Summary of Advanced User Credit Risk Prediction Model Using Lightgbm, Xgboost and Tabnet with Smoteenn, by Chang Yu et al.
Advanced User Credit Risk Prediction Model using LightGBM, XGBoost and Tabnet with SMOTEENN
by Chang Yu, Yixin Jin, Qianwen Xing, Ye Zhang, Shaobo Guo, Shuchen Meng
First submitted to arxiv on: 7 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This study addresses the crucial challenge of identifying qualified credit card holders among a large number of applicants for bank credit risk assessment. To tackle this issue, researchers leveraged machine learning (ML) models to streamline the process. They utilized a dataset of over 40,000 records from a commercial bank and compared various dimensionality reduction techniques like Principal Component Analysis (PCA) and t-distributed Stochastic Neighbor Embedding (T-SNE) for preprocessing high-dimensional datasets. Additionally, they performed in-depth adaptation and tuning of distributed models such as LightGBM and XGBoost, as well as deep models like Tabnet. By combining SMOTEENN with these techniques, the researchers achieved excellent results, demonstrating that LightGBM combined with PCA and SMOTEENN can accurately predict high-quality customers. This study showcases the potential of ML models in bank credit risk assessment, contributing to the development of more reliable and powerful AI intelligent models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps banks figure out which people are good credit risks. Right now, it takes a lot of time and effort to check all the applicants. The researchers used special computer programs called machine learning models to make this process faster and better. They looked at a huge dataset with over 40,000 records from a bank and tried different ways to get the data ready for analysis. They also tested different types of computer models to see which one worked best. In the end, they found that using certain combinations of these techniques could help banks accurately identify good credit risks. |
Keywords
» Artificial intelligence » Dimensionality reduction » Embedding » Machine learning » Pca » Principal component analysis » Xgboost
