Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.16182 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918103067131904 |
|---|---|
| author | Scarone, Bruno Baeza-Yates, Ricardo |
| author_facet | Scarone, Bruno Baeza-Yates, Ricardo |
| contents | We study the societal impact of pseudo-scientific assumptions for predicting the behavior of people in a straightforward application of machine learning to risk prediction in financial lending. This use case also exemplifies the impact of survival bias in loan return prediction. We analyze the models in terms of their accuracy and social cost, showing that the socially optimal model may not imply a significant accuracy loss for this downstream task. Our results are verified for commonly used learning methods and datasets. Our findings also show that there is a natural dynamic when training models that suffer survival bias where accuracy slightly deteriorates, and whose recall and precision improves with time. These results act as an illusion, leading the observer to believe that the system is getting better, when in fact the model is suffering from increasingly more unfairness and survival bias. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16182 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Impact of Pseudo-Science in Financial Loans Risk Prediction Scarone, Bruno Baeza-Yates, Ricardo Computers and Society Machine Learning We study the societal impact of pseudo-scientific assumptions for predicting the behavior of people in a straightforward application of machine learning to risk prediction in financial lending. This use case also exemplifies the impact of survival bias in loan return prediction. We analyze the models in terms of their accuracy and social cost, showing that the socially optimal model may not imply a significant accuracy loss for this downstream task. Our results are verified for commonly used learning methods and datasets. Our findings also show that there is a natural dynamic when training models that suffer survival bias where accuracy slightly deteriorates, and whose recall and precision improves with time. These results act as an illusion, leading the observer to believe that the system is getting better, when in fact the model is suffering from increasingly more unfairness and survival bias. |
| title | The Impact of Pseudo-Science in Financial Loans Risk Prediction |
| topic | Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2507.16182 |