Оn predictability of precious metals towards robust trading

  • 1 Department of Industrial Engineering, Atilim University, Ankara, Turkey
  • 2 Grodan BV, Roermond, the Netherlands


Large amounts of liquidity flow into several precious metals every day. Investment decisions are mainly based on predicting the future movements of the instrument(s) in question. However, high frequency financial data are somewhat hard to model or predict as stochastic processes and many other random factors are involved. It would be valuable information for the investor if he or she knew which precious metals were quantitatively more predictable, that would also be a good basis for more robust trading decisions. The objective in this study is to build predictive models on high frequency precious metal data and compare predictabilities of different metals using only past price and volume values which should be a basis for robust trading decisions. The data used consist of various frequencies from 1-minute to 4-hour covering a period of almost 20 years for each instrument and frequency. Artificial Neural Network (ANN) and Gradient Boosted Decision Tree (XGB) methods are applied. Comparable results are achieved



  1. Konstantinidi E., Skiadopoulos G. Are VIX futures prices predictable? An empirical. investigation. IJOF 27 543–560 (2011)
  2. Bossaerts P., Hillion P. Implementing Statistical Criteria to Select Return Forecasting Models: What Do We Learn? Rev. of Fin. Stud., 12(2), 405−428 (1999)
  3. Goyal A., Welch I. A Comprehensive Look at the Empirical Performance of Equity Premium Prediction. Rev. of Fin. Stud. Vol. 21 Issue 4, pp. 1455-1508 (2008)
  4. Hartzmark M. L. Returns to individual traders of futures: Aggregate results. JPE, 95, 1292–1306 (1987)
  5. Kho B. C. Time-varying Risk Premia, Volatility, and Technical Trading Rule Profits: Evidence from Foreign Currency Futures Markets. JFE, 41, 249–290 (1996)
  6. Strozzi F., Zaldivar J.M. Non-linear Forecasting in High-frequency Financial Time Series. Physica A, 353 (2005) 463–479 (2005)
  7. Taylor S. J. Rewards Available to Currency Futures Speculators: Compensation for Risk or Evidence of Inefficient Pricing? Economic Record, 68(Supplement), 105–116 (1992)
  8. Wang C. Futures Trading Activity and Predictable Foreign Exchange Market Movements. J. of Bank. & Fin. 28, 1023–1041 (2004)
  9. Yoo J., Maddala G. S. Risk Premia and Price Volatility in Futures Markets. JFM, 11, 165–177 (1991)
  10. Campbell J. Y., Thompson S. Predicting the Equity Premium Out of Sample: Can Anything Beat the Historical Average? Rev. of Fin. Stu. Vol. 21, Issue 4, pp. 1509-1531 (2008)
  11. Zunino L., Tabak B.M., Serinaldi F., Zanin M., Perez D.G., Rosso O.A. Commodity Predictability Analysis with a Permutation Information Theory Approach. Physica A, 390 (2011) 876–890 (2010)
  12. Cheng W., McClain B.W., Kelly C. Artificial Neural Networks Make Their Mark as a Powerful Tool for Investors. Rev. of Bus. 4 – 9 (1997)
  13. Dash R., Dash P.K., Bisoi R. A self-adaptive differential harmony search based optimized extreme learning machine for financial time series prediction. SAEC Vol. 19 pp 25-42 (2014)
  14. Dutta S., Shekhar S. Bond-rating: a Non-conservative Application of Neural Networks. Proceedings of the IEEE Int. Conf. on NN 2 pp 443– 450 (1988)
  15. Lam M. Neural Network Techniques for Financial Performance Prediction: Integrating Fundamental and Technical Analysis. Decision Support Systems, 37 567– 581 (2004)
  16. Wedding D.K., Cios K.J. Time series forecasting by combining RBF networks, certainty factors, and the Box-Jenkins model. Neurocomputing Vol. 10, Issue 2, pp 149-168 (1996)
  17. Xi L., Muzhou H., Lee M.H., Li J., Wei D., Hai H., Wu Y. A new constructive neural network method for noise processing and its application on stock market prediction. App. S. Comp. Vol. 15, pp 57-66 (2014)
  18. Yu L., Lai K.K., Wang S. Multistage RBF neural network ensemble learning for exchange rates forecasting. Neurocomputing Vol. 71, Issues 16-18, pp 3295-3302 (2008)
  19. Zięba M., Tomczak S. K., Tomczak J. M. Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction, Exp. Sys. w. Apps., Volume 58, pp 93-101 (2016)
  20. Chen, T., & Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22Nd ACM SIGKDD (pp. 785-794). ACM (2016)
  21. Karacor A. G., Sivri N., Ucan O.N., Maximum Stream Temperature Estimation of Degirmendere River Using Artificial Neural Network, JSIR, Vol. 66 No. 5 pp. 363-366 (2007)
  22. Karacor G., Denizhan Y. Advantages of Hierarchical Organisation in Neural Networks, IJCAS Vol. 16 pp 48-60 (2004)
  23. Aktepe A., Ersoz S. A Quantitative Performance Evaluation Model Based on a Job Satisfaction - Performance Matrix and Application in a Manufacturing Company. IJIE, 19(6), 264 – 277 (2012)
  24. Shamsipoor H., Sandidzadeh M.A., Yaghini M. Solving Capacitated P - Median Problem by a New Structure of Neural Network. IJIE, 19(8), 305 – 319 (2012)
  25. Yeoum S.J., Lee Y.H. A Study on Prediction Modeling of Korea Millitary Aircraft Accident Occurrence. IJIE, 20(9-10), 562 – 573 (2013)
  26. Hornik K., Stinchcombe M., White H. Multilayer Feedforward Networks are Universal Approximators, NN, Vol. 2, pp. 359-366 (1989)
  27. Rossum G. Python tutorial, Technical Report CS-R9526, Centrum voor Wiskunde en Informatica (CWI) (1995).

Article full text

Download PDF