ISMIS 2017 Data Mining Competition: Trading Based on Recommendations - XGBoost Approach with Feature Engineering

Chapter
Part of the Studies in Big Data book series (SBD, volume 40)

Abstract

This paper presents an approach to predict trading based on recommendations of experts using XGBoost model, created during ISMIS 2017 Data Mining Competition: Trading Based on Recommendations. We present a method to manually engineer features from sequential data and how to evaluate its relevance. We provide a summary of feature engineering, feature selection, and evaluation based on experts recommendations of stock return.

References

  1. 1.
    Dey, S., Kumar, Y., Saha, S., Basak, S.: Forecasting to classification: predicting the direction of stock market price using Xtreme Gradient BoostingGoogle Scholar
  2. 2.
    Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16), pp. 785–794. ACM, New York (2016).  https://doi.org/10.1145/2939672.2939785
  3. 3.
    Hastie, T., Tibshirani, R., Friedman, J.: Boosting and additive trees. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, pp. 337–387. Springer, New York (2009).  https://doi.org/10.1007/978-0-387-84858-7_10. (ISBN 978-0-387-84858-7)CrossRefMATHGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Polish-Japanese Academy of Information TechnologyWarsawPoland
  2. 2.National Information Processing InstituteWarsawPoland

Personalised recommendations