Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

98196294392 · Jun 202019922001200920182026
48 results for Loan Features

Paper uses BERT to assess P2P borrowers' credit risk from loan descriptions.

problem Information asymmetry in P2P lending due to lack of borrower data.
method Fine-tunes BERT on Lending Club dataset to generate risk scores from loan descriptions.
result BERT-generated risk scores improve XGBoost classifier's performance in loan granting.

5D AI model detects bad loans without biased features, improving consumer protection.

problem Detecting bad loans without biased features and improving consumer protection.
method Machine learning, BiMOPT features, European Banking Authority principles, AI principles, historical and validation datasets.
result 5D correctly detected 1,461 bad loans out of 1,613 (Sensitivity = 0.91, Prevalence = 0.0253, Positive Predictive Value = 0.19).

Transfer learning improves loan recovery rate forecasting under data scarcity.

problem Data scarcity in loan portfolios limits RR modeling accuracy.
method Introduces FT-MDN-Transformer, a mixture-density tabular Transformer architecture for TL.
result FT-MDN-Transformer outperforms baseline models in RR forecasting, especially under covariate and conditional shifts.

Optimal student loan repayment strategies vary based on loan size.

problem Finding the most cost-effective repayment strategy for federal student loans.
method Analyzing the impact of different repayment strategies on total cost for varying loan sizes.
result Optimal repayment strategies depend on the loan balance, with different approaches for small, large, and intermediate balances.

Machine learning improves risk prediction for online lending.

problem Traditional credit scoring models fail to utilize big data effectively.
method Collected diverse data, built and tested ensemble machine learning models (random forest and XGBoost).
result XGBoost model outperforms traditional models in loan default probability prediction.

Paper analyzes U.S. broker call rate laws of motion and their implications.

problem Understanding the dynamics and pricing of margin loans in the U.S. market.
method Analysis of monthly observations, derivation of stochastic differential equations, application of arbitrage theory.
result Margin loan interest rate follows mean-reverting behavior, with total call loan volume constituting over 70% of leveraged portfolios.

Paper proposes an intelligent credit limit management system using causal inference.

problem Traditional credit limit management strategies are heuristic and not data-driven.
method Conditional independence testing, response model, log transformation, GBDT encoding, non-linear transformation on features, well-designed metric.
result The proposed approach effectively manages credit limits and incorporates diminishing marginal effects.

In this paper we first introduce two new financial products: stock loan and capped stock loan. Then we develop a pure variational inequality method to establish explicitly the values of these stock loans. Finally, we work out ranges of fair values of parameters associated with the loans.

2010-05-09abs ↗pdf ↗

Examines how extending home loan durations affects French households financially.

problem Financial implications for households with extended home loan durations.
method Analysis of French and international home loan systems, including bullet loans and Japanese home loans.
result Extending home loan durations can reduce monthly payments but raises financial risks.

We analyze cascades of defaults in an interbank loan market. The novel feature of this study is that the network structure and the size distribution of banks are derived from empirical data. We find that the ability of a defaulted institution to start a cascade depends on an interplay of shock size and connectivity. Fu…

2013-10-06abs ↗pdf ↗

AI models predict loan rejection and default risk, reducing default risk by 70%.

problem Predicting loan rejection and default risk to reduce default risk.
method Applied Logistic Regression, Support Vector Machine, and Deep Neural Networks to lending data.
result Deep Neural Networks achieved best performance for default prediction, reducing default risk by 70%.

Current auto loans converge to super-prime credit despite remaining underwater.

problem Inefficient consumer behavior in auto loans leading to suboptimal credit risk.
method Large-sample statistical hypothesis test on transition matrix between risk bands.
result All current risk bands converge to super-prime credit, despite remaining underwater.

Paper develops a credit scoring system for micro-loans, addressing interpretability and data quality challenges.

problem Developing a credit scoring system for micro-loans with interpretability and data quality concerns.
method Introduces semi-supervised algorithm to aid model development and evaluates its performance.
result Semi-supervised algorithm aids in model development and demonstrates improved performance.

Study shows group loans on Kiva platforms speed up funding time by 3.3 days.

problem Measuring the effect of group loans on funding time in Kiva microfinance platform.
method Deep learning in natural language processing to analyze loan descriptions.
result Forming group loans speeds up funding time by about 3.3 days.

Set-Sequence model learns cross-sectional dynamics directly from time series data.

problem Predicting large cross-sections of time series data with latent cross-sectional dynamics.
method A model that learns cross-sectional structure directly, enhancing expressivity and eliminating manual feature engineering.
result Significantly outperforms strong baselines in equity portfolio optimization and loan risk prediction.

A stock loan is a loan, secured by a stock, which gives the borrower the right to redeem the stock at any time before or on the loan maturity. The way of dividends distribution has a significant effect on the pricing of the stock loan and the optimal redeeming strategy adopted by the borrower. We present the pricing mo…

2009-06-03abs ↗pdf ↗

Extends ASRF model for green and brown loans, accounting for systematic and idiosyncratic risks.

problem Credit risk assessment for portfolios of green and brown loans.
method Two-factor copula structure, skewed distributions for systematic risk, Gaussian for idiosyncratic risk, non-uniform exposure setting.
result Portfolio loss convergence to a limit reflecting green and brown loan characteristics.

