Clustering Analysis of User Loyalty Based on K-means

Authors

  • Qiushui Fang Guangdong lingnan Pass co., LTD., Guangzhou, 510000, China
  • Zhiming Li Guangdong lingnan Pass co., LTD., Guangzhou, 510000, China
  • Mengtian Leng Guangdong lingnan Pass co., LTD., Guangzhou, 510000, China
  • Jincheng Wu Guangdong lingnan Pass co., LTD., Guangzhou, 510000, China
  • Zhen Wang Guangdong lingnan Pass co., LTD., Guangzhou, 510000, China

DOI:

https://doi.org/10.30564/jmser.v2i2.1851

Abstract

In recent years, the rise of machine learning has made it possible to further explore large data in various fields. In order to explore the attributes of loyalty of public transport travelers and divide these people into different clustering clusters, this paper uses K-means clustering algorithm (K-means) to cluster the holding time, recharge amount and swiping frequency of bus travelers. Then we use Kernel Density Estimation Algorithms (KDE) to analyze the density distribution of the data of holding time, recharge amount and swipe frequency, and display the results of the two algorithms in the way of data visualization. Finally, according to the results of data visualization, the loyalty of users is classified, which provides theoretical and data support for public transport companies to determine the development potential of users.

Keywords:

Machine Learning, Public Transportation, K_means, KDE

References

[1] Zhou Tao, Zhai Changxu, Gao Zhigang. Research on OD calculation technology based on bus IC card data [J]. Urban transportation, 2007 (03): 48-52

[2] Li Xiangyun, Ren Shuai, Zhang Weigang, Wu JUANJUAN, Wu Jing. Prediction method of bus arrival based on Gaussian process regression [J / OL]. Computer technology and development, 2019 (09): 1-7

[3] Li Goldman Sachs, Peng Ling, Li Xiang, Wu Tong. Study on short-term passenger flow prediction of urban bus stations based on LSTM [J]. Highway transportation technology, 2019,36 (02): 128-135

[4] Zhou Siyuan, Liu Jiayu, Chen Jiayi, Ren Yue, Dou Wanfeng. Station matching method based on bus IC card passenger flow data [J]. Electronic technology and software engineering, 2017 (12): 173-174

[5] Xu Zeda, Yao Minfeng. Optimization method of conventional public transport under the common line relationship between rail transit and conventional public transport [J]. Journal of Huaqiao University (NATURAL SCIENCE EDITION), 2018,39 (04): 562-568

[6] Zhang Tieyan. Population division and travel characteristics analysis based on public transportation IC card data -- Taking Qingdao as an example [a] Academic Committee of urban transport planning of China Urban Planning Society. Innovation driven and intelligent development: Proceedings of 2018 China Annual Conference of urban transport planning [C]. Academic Committee of urban transport planning of China Urban Planning Society: Urban Transport Research Institute of China urban planning and Design Institute, 2018:9

[7] Wang Zhengwu, Liu Anqi, Tan Kangkang. Optimization of DRC bus operation cycle under uneven passenger distribution [J]. Transportation science and engineering, 2016,32 (02): 85-88

[8] Li Hui. Analysis and Research on potential customer development and customer loyalty [D]. Yanshan University, 2016

Downloads

How to Cite

Fang, Q., Li, Z., Leng, M., Wu, J., & Wang, Z. (2020). Clustering Analysis of User Loyalty Based on K-means. Journal of Management Science & Engineering Research, 2(2), 4–8. https://doi.org/10.30564/jmser.v2i2.1851

Issue

Article Type

Article