E3S Web Conf.
Volume 214, 20202020 International Conference on Energy Big Data and Low-carbon Development Management (EBLDM 2020)
|Number of page(s)||5|
|Section||Machine Learning and Energy Industry Structure Forecast Analysis|
|Published online||07 December 2020|
Research on market consumption prediction based on machine learning
monash university Guangzhou, China
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.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.