Green credit risk assessment and prediction in China’s construction industry: based on the optuna-catboost model
Zenan Qin, Meitong Meng, Dongbao Li, Junwei Li · 2026
Read Green credit risk assessment and prediction in China’s construction industry: based on the optuna-catboost model by Zenan Qin, Meitong Meng, Dongbao Li, Junwei Li (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13483942.txt.
Description
Qin and team built a forecasting model for green credit risk in China's construction industry, where loans carry both ordinary default risk and environmental risk. Green credit rewards cleaner building, but banks need warning when borrowers may fail. Their 2026 study first measured risk with an adjusted version of a classic default model, then ranked candidate indicators and trained a boosted-tree predictor tuned by an automated search tool.
The tuned model, nicknamed OptCAT, out-predicted four rival learning methods including random forests and gradient boosting in their comparisons. Its tuning method also beat five other search strategies for finding good model settings. The authors assembled the winning indicators into a risk assessment system tailored to construction firms. Qin offers the pipeline as a reference for lenders, while admitting the small number of real defaults limits how far the results stretch.
Catalog record
| CREATOR | Zenan Qin, Meitong Meng, Dongbao Li, Junwei Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 125 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |