New credit attribution methods for machine learning models using relaxed stability guarantees.
problem Ensuring proper attribution in generative models trained on existing works.
method Proposed new definitions of stability that allow for non-stable processing of a subset of datapoints with permission.
result Extended well-studied stability notions and provided a comprehensive characterization of learnability.
The study improves credit evaluation in peer-to-peer lending using machine learning.
problem Traditional credit histories are insufficient for distinguishing good from bad borrowers.
method Used machine learning classification and clustering algorithms to predict creditworthiness.
result Achieved 65% F1 and 73% AUC on LendingClub data, identifying key secondary attributes.
We present an analysis of the credit market of Japan. The analysis is performed by investigating the bipartite network of banks and firms which is obtained by setting a link between a bank and a firm when a credit relationship is present in a given time window. In our investigation we focus on a community detection alg…
LLMs can help explain credit risk models but not autonomously.
problem Leveraging LLMs for post-hoc explainability in credit risk models.
method Comparison of LLM outputs with SHAP and coefficient-based attributions on three LMs.
result LLMs reliably preserve feature-importance rankings but poorly align with autonomous explanations.
The study tests and optimizes fairness in credit scoring models.
problem Discrimination in credit scoring models based on protected attributes.
method Formal testing and variable identification to optimize fairness and performance.
result Guidance on monitoring and improving algorithmic fairness in credit scoring.
Study uses synthetic data to estimate credit risk for underbanked consumers in Istanbul.
problem Estimating credit risk for underbanked consumers lacking formal credit records.
method Created synthetic dataset, used retrieval augmented generation, trained CatBoost, LightGBM, and XGBoost models.
result Alternative financial data improves credit risk estimation, raising AUC by 13%.
Method to decompose portfolio performance into FX, interest rate, carry, and residual market risks.
problem Understanding the sources of portfolio performance.
method Decomposition of portfolio PnL into four components.
result Demonstrated usefulness of the method through fund performance analysis.
We detect the backbone of the weighted bipartite network of the Japanese credit market relationships. The backbone is detected by adapting a general method used in the investigation of weighted networks. With this approach we detect a backbone that is statistically validated against a null hypothesis of uniform diversi…
Study examines fairness in machine learning for credit scoring.
problem Bias in machine learning models for credit scoring.
method Comprehensive experimental study of fairness-aware machine learning models.
result Fairness-aware models improve fairness while maintaining accuracy.
Study finds public procurement awards, especially NGEU-funded ones, boost new lending.
problem Understanding the impact of public procurement on new lending.
method Panel data local projections model, controlling for various factors.
result Public procurement awards, particularly NGEU-funded ones, significantly increase new lending.
Proposes a method to simulate data for testing credit risk scorecard stability.
problem Ensuring credit risk scorecards remain representative of the population over time.
method Specification of bad ratios to generate parameter values for scorecards.
result Simulated data adheres closely to specified bad ratios.
We give a detailed account of correlations between credit sector/quality and treasury curve factors, using the robust framework of the Barclays POINT Global Risk Model. Consistent with earlier studies, we find a strong negative correlation between sector spreads and rate shifts. However, we also observe that the correl…
Proposes a framework to explain KS deterioration in credit risk models.
problem Inconsistent and ad hoc diagnosis of KS decline in credit risk models.
method Counterfactual diagnostic framework attributing KS decline to sampling variability, portfolio composition, covariate shift, and residual deterioration.
result The proposed approach provides more interpretable and governance-relevant explanations than threshold-based review alone.
Credit Suisse First Boston (CSFB) launched in 1997 the model CreditRisk+ which aims at calculating the loss distribution of a credit portfolio on the basis of a methodology from actuarial mathematics. Knowing the loss distribution, it is possible to determine quantile-based values-at-risk (VaRs) for the portfolio. An o…
Synthetic data improves credit scoring models' performance without compromising borrower privacy.
problem Scarcity of real data for credit scoring models due to privacy concerns.
method Privacy-preserving training with synthetic data.
result Credit scoring models trained with synthetic data show a reduction of 3% in AUC and 6% in KS compared to real data models.
