生物启发的深度神经网络用于预测智利学生贷款计划中的收入报告中断
Yoslandy Lazo1, Álex Paz2, Broderick Crawford1
1Escuela de Ingeniería Informática, Pontificia Universidad Católica de Valparaíso, Avenida Brasil 2241, Valparaíso 2362807, Chile.
Biomimetics (Basel, Switzerland)
|February 26, 2026
概括
这项研究使用先进的机器学习预测智利学生贷款的收入报告变化. 生物启发的深度神经网络显著提高了信用风险预测准确度,而不是传统模型.
科学领域:
- 信用风险管理 信用风险管理
- 机器学习应用 机器学习应用
- 金融数据分析 金融数据分析
背景情况:
- 学生贷款计划面临的挑战是收入报告中断.
- 准确预测违规行为对于有效的信用风险管理至关重要.
- 现有的机器学习模型缺乏整合归算和验证的方法学上稳健的评估.
研究的目的:
- 开发和评估一个强大的管道,用于在学生贷款收入报告中预测不连续性.
- 将生物灵感深度神经网络 (DNN) 与随机森林 (RF) 分类器进行比较.
- 为学生信用提供可复制的风险分析方法.
主要方法:
- 在22,303个记录上实施了MissForest归算和基于SMOTE的平衡管道.
- 对生物启发的DNN和随机森林分类器进行了比较评估.
- 使用35个分层分区进行重复的交叉验证.
主要成果:
- 生物启发的DNN在关键指标 (AUC,F1分数) 上显著超过了RF分类器.
- DNN表现出优异的性能,AUC为0.9991与0.9709,F1得分为0.9966与0.9497.
- 可解释性分析显示,金融变量是关键预测因素,人口统计数据的影响最小.
结论:
- 生物启发的DNN提供了一个非常准确和稳定的方法来预测收入报告中断.
- 开发的方法改善了学生贷款的信用风险管理实践.
- 对于这个特定的任务,财务数据比人口统计数据具有更大的预测能力.
相关概念视频
01:08Outliers and Influential Points
6.5K
An outlier is an observation of data that does not fit the rest of the data. It is sometimes called an extreme value. When you graph an outlier, it will appear not to fit the pattern of the graph. Some outliers are due to mistakes (for example, writing down 50 instead of 500), while others may indicate that something unusual is happening. Outliers are present far from the least squares line in the vertical direction. They have large "errors," where the "error" or residual is the...
6.5K
01:03Prediction Intervals
3.5K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.5K