This paper builds a recommendation system for borrowers on P2PL platforms to lower interest rates.

problem Help borrowers make wise decisions on P2PL platforms to achieve lower interest rates.
method Developed a recommendation system to suggest the type of loan borrowers should apply for.
result Borrowers can achieve lowered interest rates with a higher likelihood of getting funded using the recommendation system.

We derive a "semi-analytic" solution for a stock loan in which the lender forces liquidation when the loan-to-collateral ratio drops beneath a certain threshold. We use this to study the sensitivity of the contract to model parameters.

2016-02-01abs ↗pdf ↗

This paper works out fair values of stock loan model with automatic termination clause, cap and margin. This stock loan is treated as a generalized perpetual American option with possibly negative interest rate and some constraints. Since it helps a bank to control the risk, the banks charge less service fees compared …

2010-05-09abs ↗pdf ↗

XPER methodology decomposes credit scoring model performance.

problem Monitoring and understanding the key drivers of credit scoring model performance.
method XPER methodology based on Shapley values, decomposing performance metrics into feature contributions.
result A small number of features explain a large part of model performance.

A stock loan is a contract whereby a stockholder uses shares as collateral to borrow money from a bank or financial institution. In Xia and Zhou (2007), this contract is modeled as a perpetual American option with a time varying strike and analyzed in detail within a risk--neutral framework. In this paper, we extend th…

2010-10-11abs ↗pdf ↗

Study finds economic cycle affects bank loan recovery rates.

problem Understanding how economic conditions impact bank loan recovery rates.
method Used a two-state Markov switching mechanism to model credit cycle states and analyze recovery rates.
result Recovery rates and their determinants differ between good and bad economic times.

Proposes a venture bank using equity default swaps to multiply VC capital.

problem Lack of public markets for venture investments and derivative instruments.
method Introduces equity default swaps and a clawback lien to create a new derivative instrument (EDCS).
result EDCS can multiply VC capital and provide full coverage, with a clawback feature to prevent failure incentives.

Procedure verifies if machine learning models assign fixed predictions that preclude access.

problem Models assign fixed predictions that preclude access to credit and employment.
method Model-agnostic recourse verification with reachable sets.
result Models can inadvertently preclude access by assigning fixed predictions.

The study examines how limited liability and haircut affect a bank's loan portfolio's liquidity risk.

problem Impact of limited liability and haircut on a bank's loan portfolio's liquidity risk.
method Constructed a novel loan portfolio model with limited liability and haircut constraint, analyzed at three time steps.
result Model with haircut constraint leads to lesser liquidity risk.

Retail investors set interest rates for P2P loans based on borrower characteristics.

problem Understanding how individual investors price credit risk in online consumer loan auctions.
method Reverse auction framework, analyzing interest rate variance and borrower characteristics.
result Retail investors exhibit strong predictability in pricing, with gender and marital status influencing interest rates.

The authors examine the concept of probability of default for asset-backed loans. In contrast to unsecured loans it is shown that probability of default can be defined as either a measure of the likelihood of the borrower failing to make required payments, or as the likelihood of an insufficiency of collateral value on…

2013-06-28abs ↗pdf ↗

Quantum mechanics applied to credit loans for better repayment schedules.

problem Improving repayment schedules for credit loans.
method Introducing quantum mechanics concepts to credit loans, defining operators for debt, amortization, interest, and installments, and using SO(M) symmetry to optimize periodic payments.
result Optimized repayment schedules for borrowers without altering lender's earnings.

This study simulates biases in classifiers to assess fairness.

problem Mitigating biases in predictive models to ensure fairness.
method Agent-based model (ABM) to generate synthetic datasets with controlled biases, applied to offline and online learning approaches.
result Demonstrates how biases in data affect classifier outcomes and how mitigations impact feature usage.

Generative Adversarial Network (GAN) generates user-friendly explanations for loan denials.

problem Lack of explainable AI for financial services, especially in loan denials.
method Developed a GAN to generate explanations for loan denials, using a representative dataset.
result Demonstrated the GAN can generate explanations for various stakeholders, including applicants and decision makers.

New measure SEV shows non-sparse models can still have low decision sparsity.

problem Non-sparse models can still make accurate decisions based on a few features.
method Introduced Sparse Explanation Value (SEV) to measure decision sparsity, not overall model sparsity.
result Many non-sparse models have low decision sparsity, as measured by SEV.

Paper proposes a model to predict default risk in networked-guarantee loans.

problem Prediction of default risk in networked-guarantee loans is challenging due to imbalanced data and contagion risk.
method Developed a positive weighted k-nearest neighbors (p-wkNN) algorithm for standalone cases and integrated a data-driven default diffusion model.
result Proposed method outperforms conventional credit risk methods in terms of AUC on real-world data.

Model assesses loan profitability under changing credit conditions.

problem Financial institutions face risks of default and prepayment.
method Develops a Random Net Present Value (RNPV) model to evaluate profitability.
result Mean and variance of RNPV calculated at individual and portfolio levels.