One of the key elements in the banking industry rely on the appropriate selection of customers. In order to manage credit risk, banks dedicate special efforts in order to classify customers according to their risk. The usual decision making process consists in gathering personal and financial information about the borr…
KACDP model improves credit default prediction with enhanced interpretability.
problem Insufficient interpretability and limited performance in credit default prediction.
method Kolmogorov-Arnold Networks (KANs) for handling complex multi-dimensional data.
result KACDP model outperforms mainstream models in performance metrics.
Model predicts default risk based on company's financial forecasts and credit conditions.
problem Estimating the risk of a company defaulting on its financial obligations.
method Developed an equilibrium model linking interest rates to corporate performance and credit supply.
result Estimates idiosyncratic default risk and provides forward-looking probability of default (PD).
New framework for attributing online marketing touchpoints.
problem Fine-grained attribution of individual touchpoints' effects.
method Graphical point process framework for studying conversion effects.
result Proposed methods allocate proper credit to touchpoints for each customer's path.
Bayesian approach scores influential training examples for model predictions.
problem Enhance interpretability and safety of machine learning models.
method Formulate TDA as a Bayesian information-theoretic problem, scoring subsets by information loss.
result Method aligns with classical influence scores while promoting diversity for subsets.
Unified framework connects credit risk metrics with information theory.
problem Disconnection between industry-standard metrics and statistical theory.
method Unified information-theoretic framework, proving IV equals PSI, deriving standard errors, formalizing trade-off, automated binning with XGBoost.
result Unified framework connects IV and PSI, providing statistical foundation for metrics.
Ordinal regression predicts the objects' labels that exhibit a natural ordering, which is important to many managerial problems such as credit scoring and clinical diagnosis. In these problems, the ability to explain how the attributes affect the prediction is critical to users. However, most, if not all, existing ordi…
This paper addresses credit valuation adjustment with a new closeout convention.
problem Accurate estimation of financial claim value considering counterparty credit risk.
method Theoretical and computational analysis of a nonlinear valuation system using neural networks.
result A neural network-based algorithm effectively solves the high-dimensional nonlinear valuation system.
Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite potential gains in productivity and efficiency, several potential problems have yet to be addressed, particularly the potential for unintentional discrimination. We present an…
CDLEEDS detects local changes in evolving data streams for accurate feature attributions.
problem Local feature attributions become obsolete in evolving data streams.
method CDLEEDS, a flexible framework for detecting local change and concept drift.
result CDLEEDS reliably detects both local and global concept drift.
New insights into how to inspect and learn from multi-stage processes and AI reasoning.
problem Understanding how to attribute outcomes to early stages in multi-stage operations and AI reasoning.
method Information-theoretic analysis and mathematical proofs of four key results.
result Uniform checkpoint spacing is minimax-optimal for inspection design under homogeneous signal attenuation.
In this paper we propose a method to obtain global explanations for trained black-box classifiers by sampling their decision function to learn alternative interpretable models. The envisaged approach provides a unified solution to approximate non-linear decision boundaries with simpler classifiers while retaining the o…
Machine Learning techniques have become pervasive across a range of different applications, and are now widely used in areas as disparate as recidivism prediction, consumer credit-risk analysis and insurance pricing. The prevalence of machine learning techniques has raised concerns about the potential for learned algor…
This paper proposes a new algorithm for learning guidance rewards in RL.
problem Long-term temporal credit assignment in sparse or delayed reward environments.
method Surrogate RL objective with trajectory-space smoothing to learn guidance rewards.
result Guidance rewards can be learned without additional neural networks and have intuitive interpretation.
New research on Shapley values for feature attribution in machine learning, considering model vs. data fidelity.
problem Controversy in connecting machine learning models to coalitional games, differing approaches.
method Investigates two approaches: interventional vs. observational conditional expectation Shapley values for linear models.
result The choice between model and data fidelity depends on the specific application.
Machine learning models are widely adopted in scenarios that directly affect people. The development of software systems based on these models raises societal and legal concerns, as their decisions may lead to the unfair treatment of individuals based on attributes like race or gender. Data preparation is key in any ma…
New research shows fairness in machine learning can sometimes make disadvantaged groups worse off.
problem The impact of fairness constraints in machine learning on different groups.
method Unified, population-level (Bayes) framework for binary classification under prevalent group fairness notions.
result Fairness in machine learning can lead to leveling down, making one or both groups worse off.
