Evaluating machine learning classification for financial trading: An empirical approach

Eduardo Gerlein, Martin McGinnity, Ammar Belatreche, Sonya Coleman

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

Technical and quantitative analysis in financial trading use mathematical and statistical tools to help investors decide on the optimum moment to initiate and close orders. While these traditional approaches have served their purpose to some extent, new techniques arising from the field of computational intelligence such as machine learning and data mining have emerged to analyse financial information. While the main financial engineering research has focused on complex computational models such as Neural Networks and Support Vector Machines, there are also simpler models that have demonstrated their usefulness in applications other than financial trading, and are worth considering to determine their advantages and inherent limitations when used as trading analysis tools. This paper analyses the role of simple machine learning models to achieve profitable trading through a series of trading simulations in the FOREX market. It assesses the performance of the models and how particular setups of the models produce systematic and consistent predictions for profitable trading. Due to the inherent complexities of financial time series the role of attribute selection, periodic retraining and training set size are discussed in order to obtain a combination of those parameters not only capable of generating positive cumulative returns for each one of the machine learning models but also to demonstrate how simple algorithms traditionally precluded from financial forecasting for trading applications presents similar performances as their more complex counterparts. The paper discusses how a combination of attributes in addition to technical indicators that has been used as inputs of the machine learning-based predictors such as price related features, seasonality features and lagged values used in classical time series analysis are used to enhance the classification capabilities that impacts directly into the final profitability.
LanguageEnglish
Pages193-207
JournalExpert Systems with Applications
Volume54
Early online date1 Jul 2016
DOIs
Publication statusPublished - 15 Jul 2016

Fingerprint

Machine learning
Learning model
Profitability
Computational intelligence
Usefulness
Computational model
Technical analysis
Simulation
Financial engineering
Investors
Data mining
Predictors
Financial information
Quantitative analysis
Retraining
Prediction
Financial forecasting
Support vector machine
Seasonality
Financial time series

Keywords

  • Trading
  • Financial forecasting
  • Computer intelligence
  • Data mining
  • Machine learning
  • FOREX markets

Cite this

@article{f034f81754794edbb73083009490d2ae,
title = "Evaluating machine learning classification for financial trading: An empirical approach",
abstract = "Technical and quantitative analysis in financial trading use mathematical and statistical tools to help investors decide on the optimum moment to initiate and close orders. While these traditional approaches have served their purpose to some extent, new techniques arising from the field of computational intelligence such as machine learning and data mining have emerged to analyse financial information. While the main financial engineering research has focused on complex computational models such as Neural Networks and Support Vector Machines, there are also simpler models that have demonstrated their usefulness in applications other than financial trading, and are worth considering to determine their advantages and inherent limitations when used as trading analysis tools. This paper analyses the role of simple machine learning models to achieve profitable trading through a series of trading simulations in the FOREX market. It assesses the performance of the models and how particular setups of the models produce systematic and consistent predictions for profitable trading. Due to the inherent complexities of financial time series the role of attribute selection, periodic retraining and training set size are discussed in order to obtain a combination of those parameters not only capable of generating positive cumulative returns for each one of the machine learning models but also to demonstrate how simple algorithms traditionally precluded from financial forecasting for trading applications presents similar performances as their more complex counterparts. The paper discusses how a combination of attributes in addition to technical indicators that has been used as inputs of the machine learning-based predictors such as price related features, seasonality features and lagged values used in classical time series analysis are used to enhance the classification capabilities that impacts directly into the final profitability.",
keywords = "Trading, Financial forecasting, Computer intelligence, Data mining, Machine learning, FOREX markets",
author = "Eduardo Gerlein and Martin McGinnity and Ammar Belatreche and Sonya Coleman",
year = "2016",
month = "7",
day = "15",
doi = "10.1016/j.eswa.2016.01.018",
language = "English",
volume = "54",
pages = "193--207",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier",

}

Evaluating machine learning classification for financial trading: An empirical approach. / Gerlein, Eduardo; McGinnity, Martin; Belatreche, Ammar; Coleman, Sonya.

In: Expert Systems with Applications, Vol. 54, 15.07.2016, p. 193-207.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evaluating machine learning classification for financial trading: An empirical approach

AU - Gerlein, Eduardo

AU - McGinnity, Martin

AU - Belatreche, Ammar

AU - Coleman, Sonya

PY - 2016/7/15

Y1 - 2016/7/15

N2 - Technical and quantitative analysis in financial trading use mathematical and statistical tools to help investors decide on the optimum moment to initiate and close orders. While these traditional approaches have served their purpose to some extent, new techniques arising from the field of computational intelligence such as machine learning and data mining have emerged to analyse financial information. While the main financial engineering research has focused on complex computational models such as Neural Networks and Support Vector Machines, there are also simpler models that have demonstrated their usefulness in applications other than financial trading, and are worth considering to determine their advantages and inherent limitations when used as trading analysis tools. This paper analyses the role of simple machine learning models to achieve profitable trading through a series of trading simulations in the FOREX market. It assesses the performance of the models and how particular setups of the models produce systematic and consistent predictions for profitable trading. Due to the inherent complexities of financial time series the role of attribute selection, periodic retraining and training set size are discussed in order to obtain a combination of those parameters not only capable of generating positive cumulative returns for each one of the machine learning models but also to demonstrate how simple algorithms traditionally precluded from financial forecasting for trading applications presents similar performances as their more complex counterparts. The paper discusses how a combination of attributes in addition to technical indicators that has been used as inputs of the machine learning-based predictors such as price related features, seasonality features and lagged values used in classical time series analysis are used to enhance the classification capabilities that impacts directly into the final profitability.

AB - Technical and quantitative analysis in financial trading use mathematical and statistical tools to help investors decide on the optimum moment to initiate and close orders. While these traditional approaches have served their purpose to some extent, new techniques arising from the field of computational intelligence such as machine learning and data mining have emerged to analyse financial information. While the main financial engineering research has focused on complex computational models such as Neural Networks and Support Vector Machines, there are also simpler models that have demonstrated their usefulness in applications other than financial trading, and are worth considering to determine their advantages and inherent limitations when used as trading analysis tools. This paper analyses the role of simple machine learning models to achieve profitable trading through a series of trading simulations in the FOREX market. It assesses the performance of the models and how particular setups of the models produce systematic and consistent predictions for profitable trading. Due to the inherent complexities of financial time series the role of attribute selection, periodic retraining and training set size are discussed in order to obtain a combination of those parameters not only capable of generating positive cumulative returns for each one of the machine learning models but also to demonstrate how simple algorithms traditionally precluded from financial forecasting for trading applications presents similar performances as their more complex counterparts. The paper discusses how a combination of attributes in addition to technical indicators that has been used as inputs of the machine learning-based predictors such as price related features, seasonality features and lagged values used in classical time series analysis are used to enhance the classification capabilities that impacts directly into the final profitability.

KW - Trading

KW - Financial forecasting

KW - Computer intelligence

KW - Data mining

KW - Machine learning

KW - FOREX markets

U2 - 10.1016/j.eswa.2016.01.018

DO - 10.1016/j.eswa.2016.01.018

M3 - Article

VL - 54

SP - 193

EP - 207

JO - Expert Systems with Applications

T2 - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -