[论文] Quantum Feature Engineering for Credit Default Prediction: When and Why IQP Circuits Help Linear Classifiers (arXiv:2609.10505)

论文概要

研究领域: ML
作者: Menachem Finkelstein, Diana Legziel Levy, Zohar Yakhini, Sarel Cohen
发布时间: 2026-09-09
arXiv: 2609.10505

中文摘要

信用违约预测是一个表格分类问题，F1分数的微小提升直接转化为金融风险敞口的降低。本文探究瞬时量子多项式时间(IQP)电路能否产生改善分类器性能的特征，超越原始经典基线和核PCA（最强的无监督经典非线性替代方法）。在UCI信用卡违约数据集上使用五折交叉验证，发现将16个IQP特征（n=8量子比特）附加到逻辑回归模型上将F1从0.462提升到0.517(+0.055, p<0.0001)。核PCA在相同特征数下仅达到0.493。没有其他分类器（随机森林、SVM、XGBoost、k-NN）受益，这指向线性可表达性机制而非通用改进。

原文摘要

Credit default prediction is a tabular classification problem in which modest gains in F1 translate directly into reduced financial exposure. We ask whether Instantaneous Quantum Polynomial-time (IQP) circuits can produce features that improve a classifier over both its raw classical baseline and Kernel PCA - the strongest unsupervised classical non-linear alternative - at an equal feature budget. The dataset provides 23 financial attributes per client; for an n-qubit circuit we select n of them, encode each as a rotation angle, and read 2n expectation values back out as new features. The motivation for using a quantum circuit is computational: an n-qubit IQP circuit runs in constant depth and encodes feature correlations in a 2^n-dimensional Hilbert space, whereas classical simulation of its exact output statistics scales exponentially in n. Using the UCI Default of Credit Card Clients dataset and five-fold cross-validation, we find that appending 16 IQP features (n = 8 qubits) to a Logistic Regression model raises F1 from 0.462 to 0.517 (+0.055, p < 0.0001). Kernel PCA, the next-best method, reaches only 0.493 at the same feature count; the gap survives Benjamini-Hochberg correction across 12 tests (p = 0.00007). No other classifier - Random Forest, SVM, XGBoost, or k-NN - benefits, which points to a linear-expressivity mechanism rather than a generic improvement. We also show that how the 8 input features are chosen matters: Random Forest importance-guided selection reaches F1 = 0.523, while encoding maximally uncorrelated features drops it to 0.496, demonstrating that the circuit amplifies informative structure rather than creating it from scratch.

自动采集于 2026-09-11

#论文 #arXiv #ML #小凯