Improves local model explanations using GANs and Linear Model Trees.
problem Need for accurate and intuitive explanations of complex machine learning models.
method Generative Adversarial Network (GAN) for synthetic data generation and Linear Model Trees for surrogate model training.
result Significantly improved local model explanations with contextual information.
Machine learning algorithms can unintentionally discriminate; tools detect and fix this.
problem Unintentional discrimination in machine learning algorithms.
method Statistical tools to detect and eliminate biases.
result Tools can identify and mitigate algorithmic discrimination.
New analysis improves accuracy of Newton step and influence function data attributions.
problem Improving accuracy of data attribution methods for logistic regressions.
method Introducing a new analysis of Newton Step and Influence Function data attribution methods for convex learning problems.
result Proved asymptotically tight error bounds for Newton Step and Influence Function data attribution methods.
Fairness has become a central issue for our research community as classification algorithms are adopted in societally critical domains such as recidivism prediction and loan approval. In this work, we consider the potential bias based on protected attributes (e.g., race and gender), and tackle this problem by learning …
We present a study of price impact in the over-the-counter credit index market, where no limit order book is used. Contracts are traded via dealers, that compete for the orders of clients. Despite this distinct microstructure, we successfully apply the propagator technique to estimate the price impact of individual tra…
Study shows OAT decomposition generates unexplained profit and loss, while SU decompositions depend on risk factor order.
problem Understanding profit and loss attribution in financial markets.
method Used financial market data from 2003 to 2022 to compare OAT, SU, and ASU decompositions.
result SU decompositions are sensitive to risk factor order and cannot identify all relevant risk factors.
We introduce Generalized Integrated Gradients (GIG), a formal extension of the Integrated Gradients (IG) (Sundararajan et al., 2017) method for attributing credit to the input variables of a predictive model. GIG improves IG by explaining a broader variety of functions that arise from practical applications of ML in do…
Study shows how to better estimate credit provisions and economic capital.
problem Estimating credit provisions and economic capital accurately.
method Using supermodularity ordering properties and elliptically distributed latent factors.
result Convex risk measures of credit losses are nondecreasing w.r.t. various covariances.
This study surveys methods for detecting outliers in spatial data.
problem Detecting outliers in spatial data to avoid misinterpretation and enhance analysis.
method Survey of existing outlier detection methods for spatial data.
result Outliers in spatial data can be valuable if analyzed separately.
Machine learning (ML) can automate decision-making by learning to predict decisions from historical data. However, these predictors may inherit discriminatory policies from past decisions and reproduce unfair decisions. In this paper, we propose two algorithms that adjust fitted ML predictors to make them fair. We focu…
Study shows how macroprudential policies affect credit growth in Israel, especially in housing and business sectors.
problem Impact of macroprudential policies on credit growth in Israel.
method Bank-level panel data analysis for Israel, 2004-2019; interaction of monetary and macroprudential policies.
result Accommodative monetary policy interacts with macroprudential policies to increase total credit growth.
Unified view on selective credit assignment for reinforcement learning.
problem Efficient credit assignment in reinforcement learning.
method Unified temporal-difference algorithms with selective weightings.
result New algorithms for backward credit assignment and off-policy learning.
We apply Geometric Arbitrage Theory to obtain results in mathematical finance for credit markets, which do not need stochastic differential geometry in their formulation. We obtain closed form equations involving default intensities and loss given defaults characterizing the no-free-lunch-with-vanishing-risk condition …
This article presents FVA and CVA of a bilateral derivative in a coherent manner, based on recent developments in fair value accounting and ISDA standards. We argue that a derivative liability, after primary risk factors being hedged, resembles in economics an issued variable funding note, and should be priced at the m…
This paper develops a machine learning model to assess credit risk in UAE commercial banks.
problem Lack of precision in conventional credit rating tools for accurate credit risk prediction.
method Constructs a credit risk assessment model using Linear Discriminant Analysis.
result Demonstrates improved accuracy in predicting good and bad creditors compared to conventional methods.
Study evaluates SHAP for credit card default model consistency.
problem Model transparency and fairness in credit card default prediction models.
method Evaluates SHAP stability in credit card default prediction models via a case study.
result SHAP consistency is related to variable importance level.