Research on market consumption prediction based on machine learning
With the rapid development of artificial intelligence industry and big data technology in recent years, the traditional financial industry has gradually transformed into fintech. China Merchants Bank Credit Card Center proposes to rely on data to predict whether users will buy the Pocket Life APP co...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2020-01-01
|
Series: | E3S Web of Conferences |
Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2020/74/e3sconf_ebldm2020_02014.pdf |
id |
doaj-706bdb1dd1ee4a5da5e45edd6fa99785 |
---|---|
record_format |
Article |
spelling |
doaj-706bdb1dd1ee4a5da5e45edd6fa997852021-04-02T20:46:45ZengEDP SciencesE3S Web of Conferences2267-12422020-01-012140201410.1051/e3sconf/202021402014e3sconf_ebldm2020_02014Research on market consumption prediction based on machine learningZhao Xu0monash university GuangzhouWith the rapid development of artificial intelligence industry and big data technology in recent years, the traditional financial industry has gradually transformed into fintech. China Merchants Bank Credit Card Center proposes to rely on data to predict whether users will buy the Pocket Life APP coupons as a practical business scenario. Based on this practical problem, a variety of machine learning methods are used, including logistic regression, random forest. Xgboost, LightGBM, to explore this problem. Finally, an integrated learning method is used to fuse the final result. This paper uses the above several algorithm models for prediction. The model principle is analyzed, and the performance of each model is measured on multiple evaluation indicators. The advantages and disadvantages of different models are compared horizontally, and the reasons for the difference in results are summarized.https://www.e3s-conferences.org/articles/e3sconf/pdf/2020/74/e3sconf_ebldm2020_02014.pdf |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhao Xu |
spellingShingle |
Zhao Xu Research on market consumption prediction based on machine learning E3S Web of Conferences |
author_facet |
Zhao Xu |
author_sort |
Zhao Xu |
title |
Research on market consumption prediction based on machine learning |
title_short |
Research on market consumption prediction based on machine learning |
title_full |
Research on market consumption prediction based on machine learning |
title_fullStr |
Research on market consumption prediction based on machine learning |
title_full_unstemmed |
Research on market consumption prediction based on machine learning |
title_sort |
research on market consumption prediction based on machine learning |
publisher |
EDP Sciences |
series |
E3S Web of Conferences |
issn |
2267-1242 |
publishDate |
2020-01-01 |
description |
With the rapid development of artificial intelligence industry and big data technology in recent years, the traditional financial industry has gradually transformed into fintech. China Merchants Bank Credit Card Center proposes to rely on data to predict whether users will buy the Pocket Life APP coupons as a practical business scenario. Based on this practical problem, a variety of machine learning methods are used, including logistic regression, random forest. Xgboost, LightGBM, to explore this problem. Finally, an integrated learning method is used to fuse the final result. This paper uses the above several algorithm models for prediction. The model principle is analyzed, and the performance of each model is measured on multiple evaluation indicators. The advantages and disadvantages of different models are compared horizontally, and the reasons for the difference in results are summarized. |
url |
https://www.e3s-conferences.org/articles/e3sconf/pdf/2020/74/e3sconf_ebldm2020_02014.pdf |
work_keys_str_mv |
AT zhaoxu researchonmarketconsumptionpredictionbasedonmachinelearning |
_version_ |
1721546498190082048 |