Analyzing Factors of Users Click Behavior on Ads Based on Logistic Regression and Machine Learning

DOI

10.2991/978-2-494069-31-2_299How to use a DOI?

Keywords

Online advertising; Click behavior; Logistic Regression; Machine Learning

Abstract

With the development of digital marketing, e-commerce industry is gradually increasing the market share it occupies, so one of the most concerned things for e-commerce platform is the users’ behavior of clicking online advertising. High clicks indicates that users have greater possibilities to buy products. There are several methods for analyzing click behavior, while less of them value e-commerce and specific features of users and ads. Among these methods, Logistics Regression (LR) was adopted most before, but it can only analyze linear relationship. Based on the Taobao users data of AliCloud Tianchi, Decision Tree Model of machine learning is proposed innovatively in theis paper to explore the impact of different users characteristics on clicking behavior and compares Decision Tree Model with LR. The results present that gender, age, consumption level and brand are filtered out by both two methods to build model because of these variables’ significance. Differently, Decision Tree Model analyze users characteristics precisely and in more detail, and it performs better in handling nonlinear and complex relationships. Additionally, from time’s perspective this paper find that click-through rate (CTR) may be higher when people are spiritually active and may be in connection with users’ life-shopping cycles instead of weekends. This article can provide guidance to e-commerce platforms’ personalized and high-efficient online ad placement strategies to improve the competitiveness of platforms and users conversion rates and maximize e-stores’ benefits.

Copyright

© 2022 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sitong Zhou
PY  - 2022
DA  - 2022/12/29
TI  - Analyzing Factors of Users Click Behavior on Ads Based on Logistic Regression and Machine Learning
BT  - Proceedings of the 2022 6th International Seminar on Education, Management and Social Sciences (ISEMSS 2022)
PB  - Atlantis Press
SP  - 2538
EP  - 2549
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-494069-31-2_299
DO  - 10.2991/978-2-494069-31-2_299
ID  - Zhou2022
ER  -