Paper: arXiv 2510.07444

Authors: Albert Di Wang, Ye Du

Abstract

Risk management is a prominent issue in peer-to-peer lending. An investor may naturally reduce his risk exposure by diversifying instead of putting all his money on one loan. In that case, an investor may want to minimize the Value-at-Risk (VaR) or Conditional Value-at-Risk (CVaR) of his loan portfolio. We propose a low degree of freedom deep neural network model, DeNN, as well as a high degree of freedom model, DSNN, to tackle the problem. In particular, our models predict not only the default probability of a loan but also the time when it will default. The experiments demonstrate that both models can significantly reduce the portfolio VaRs at different confidence levels, compared to benchmarks. More interestingly, the low degree of freedom model, DeNN, outperforms DSNN in most scenarios.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 6.0/10 (capped from 8.0: transaction costs not modelled; see penalty flags)
  • Quadrant: Holy Grail — high math complexity, high empirical rigor (effective empirical rigor capped from 8.0)

Why this score: The paper employs advanced mathematical concepts including VaR optimization, probability distributions, survival analysis, and neural network architectures (DSNN/DeNN) with detailed derivations, justifying a high math score. It demonstrates empirical rigor by using real-world Lending Club data, implementing deep learning models, conducting Monte-Carlo simulations, and reporting comparative performance against benchmarks, making it backtest-ready.

Research Flowchart

  flowchart TD
  A["Research Goal: Minimize VaR of Loan Portfolio using Deep Neural Networks"] --> B["Methodology: DeNN & DSNN Models"]
  B --> C["Data Input: Peer-to-Peer Lending Historical Data"]
  C --> D{"Computational Process: Predict Default Probability & Timing"}
  D --> E["Simulate Portfolio Distributions"]
  E --> F["Calculate VaR & CVaR"]
  F --> G["Key Findings: Models significantly reduce Portfolio VaR"]
  G --> H["Outcome: Low-freedom DeNN outperforms High-freedom DSNN"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes two deep neural network models, DeNN (low degree of freedom) and DSNN (high degree of freedom), to predict loan default probabilities and times, and uses Monte‑Carlo simulations to minimize portfolio VaR and CVaR.

Source sentence
We propose a low degree of freedom deep neural network model, DeNN, as well as a high degree of freedom model, DSNN, to tackle the problem.

Assumes 4

  • Loan returns are independent of each other. model
    Source sentence
    assuming loans’ returns are independent of each other.
  • Portfolio consists of a fixed number of 40 loans. execution
    Source sentence
    We set the portfolio size 𝑛=40, and randomly sample 2,000 portfolios with replacement from the test set.
  • Monte‑Carlo simulation of returns approximates the true VaR/CVaR distribution. statistical
    Source sentence
    we use Monte‑Carlo methods to simulate possible realized returns for loans in a portfolio
  • The cleaned Lending Club data accurately represents loan characteristics. data
    Source sentence
    After thoroughly cleansing and preprocessing, 244,720 loans with 104 features and 2 labels (lifetime and default indicator) are left.

Data

  • Lending Club loan dataset · Lending Club fundamentals public
    244,720 loans
    Source sentence
    The dataset was downloaded from Lending Club, one of the largest P2P online lending platforms in the world. After thoroughly cleansing and preprocessing, 244,720 loans with 104 features and 2 labels (lifetime and default indicator) are left.

Costs

Not modeled A trading or execution result is reported without costs.

Finds 4

  • Both DeNN and DSNN significantly reduce portfolio VaR at various confidence levels compared to equal‑weight and random‑weight baselines. performance
    Source sentence
    both DeNN and DSNN are significantly outperforming the Equal weights and Random weights baselines in VaRs minimization.
  • DeNN outperforms DSNN in most scenarios despite having a lower degree of freedom. performance
    Source sentence
    the low degree of freedom model, DeNN, outperforms DSNN in most scenarios.
  • DeNN reduces VaR at 95% confidence by 17.45% when optimizing CVaR' compared to the LRM benchmark. performance
    Source sentence
    comparing to LRM, the DeNN reduces the VaR at 95% when optimizing CVaREF% by 17.45%, which corresponds to a decrease of
  • DSNN reduces VaR at 95% confidence by 6.26% when optimizing VaR' compared to a simple SNN benchmark. performance
    Source sentence
    comparing to simple SNN, the DSNN reduces the VaR at 95% when optimizing VaREF% by 6.26%, which corresponds to a decrease of annualized loss from 44.40% to 41.62%.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 45 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.