Using ensemble learning and explainable AI to predict bank marketing customer subscription
Wenyue Wang, Qi Liu, Sufeng Li, Hongyan Feng · 2026
Read Using ensemble learning and explainable AI to predict bank marketing customer subscription by Wenyue Wang, Qi Liu, Sufeng Li, Hongyan Feng (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/PMC13550453.txt.
Description
Wenyue Wang and colleagues predict which bank customers will sign up for term deposits using an ensemble model that also explains itself, in a 2026 study. Marketing data are lopsided and shift between settings, which trips ordinary models. Their approach trains five varied versions of a gradient boosting method. They are weighted by validation performance. A layered explanation system then reads their decisions, scaling from single customers to the whole portfolio.
On public data the system reached a discrimination score of zero point nine five. The real test came at a Chinese city commercial bank, where a pre-deployment fine-tuning strategy lifted performance from zero point eight four to zero point nine three on the new population. Explanation analysis surfaced sensible drivers such as call duration. The authors offer the package as a balance of accuracy, transparency, and portability for bank marketing.
Catalog record
| CREATOR | Wenyue Wang, Qi Liu, Sufeng Li, Hongyan Feng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 118676 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |