A comparative study of the performance of Stock trading strategies based on LGBM and CatBoost algorithms.

Document Type : Original Article


1 Ph.D. Candidate, Department of Financial Management, Faculty of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran.

2 Professor of financial management, Department of Financial Management, Faculty of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran.


Today, investment in the stock market requires novel and efficient methods along with effective trading strategies for more accurate prediction of stock price future movements. This paper compares the performance of implementing LGBM and CatBoost trading strategies on a portfolio, which is formed, based on fundamental analysis and future study. First with use of future study and expert’s opinion, stock market scenarios designed and a portfolio consist of 6 fundamental stocks is built. In next step for each selected stocks a model is developed by means of LGMB and CatBoost algorithms and related stocks data from 2014 to 2019 to predict stock price movement. Model inputs includes, technical indicators, stocks trading data and some market and fundamental index. Bayesian hyper parameter was used to optimize the model’s key parameters. Results show that models optimized with Bayesian hyper parameter are more accurate than models, which optimized with grid search and implementing short-term trading strategies based on gradient boosting machine (LGBM) prediction signals cause better performance in comparison with CatBoost based strategies and Tehran Stock Exchange Index.


  • Atsalakis, G.S., Valavanis, K.P., (2009). Surveying stock market forecasting techniques part II: soft computing methods, Expert Syst. Appl.36 (3), 5932-5941.
  • Bajelan, Saeed, Fallahpour, Saeed, Dana,Shirin.(2016), The Stock Trend Prediction Using Volume Weighted Support Vector Machine with a Hybrid Feature Selection Method to Predict the Stock Price Trend in Tehran Stock Exchange, Financial Management Strategy,4(3),121-148.
  • Choudry,R, Grag, K. (2008). A Hybrid Machin Learning System for Stock Market Word Academy of Science, Engineering and Technology, 39.
  • Esfandyar Shahmansuri,(2017), Testing portfolio strategies based on fundamental, technical and heuristically with behavioral objects and characteristics of Tehran stoke market investors, Investment Knowledge,6(24),99-116.
  • Fama, E.-F., Blume, M.-E., (1966), Filter rules and stock market trading, J. Bus. 39 (1), 226–241.
  • gholamian, elham, davoodi , sayyed mohammad reza,(2018),  Predicting the Direction of Stock Market Prices Using Random Forest, financial engineering and portfolio management,9(35), 301-322.
  • Gulin, Ke, et.al, (2017), LightGBM: A Highly Efficient Gradient Boosting Decision Tree, Neural Information Processing Systems, 30.
  • Hanafizadeh, P., Kazazi, A., and Jalili Bolhasani, A., (2011) Portfolio design for investment companies through scenario planning, Management Decision, 49(4), 513-532.
  • Huang, Gumine, et.al, (2019), Evaluation of CatBoost method for prediction of reference evapotranspiration in humid regions, Hydrology,574,1029-1041.
  • Jing, Zhang, et.al. (2018), A novel data- driven stock price trend prediction system, Expert system with applications, 97,60 -
  • Lawrence, R. (1997), Using Neural Networks to Forecast Stock Market Prices, 1-12.
  • Leung, M, T., Chen, A. S., & Daouk, H. (2000). Forecasting exchange rates general regression neural networks.
  • Moshari, Mohammad,et.al,(2019), Designing a Hybrid Intelligent Model for Prediction of Stock Price Golden Points, Investment Knowledge,8(29),45-66.
  • Nanni, L., & Lumini, A. (2009). An experimental comparison of ensemble of classi- fiers for bankruptcy prediction and credit scoring. Expert Systems with Applica- tions, 36, 3028–3033.
  • Pamučar, Ddragan, Ćirović, Goran, (2015), the selection of transport and handling resources in logistics centres using Multi-Attributive Border Approximation Area Comparison (MABAC), Expert system with applications, 42, 3016- 3028.
  • Parsa M, et.al. (2020) Bayesian Multi-objective hyperparameter Optimization for accurate, Fast, and Efficient Neural, Frontiers in Neuroscience,14. Network Accelerator Design.
  • Patel, J, et.al. (2015). Predicting stock and stock price index movement using trend deterministic data preparation and machinelearnning techniques. Expert Systems with Applications, 42 (1), 259–268.
  • Raei, Reza, Hoseini, Farhang,(2015 ),Comparison of trading returns based on technical indicators and fuzzy logic and the combined method of genetic algorithm - fuzzy logic, financial engineering and portfolio management,6(24)
  • Rahnamay Roodposhti, feridoon, Shirinbayan ,Neda,(2016), Design portfolio using a scenario planning approach using Assumption-based planning, financial engineering and portfolio management,7(28), 1-21.
  • Saranj, et.al. (2020). Developing a Stock Technical Trading System Integrating MLP Neural Network with Evolutionary Algorithms, Financial knowledge and securities Analysis, 13(45), 47-64.
  • Shearer C. (2000), The CRISP-DM model: the new blueprint for data mining, J Data Warehousing (2000); 5:13-22.
  • Sarkar, Sobhan, et al. (2019), Application of optimized machine learning techniques for prediction of Occupational accidents,Computer & Operation research, 106, 210-224.
  • Shynkevich, Yauheniya, et al. (2017), forecasting price movements using technical indicators: Investigating the impact of varying input window length. Neurocomputing, 264 71–88.
  • Suryoday, Basak, et al., (2018), predicting the direction of stock market prices using tree-based classifiers, North American Journal of Economics and finance, In Press.
  • Tehrani, Reza, Hendijanizadeh, Mohammad, Noruzian Lakvan, Eisa,(2015),  A novel approach to fulfill active portfolio management and automatic stock trading based on feature selection algorithm, Investment Knowledge,4(13),107-126
  • Trappey, C., Shin, T. and Trappey, A. (2007), “Modeling international investment decisions for financial holding companies”, European Journal of Operational Research, Vol. 180, pp. 800-14.
  • Xiaolei, Sun, Mingxi, Liu, Zeqian, Sima, (2020). A novel cryptocurrency price trend forecasting model base on LightGBM, Finance Research Letters, 32.
  • Xiao-dan Z., Ang L., Ran P., (2016), Stock trend prediction based on a new status box method and AdaBoost probabilistic support vector machine, Journal of Applied    Soft Computing, 385-398.
  • Yufei, Xia, Chuanzhe, liu, YuYing, Li, Nana, Liu, (2017). Aboosted decision tree approach using Bayesian hyper_parameter optimization for credit scoring, Expert System with Application, 78, 225-241.
  • Wu, Jia, et.al, (2019), Hyper parameter Optimization for Machine Learning Models Based on Bayesian Optimization, Electronic Science and Technology, 17(1).