In the era of e-commerce, purchase behavior prediction is one of the most important issues to promote both online companies' sales and the consumers' experience. The previous researches usually use the feature engineering and ensemble machine learning algorithms for the prediction. The performance really depends on designed features and the scalability of algorithms because the large-scale data and a lot of categorical features lead to huge samples and the high-dimensional feature. In this study, we explore an alternative to use tree-based Feature Transformation (FT) and simple machine learning algorithms (e.g. Logistic Regression). Random Forest (RF) and Gradient Boosting decision tree (GB) are used for FT. Then, the simple algorithm, rather than ensemble algorithms, is used to predict purchase behavior based on transformed features. Tree-based FT regards the leaves of trees as transformed features, and can learn high-order interactions among original features. Compared with RF, if GB is used for FT, simple algorithms are enough to achieve better performance.
Chunyan HOU
Tianjin University of Technology
Chen CHEN
Nankai University
Jinsong WANG
Tianjin University of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Chunyan HOU, Chen CHEN, Jinsong WANG, "Tree-Based Feature Transformation for Purchase Behavior Prediction" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 5, pp. 1441-1444, May 2018, doi: 10.1587/transinf.2017EDL8210.
Abstract: In the era of e-commerce, purchase behavior prediction is one of the most important issues to promote both online companies' sales and the consumers' experience. The previous researches usually use the feature engineering and ensemble machine learning algorithms for the prediction. The performance really depends on designed features and the scalability of algorithms because the large-scale data and a lot of categorical features lead to huge samples and the high-dimensional feature. In this study, we explore an alternative to use tree-based Feature Transformation (FT) and simple machine learning algorithms (e.g. Logistic Regression). Random Forest (RF) and Gradient Boosting decision tree (GB) are used for FT. Then, the simple algorithm, rather than ensemble algorithms, is used to predict purchase behavior based on transformed features. Tree-based FT regards the leaves of trees as transformed features, and can learn high-order interactions among original features. Compared with RF, if GB is used for FT, simple algorithms are enough to achieve better performance.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDL8210/_p
Copy
@ARTICLE{e101-d_5_1441,
author={Chunyan HOU, Chen CHEN, Jinsong WANG, },
journal={IEICE TRANSACTIONS on Information},
title={Tree-Based Feature Transformation for Purchase Behavior Prediction},
year={2018},
volume={E101-D},
number={5},
pages={1441-1444},
abstract={In the era of e-commerce, purchase behavior prediction is one of the most important issues to promote both online companies' sales and the consumers' experience. The previous researches usually use the feature engineering and ensemble machine learning algorithms for the prediction. The performance really depends on designed features and the scalability of algorithms because the large-scale data and a lot of categorical features lead to huge samples and the high-dimensional feature. In this study, we explore an alternative to use tree-based Feature Transformation (FT) and simple machine learning algorithms (e.g. Logistic Regression). Random Forest (RF) and Gradient Boosting decision tree (GB) are used for FT. Then, the simple algorithm, rather than ensemble algorithms, is used to predict purchase behavior based on transformed features. Tree-based FT regards the leaves of trees as transformed features, and can learn high-order interactions among original features. Compared with RF, if GB is used for FT, simple algorithms are enough to achieve better performance.},
keywords={},
doi={10.1587/transinf.2017EDL8210},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Tree-Based Feature Transformation for Purchase Behavior Prediction
T2 - IEICE TRANSACTIONS on Information
SP - 1441
EP - 1444
AU - Chunyan HOU
AU - Chen CHEN
AU - Jinsong WANG
PY - 2018
DO - 10.1587/transinf.2017EDL8210
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2018
AB - In the era of e-commerce, purchase behavior prediction is one of the most important issues to promote both online companies' sales and the consumers' experience. The previous researches usually use the feature engineering and ensemble machine learning algorithms for the prediction. The performance really depends on designed features and the scalability of algorithms because the large-scale data and a lot of categorical features lead to huge samples and the high-dimensional feature. In this study, we explore an alternative to use tree-based Feature Transformation (FT) and simple machine learning algorithms (e.g. Logistic Regression). Random Forest (RF) and Gradient Boosting decision tree (GB) are used for FT. Then, the simple algorithm, rather than ensemble algorithms, is used to predict purchase behavior based on transformed features. Tree-based FT regards the leaves of trees as transformed features, and can learn high-order interactions among original features. Compared with RF, if GB is used for FT, simple algorithms are enough to achieve better performance.
ER -