This paper tackles credit card fraud detection using graph-based learning methods.
problem Detecting credit card fraud to reduce financial losses.
method Graph p-Laplacian based semi-supervised learning combined with undersampling techniques.
result Graph p-Laplacian semi-supervised learning outperforms current methods.
A new approach models credit card transactions using HMMs to detect fraud.
problem Detecting credit card fraud using isolated event analysis.
method Model sequences from three perspectives using HMMs and combine likelihoods as features.
result Improved fraud detection effectiveness compared to state-of-the-art methods.
Enhances fraud detection with multiple HMM perspectives.
problem Detecting credit card fraud from sequential transactions.
method Modeling credit card transactions from three perspectives (card-holder, terminal, amount/time) using HMMs and combining likelihoods as features.
result 15% increase in precision-recall AUC compared to state-of-the-art methods.
Study reveals the complex topology of real-world credit card transactions.
problem Understanding the true structure of real-world money flows from credit card data.
method Analysis of real-world credit card transaction data from a major bank, creation of a stochastic model.
result Real-world credit card transactions exhibit nontrivial characteristics in their topology.
Generative Adversarial Networks improve credit card fraud detection.
problem Detecting fraudulent credit card transactions accurately.
method Using GANs to generate synthetic data for oversampling.
result Wasserstein-GAN produces more realistic fraudulent transactions.
Paper explores active learning strategies for real-time credit card fraud detection.
problem Challenges in labeling and imbalanced transaction data for real-time fraud detection.
method Investigates active learning strategies for querying unlabeled transactions, comparing supervised, semi-supervised, and unsupervised approaches.
result Highlights an exploitation/exploration trade-off for active learning in fraud detection.
ARIMA model detects credit card fraud in unbalanced datasets.
problem Unsupervised credit card fraud detection in unbalanced datasets.
method ARIMA model applied to customer spending patterns for anomaly detection.
result ARIMA model outperforms benchmark anomaly detection methods.
Semi-supervised GANs with log-signatures improve credit card fraud detection.
problem Detecting fraud in large, complex financial transaction data streams.
method Conditional GANs with Bayesian inference and log-signatures for robust feature encoding.
result Consistent improvements over benchmarks in global and domain-specific metrics.
This paper summarizes AI methods for detecting credit card fraud.
problem Detecting credit card fraud from millions of transactions.
method Rule-based and AI approaches, addressing imbalanced datasets, real-time scenarios, and feature engineering.
result Summarizes state-of-the-art AI methods for fraud detection.
CaT-GNN improves credit card fraud detection by integrating causal reasoning into GNNs.
problem Credit card fraud detection overlooks causal structure of transactions.
method CaT-GNN combines causal invariant learning and temporal graph neural networks.
result CaT-GNN outperforms existing methods on various datasets.
Paper quantifies dataset shift for credit card fraud detection.
problem Change in purchase behavior over time affects fraud detection accuracy.
method Measures day-to-day dataset shift using classification efficiency and clustering.
result Improves credit card fraud detection by incorporating dataset shift knowledge.
We present a model of credit card profitability, assuming that the card-holder always pays the full outstanding balance. The motivation for the model is to calculate an optimal credit limit, which requires an expression for the expected outstanding balance. We derive its Laplace transform, assuming that purchases are m…
A hybrid ML model detects fraudulent transactions with high accuracy.
problem Detecting and preventing fraudulent credit card transactions.
method Intelligent combination of multiple algorithms with Grid search and IHT-LR.
result Achieves impressive accuracy rates of 99.66% for ENS model.
DeepTrax learns embeddings for financial transactions graphs.
problem Large and sparse bipartite graphs of financial transactions are hard to analyze.
method Graph representation learning to embed account and merchant entities into vectors.
result Effective embeddings for account and merchant entities, validated by link prediction metrics.
Proposes a system to explain black box classifier outputs.
problem Providing understandable explanations for complex models.
method Extends Turner's (2015) MES to explain positive predictions in credit card fraud detection.
result Able to explain single predictions from black box classifiers.
Adaptive Stress Testing detects financial fraud by simulating potential failures.
problem Detecting and mitigating vulnerabilities in financial systems.
method Developed a simplified model using historical data and reinforcement learning.
result Identified the most likely path to system failure and improved fraud detection.
