewis ND. Deep Time Series Forecasting with Python. Create Space Independent Publishing Platform. 2016 Dec.

Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. 2014 Dec 22.

Hansun S. A new approach of moving average method in time series analysis. In2013 conference on new media studies (CoNMedia) 2013 Nov 27 (pp. 1–4). IEEE.

Zhang Z, Qiao Y, Zhang T, Lu Y. Fractional weight moving average based thresholding scheme for VLC with mobile-phone camera. IEEE Photonics Journal. 2019 Jan 21;11(1):1–8.

Klinker F. Exponential moving average versus moving exponential average. Mathematische Semesterberichte. 2011 Apr;58(1):97–107.

Downloads

Published

2022-09-15

How to Cite

Boongasame, L. ., Viriyaphol, P. ., Tassanavipas, K. ., & Temdee, P. . (2022). Gold-Price Forecasting Method Using Long Short-Term Memory and the Association Rule. Journal of Mobile Multimedia, 19(01), 165–186. https://doi.org/10.13052/jmm1550-4646.1919

Issue

2023: Vol 19 Iss 1

Section

Articles