Integrated GBDT and logistic power customer complaint early warning method

Nuo Tian; Jing Yang; Jiajia Wang; Longzhu Zhu; Jian Gong; Feng Qian; Yanyan Li

doi:10.1117/12.2639291

19 October 2022 Integrated GBDT and logistic power customer complaint early warning method

Nuo Tian, Jing Yang, Jiajia Wang, Longzhu Zhu, Jian Gong, Feng Qian, Yanyan Li

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 1229460 (2022) https://doi.org/10.1117/12.2639291
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

The traditional early warning method of power user complaints, the complaint classification management model is not perfect, and the prediction accuracy rate is low. For this reason, an early warning method for power user complaints is designed that integrates GBDT and Logistic. This paper obtains grid customer behavior preference data, focusing on mining potential customers. On this basis, customer satisfaction characteristics are extracted, which promotes customer demand feedback. This paper divides power customers into different categories and builds a complaint classification management model. This paper uses a decision tree as the basic learner, using GBDT and Logistic to establish a complaint early warning mode. The experimental results show that the average prediction accuracy of this method is 83.367% in the 5dB noise environment. The average prediction accuracy of this method is 53.602% in the 10dB noise environment. The prediction accuracy of this method is higher than the two compared methods, which shows that the method in this paper can achieve the purpose of improving the prediction accuracy.

Citation Download Citation

Nuo Tian, Jing Yang, Jiajia Wang, Longzhu Zhu, Jian Gong, Feng Qian, and Yanyan Li "Integrated GBDT and logistic power customer complaint early warning method", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 1229460 (19 October 2022); https://doi.org/10.1117/12.2639291

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available