Study examines fraud detection methods for credit cards with limited data.
problem Data imbalance in credit card fraud detection.
method Assesses different sampling methods and machine learning algorithms.
result Monte Carlo analysis shows random undersampling outperforms SMOTE in fraud cost reduction.
BreachRadar detects points-of-compromise in bank transactions to prevent fraud.
problem Detecting and preventing bank transaction fraud caused by data breaches.
method A distributed alternating algorithm that assigns probabilities to different locations being compromised.
result BreachRadar achieves over 90% precision and recall in detecting compromised cards.
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.
A new method uses persistent homology to assess auto-encoders' latent manifold quality.
problem Chaos in auto-encoders' latent manifold and failure of current distance measures.
method Persistent Homology for Wasserstein Auto-Encoders (PHom-WAE).
result PHom-WAE improves auto-encoders' performance in credit card transaction data.
Study improves fraud detection in e-commerce with a stacked model combining CNNs, GNNs, and confidence gating.
problem Detecting credit card fraud in online transactions.
method Stacking approach with attention and confidence-driven layers, using DOWA and IOWA operators.
result The method achieves high accuracy and robust generalization in CCF detection.
Study optimizes classifiers for credit card mail campaigns and default prediction.
problem Optimizing classifiers for credit card mail campaigns and default prediction.
method Three distinct models: response, risk, and response-risk. Optimized various performance metrics.
result Random Forest classifier achieves highest accuracy (83.2%) in multi-class response-risk model.
Cluster analysis of credit card accounts helps assess risk levels.
problem Assessing risk levels for credit accounts.
method Parametric modelling of account behavior, behavioral cluster analysis with a new dissimilarity measure.
result Interesting clusters and superior prediction of account default.
Expert system predicts credit card charge-offs using macroeconomic indicators.
problem Managing charge-off rates in the credit card industry.
method Developed an expert system using machine learning and macroeconomic indicators.
result Achieved mean squared error values of 1.15E-03 and 1.04E-03.
Bayesian Neural Networks improve credit card default prediction and provide feature importance.
problem Lack of interpretability and uncertainty measures in neural network models for credit risk.
method Developed and compared BNNs trained by Gaussian approximation and Hybrid Monte Carlo.
result BNNs with Automatic Relevance Determination outperform normal BNNs in credit card default prediction.
Simple tabular event prediction model outperforms existing methods.
problem Predicting events from tabular data with historic events.
method Standard autoregressive LLM-style transformers with elementary positional embeddings and causal language modeling.
result Simple model outperforms existing approaches across various datasets and use-cases.
Study evaluates AD methods for fraud detection in online credit card payments.
problem Fraud detection in online credit card payments using anomaly detection methods.
method Assessed several recent anomaly detection methods and compared them with standard supervised learning methods.
result LightGBM outperforms other methods but is more sensitive to distribution shifts.
The paper proposes a method to detect credit card fraud using sparse Gaussian approximations.
problem Detecting credit card fraud in financial institutions.
method Sparse Gaussian classification method with pseudo or inducing inputs and different kernels and inducing points.
result The RBF kernel with a higher number of inducing points achieved the best accuracy.
Paper proposes a DAE algorithm to improve credit card fraud detection.
problem Imbalanced data classification problem in credit card fraud detection.
method Proposes a denoising autoencoder neural network (DAE) algorithm to oversample and denoise minority class samples.
result Improves classification accuracy of minority class samples in imbalanced datasets.
This paper builds a machine learning model to predict credit defaults for unsecured lending.
problem High credit defaults and delinquency rates in unsecured lending due to imbalanced data.
method Employing machine learning techniques, particularly SMOTE for imbalanced data, and evaluating models like LGBM Classifier.
result LGBM Classifier model outperforms other models in predicting credit defaults.
Deep learning improves credit risk assessment without new data.
problem Improving credit risk assessment in banking without new data.
method Sequential deep learning using temporal convolutional networks.
result Sequential deep learning outperformed tree-based models in credit risk assessment.
