Research on Factors Influencing User Experience of Beijing Mobile Based on GBTD Classification Model
DOI:
https://doi.org/10.54097/d562m203Keywords:
GBTD Classification Model, Genetic Algorithm Optimization, descriptive statistics, Mobile user experience satisfaction.Abstract
To improve the quality of user experience for Beijing Mobile, this article focuses on user evaluation, evaluates the influencing factors of user satisfaction, and determines its degree of impact. Firstly, this article preprocesses existing data and classifies it into scenarios. Secondly, descriptive statistical analysis is conducted on the data, and Outlier are studied. Finally, the GBTD classification model optimized by genetic algorithm is introduced and trained to determine the main factors of satisfaction and the importance percentage of each factor. The study found that the main factors affecting the satisfaction of Beijing Mobile's voice service are: "Total GPRS traffic", "MOU in the first three months", "ARPU in the current month", and "Network issues"; The main factors that affect the satisfaction of mobile internet business are: "Poor network signal/no signal", "redirect times", and "GPRS resource usage for the month".
Downloads
References
Yuan Xiaohua, Li Mingxia, Wang Lihong, etc Descriptive Statistical Analysis of Blood Composition Quality Sampling Data [C]//Chinese Blood Transfusion Association. Paper Album of the 9th Blood Transfusion Conference of the Chinese Blood Transfusion Association. Paper Album of the 9th Blood Transfusion Conference of the Chinese Blood Transfusion Association, 2018:64
Zhang Dingding. Descriptive Statistical Analysis and SPSS Implementation [J]. Journal of Union Medical College, 2018,9 (05): 447
Qin Yu GPRS data traffic analysis and its equivalent model research [D]. Beijing Jiaotong University, 2013
Zhai Ruyu Descriptive statistics and visualization of flight delay data [D]. Heilongjiang University, 2019.
Chen Mirong Emphasize the value of descriptive statistics in social science research [N] China Social Science Journal, 2022-05-25 (002).
Zhang Wei, Yang Weisen, Bai Qian, et al. Study on the correlation between motor vehicle ownership and urban air quality in Xi'an based on descriptive statistics and grey correlation model [J]. Transportation Research, 2022,8 (03): 111-119.
He Shijian Research on recommendation algorithm based on gradient lifting decision tree and deep belief network fusion [D]. Guangxi Normal University, 2017
Qu Hongquan, Wang Zhengyi, Sheng Zhiyong, et al. Fiber intrusion signal classification based on gradient lifting decision tree algorithm [J]. Progress in Laser and Optoelectronics, 2022,59 (23): 106-113
Ou Dongxiu, Zhang Xinyin, Zhao Yuan, et al. Prediction of Train Emergency Delay Time in Urban Rail Transit Based on Gradient Enhancement Decision Tree Cascading Classification Method [J]. Urban Rail Transit Research, 2022-25 (10): 65-70.
Ma Longfei, Xiao Hanmin, Tao Jingwei, et al. An Intelligent Classification Method for Lithology Based on Gradient Enhancement Decision Tree Algorithm [J]. Oil and Gas Geology and Recovery, 2022, 29 (01): 21-29.
Liu Chunlei, Liang Ruisi, Di Yuanhao. Research on Short Text Classification Based on TFIDF and Gradient Enhancement Decision Tree [J]. Science and Technology Wind, 2019 (24): 231.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
