Utilizing the LightGBM Algorithm for Operator User Credit Assessment Research

TL;DR

The paper tackles operator-based mobile user credit assessment by leveraging massive telecom data and a fusion modeling approach around LightGBM. It introduces four feature subsets derived from user portraits, builds base models with LightGBM (and other algorithms) on each subset, and then refines predictions with ensemble methods including Stacking, Blending, and Voting, finding that LightGBM-Stacking yields the strongest performance. Key findings show that LightGBM consistently outperforms traditional baselines, and ensemble fusion often surpasses a single model, with Stacking providing the best gains. The work has practical implications for telecom operators seeking accurate, scalable credit evaluation to inform decisions and optimize benefits, while contributing methodological insights into feature engineering and multi-model fusion. $MAE$, $MAPE$, $RMSE$, and $R^2$ are used to quantify improvements across datasets, reinforcing the value of data-driven, ensemble-based credit assessment in this domain.

Abstract

Mobile Internet user credit assessment is an important way for communication operators to establish decisions and formulate measures, and it is also a guarantee for operators to obtain expected benefits. However, credit evaluation methods have long been monopolized by financial industries such as banks and credit. As supporters and providers of platform network technology and network resources, communication operators are also builders and maintainers of communication networks. Internet data improves the user's credit evaluation strategy. This paper uses the massive data provided by communication operators to carry out research on the operator's user credit evaluation model based on the fusion LightGBM algorithm. First, for the massive data related to user evaluation provided by operators, key features are extracted by data preprocessing and feature engineering methods, and a multi-dimensional feature set with statistical significance is constructed; then, linear regression, decision tree, LightGBM, and other machine learning algorithms build multiple basic models to find the best basic model; finally, integrates Averaging, Voting, Blending, Stacking and other integrated algorithms to refine multiple fusion models, and finally establish the most suitable fusion model for operator user evaluation.

Figures (4)

• Figure 1: Comparison of basic models of consumer capacity
• Figure 2: Comparison of models of location trajectory
• Figure 3: Comparison of models of application behavior preference
• Figure 4: Comparison of basic models of others