Training ensembles of faceted classification models for quantitative stock trading


Forecasting the stock markets is among the most popular research challenges in finance. Several quantitative trading systems based on supervised machine learning approaches have been presented in literature. Recently proposed solutions train classification models on historical stock-related datasets. Training data include a variety of features related to different facets (e.g., stock price trends, exchange volumes, price volatility, news and public mood). To increase the accuracy of the predictions, multiple models are often combined together using ensemble methods. However, understanding which models should be combined together and how to effectively handle features related to different facets within different models are still open research questions. In this paper we investigate the use of ensemble methods to combine faceted classification models for supporting stock trading. To this aim, separate classification models are trained on each subset of features belonging to the same facet. They produce trading signals tailored to a specific facet. Signals are then combined together and filtered to generate a unified, multi-faceted recommendation. The experimental validation, performed on different markets and in different conditions, shows that, in many cases, some of the faceted models perform as good as or better than models trained on a mix of different features. An ensemble of the faceted recommendations makes the generated trading signals more profitable yet robust to draw-down periods.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4


  1. 1.

    For the sake of simplicity, throughout the paper we have considered yearly periods.

  2. 2.

    Recommended configuration settings: SVC (Rbf kernel. \(\text {C}=1\). \(\text {Gamma}=\frac{1}{|D|}\)), MNB (\(\alpha =1.0\)), K-NN (\(K=5\)), RFC (\(\text {Criterion}=Gini\), \(\text {Max}\_\text {depth}=none\), \(\text {num}\_\text {estimators}=100\)), MLP (\(\text {hidden}\_\text {layer}\_\text {sizes}=20\), \(\text {solver}=lbfgs\), \(\text {n}\_\text {iter}\_\text {no}\_\text {change}=2\)).

  3. 3.

    Due to the lack of space, the detailed results are given as additional material.


  1. 1.

    Baralis E, Cagliero L, Cerquitelli T, Garza P, Pulvirenti F (2017) Discovering profitable stocks for intraday trading. Inf Sci 405:91–106

    Article  Google Scholar 

  2. 2.

    Chan E (2013) Algorithmic trading: winning strategies and their rationale, 1st edn. Wiley, Hoboken

    Google Scholar 

  3. 3.

    Chen Y, Hao Y (2017) A feature weighted support vector machine and k-nearest neighbor algorithm for stock market indices prediction. Expert Syst Appl 80:340–355

    Article  Google Scholar 

  4. 4.

    Chiang WC, Enke D, Wu T, Wang R (2016) An adaptive stock index trading decision support system. Expert Syst Appl 59:195–207

    Article  Google Scholar 

  5. 5.

    Enke D, Thawornwong S (2005) The use of data mining and neural networks for forecasting stock market returns. Expert Syst Appl 29(4):927–940

    Article  Google Scholar 

  6. 6.

    Gaaken M, Afezaalaca M, Boru A, Dosdoayru AT (2016) Integrating metaheuristics and artificial neural networks for improved stock price prediction. Expert Syst Appl 44:320–331

    Article  Google Scholar 

  7. 7.

    Kim MJ, Min SH, Han I (2006) An evolutionary approach to the combination of multiple classifiers to predict a stock price index. Expert Syst Appl 31:241–247

    Article  Google Scholar 

  8. 8.

    Kim Y, Ahn W, Oh KJ, Enke D (2017) An intelligent hybrid trading system for discovering trading rules for the futures market using rough sets and genetic algorithms. Appl Soft Comput 55:127–140

    Article  Google Scholar 

  9. 9.

    Kwon Y, Moon B (2007) A hybrid neurogenetic approach for stock forecasting. IEEE Trans Neural Netw 18(3):851–864

    Article  Google Scholar 

  10. 10.

    Li Q, Chen Y, Jiang LL, Li P, Chen H (2016) A tensor-based information framework for predicting the stock market. ACM Trans Inf Syst 34(2):11:1–11:30

    Article  Google Scholar 

  11. 11.

    Loper E, Bird S (2002) Nltk: the natural language toolkit. In: In Proceedings of the ACL workshop on effective tools and methodologies for teaching natural language processing and computational linguistics. Association for Computational Linguistics, Philadelphia

  12. 12.

    Murphy J (1999) Technical analysis of the financial markets: a comprehensive guide to trading methods and applications. New York Institute of Finance Series. New York Institute of Finance.

  13. 13.

    Naranjo R, Arroyo J, Santos M (2018) Fuzzy modeling of stock trading with fuzzy candlesticks. Expert Syst Appl 93:15–27

    Article  Google Scholar 

  14. 14.

    Nayak RK, Mishra D, Rath AK (2015) A naive svm-knn based stock market trend reversal analysis for Indian benchmark indices. Appl Soft Comput 35:670–680

    Article  Google Scholar 

  15. 15.

    Nelson DMQ, Pereira ACM, de Oliveira RA (2017) Stock market’s price movement prediction with lstm neural networks. In: 2017 International joint conference on neural networks (IJCNN), pp 1419–1426

  16. 16.

    Patel J, Shah S, Thakkar P, Kotecha K (2015) Predicting stock market index using fusion of machine learning techniques. Expert Syst Appl 42(4):2162–2172

    Article  Google Scholar 

  17. 17.

    Malagrino LS, Roman NT, Monteiro AM (2018) Forecasting stock market index daily direction: a Bayesian network approach. Expert Syst Appl 105:11–22

    Article  Google Scholar 

  18. 18.

    Selvin S, Vinayakumar R, Gopalakrishnan EA, Menon VK, Soman KP (2017) Stock price prediction using lstm, RNN and cnn-sliding window model. In: ICACCI. IEEE, pp 1643–1647

  19. 19.

    Tan PN, Steinbach M, Karpatne A, Kumar V (2018) Introduction to data mining, 2nd edn. Pearson, London

    Google Scholar 

  20. 20.

    Tsai CF, Lin YC, Yen DC, Chen YM (2011) Predicting stock returns by classifier ensembles. Appl Soft Comput 11(2):2452–2459

    Article  Google Scholar 

  21. 21.

    Zhong X, Enke D (2017) Forecasting daily stock market return using dimensionality reduction. Expert Syst Appl 67:126–139

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Luca Cagliero.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (xlsx 5600 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Cagliero, L., Garza, P., Attanasio, G. et al. Training ensembles of faceted classification models for quantitative stock trading. Computing 102, 1213–1225 (2020).

Download citation


  • Quantitative stock trading
  • Classification
  • Ensemble methods
  • Financial application

Mathematics Subject Classification

  • 68U35