Time Series Feature Redundancy Paradox: An Empirical Study Based on Mortgage Default Prediction
원문 초록
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 The experimental results indicate that extended time spans may introduce noise from historical data and outdated market patterns, while excessive non-critical features interfere with the model's learning of core default factors.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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Predicting Graph Structure via Adapted Flux Balance Analysis
Robust Online Time Series Prediction with Recurrent Neural Networks
Foundation models for time series forecasting: Application in conformal prediction
SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs
Bayesian Joint Model of Multi-Sensor and Failure Event Data for Multi-Mode Failure Prediction
MS-TVNet:A Long-Term Time Series Prediction Method Based on Multi-Scale Dynamic Convolution
토론
이 논문과 연결된 포럼 글이 아직 없습니다.