@article{393, author = "Xiangrong Shi and Qi Zheng and Pengsai Guo and Yifei Ye", abstract = "In recent years, credit debt default events have occurred frequently, and the current credit debt default has become a common phenomenon in the capital market. Many high-rated companies have also defaulted on their bonds, and credit ratings are no longer sufficient to predict a company's default. This paper utilizes the mainstream Logistic algorithm and XGboost algorithm to construct a credit debt default risk method, the performance of the two is compared and analyzed, and the historical data information is used to improve the original algorithm, and the experimental results testify that the improved model prediction effect is better than the original algorithm, of which the enhanced-XGboost algorithm has the best comprehensive performance in various indicators, which is more suitable for credit debt risk audit.", issn = "23942894", journal = "IJASM", keywords = "Credit Debt Default;Logistic;XGBoost;Algorithm Boosting;Risk Audits", month = "July", number = "4", pages = "61-72", title = "{T}he use of the {I}mproved {XGB}oost {A}lgorithm in {C}redit {D}ebt {R}isk {A}uditing", volume = "9", year = "2022", }