Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.00034 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909445699665920 |
|---|---|
| author | Huang, Chengyue Yang, Yahe |
| author_facet | Huang, Chengyue Yang, Yahe |
| contents | With the widespread application of machine learning in financial risk management, conventional wisdom suggests that longer training periods and more feature variables contribute to improved model performance. This paper, focusing on mortgage default prediction, empirically discovers a phenomenon that contradicts traditional knowledge: in time series prediction, increased training data timespan and additional non-critical features actually lead to significant deterioration in prediction effectiveness. Using Fannie Mae's mortgage data, the study compares predictive performance across different time window lengths (2012-2022) and feature combinations, revealing that shorter time windows (such as single-year periods) paired with carefully selected key features yield superior prediction results. The experimental results indicate that extended time spans may introduce noise from historical data and outdated market patterns, while excessive non-critical features interfere with the model's learning of core default factors. This research not only challenges the traditional "more is better" approach in data modeling but also provides new insights and practical guidance for feature selection and time window optimization in financial risk prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_00034 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Time Series Feature Redundancy Paradox: An Empirical Study Based on Mortgage Default Prediction Huang, Chengyue Yang, Yahe Statistical Finance Artificial Intelligence Machine Learning With the widespread application of machine learning in financial risk management, conventional wisdom suggests that longer training periods and more feature variables contribute to improved model performance. This paper, focusing on mortgage default prediction, empirically discovers a phenomenon that contradicts traditional knowledge: in time series prediction, increased training data timespan and additional non-critical features actually lead to significant deterioration in prediction effectiveness. Using Fannie Mae's mortgage data, the study compares predictive performance across different time window lengths (2012-2022) and feature combinations, revealing that shorter time windows (such as single-year periods) paired with carefully selected key features yield superior prediction results. The experimental results indicate that extended time spans may introduce noise from historical data and outdated market patterns, while excessive non-critical features interfere with the model's learning of core default factors. This research not only challenges the traditional "more is better" approach in data modeling but also provides new insights and practical guidance for feature selection and time window optimization in financial risk prediction. |
| title | Time Series Feature Redundancy Paradox: An Empirical Study Based on Mortgage Default Prediction |
| topic | Statistical Finance Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2501.00034 |