An Intelligent Automotive Marketing Monitoring Platform Based on Vehicle Network Data

Yafei Wang; Dehuan Kong; Xue Zheng; Fan Zhang

doi:10.62051/ijgem.v7n1.15

Authors

Yafei Wang
Dehuan Kong
Xue Zheng
Fan Zhang

DOI:

https://doi.org/10.62051/ijgem.v7n1.15

Keywords:

Internet of Vehicles data, Feature dimension, Feature engineering, Intelligent sales systems for automobiles

Abstract

With the rapid development of Internet of Vehicles technology, the application of Internet of Vehicles data in the automotive sales field has gradually become an important means to improve sales efficiency and customer experience. This paper aims to study and construct a monitoring system for intelligent automotive sales systems based on connected vehicle data. First, handle the missing values and outliers according to the different characteristics of the Internet of Vehicles data; Then, feature engineering is carried out based on the distribution trend of the data and the relationship between feature dimensions; Finally, build an intelligent sales system that includes the data collection layer, data transmission layer, data storage and processing layer, business logic layer and application layer. The research results show that the system can effectively improve the accuracy and efficiency of car sales, provide strong support for the decision-making of car enterprises, and has significant practical significance and application value.

Downloads

Download data is not yet available.

References

[1] Lu Haibo, Chen Chengfeng, Chen Chunyan. Research on the application of big data from Internet of Vehicles in automotive reliability testing [J]. Automotive Practical Technology, 2024, 49 (18): 87-91. DOI:10.16638/j.cnki.1671-7988.2024.018.016.

[2] Li Zonghua, Zhai Jun, Wang Xianjun, et al. Electric vehicle driving evaluation application based on Internet of Vehicles data [J]. Automotive Practical Technology, 2022, 47 (13): 15-20. DOI:10.16638/j.cnki.1671-7988.2022.013.005.

[3] Wu, Z., Yang, J., Zhang, F. et al. Exploring automobile brand power: A multi - dimensional approach. Environ Dev Sustain (2024). https://doi.org/10.1007/s10668-024-05089-0.

[4] Zhang Fan, Guo Yaxin, Yang Jing, et al. Research on prediction of electric quantity based on GBDT+ feature engineering method [J]. Electron Quality, 2020, (01): 1-4.

[5] Y. Jing, H. Huiying, Z. Fan and Z. Yishu, "Research on Automobile User Association Recommendation Algorithm Based on Feature Attribute and Matrix Decomposition," 2024 International Conference on Computers, Information Processing and Advanced Education (CIPAE), Ottawa, ON, Canada, 2024, pp. 594-600, doi: 10.1109 / CIPAE64326.2024.00114.

[6] Liu Yulin, Bai Yang, Cui Bin, et al. A review of automated feature engineering for machine learning [J]. Computer Applications and Software, 2025, 42 (01): 1-10+40.

[7] Sheng Zhongsong. User Purchase prediction based on feature learning and ensemble algorithms [D]. Sichuan university, 2021. DOI: 10.27342 /, dc nki. Gscdu. 2021.000464.