NetDP predicts loan defaults using network data, addressing cold-start issues.
problem Cold-start problem in default prediction for new users.
method Combines unsupervised and supervised network representations, using parameter-server for scalability.
result Effectiveness in cold-start problem, especially for new users.
UNMIX identifies hidden buyers in darknet markets by clustering anonymized IDs.
problem Identifying hidden buyers in darknet markets where IDs are anonymized.
method UNMIX, a hidden buyer identification model using Dirichlet Hawkes Process.
result UNMIX successfully groups transactions from one hidden buyer into one cluster.
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.
Enhances credit card limit adjustments by considering treatment uncertainty and prediction criteria.
problem Optimal treatment selection under multitreatment scenarios.
method Proposes a comprehensive methodology incorporating conditional value-at-risk and prediction criterion for continuous outcomes.
result Significantly improved policy performance in credit card limit adjustments.
Stablecoins offer efficient settlement but externalize costs and risks.
problem Comparing stablecoins to card networks in retail payments.
method Unified analytical framework (CLEAR) across five dimensions.
result Stablecoins are advantageous in closed-loop and high-friction contexts but structurally disadvantaged as open-loop instruments.
The paper assesses fairness in AI for financial services, using statistical methods.
problem Unintentional bias and insufficient model validation in AI applications.
method Statistical methods for imbalanced data treatment and bias mitigation.
result Fairness evaluation metrics applied to a credit card default payment example.
Approach detects outliers in large datasets for credit card fraud.
problem Lack of patterns and changing fraudulent patterns make fraud detection difficult.
method Ensemble of clustering methods to assign consistency scores to data points.
result Area under precision-recall curve is a better evaluation metric for outlier detection.
DAMVI algorithm improves imbalanced binary classification by adjusting weights of examples and classifiers.
problem Imbalanced binary classification tasks where minority class is underrepresented.
method DAMVI algorithm increases positive example weights and optimizes classifier weights using PAC-Bayesian C-Bound.
result DAMVI outperforms state-of-the-art models on various imbalanced datasets.
Credit networks represent a way of modeling trust between entities in a network. Nodes in the network print their own currency and trust each other for a certain amount of each other's currency. This allows the network to serve as a decentralized payment infrastructure---arbitrary payments can be routed through the net…
An adversarial detector identifies anomalous sequences in sequential data.
problem Detecting anomalous sequences in one-class settings with limited data.
method Solves a minimax problem to find an optimal detector against the worst-case sequences from a generator, using marked point process model.
result Demonstrated good performance on simulations and real credit card fraud datasets.
Study predicts customer data sharing in Open Banking and explains key factors.
problem Predicting and explaining customer data sharing in Open Banking environments.
method Hybrid data balancing strategy with ADASYN and NEARMISS, XGBoost models, SHAP, CART.
result 91.39% accuracy for inflow and 91.53% for outflow predictions, revealing influential features.
IA-BMA adapts model weights to inputs for better predictions.
problem Predicting with multiple models in heterogeneous settings.
method Input adaptive Bayesian Model Averaging (IA-BMA) with an input adaptive prior and amortized variational inference.
result IA-BMA consistently delivers more accurate and better-calibrated predictions.
Boosting algorithm improved by DRO framework for financial prediction.
problem Improving boosting algorithms for robust financial prediction.
method Proposes DRO-Boosting algorithm to solve DRO formulation.
result DRO-Boosting algorithm recovers AdaBoost and performs well on financial data.
The study reveals fundamental limits of fraud detection in card payment networks.
problem Fraud detection in card payment networks is challenging due to structural information impairments.
method Formalized card authorization as a sequential decision problem with delayed feedback, derived minimax regret lower bound.
result Improving issuer reporting quality or reducing censorship can yield larger reductions in the regret floor than increasing model complexity.
EmDT generates synthetic fraud data to improve detection accuracy.
problem Imbalanced datasets in fraud detection lead to poor performance on rare fraudulent transactions.
method EmDT uses UMAP clustering to identify fraudulent patterns and a Transformer denoising network to generate synthetic data.
result EmDT significantly improves classification performance compared to existing methods.
Paper tackles transparency and auditability of machine learning in credit scoring.
problem Missed potential in using modern machine learning for credit scoring due to lack of transparency.
method Develops a framework for making black box machine learning models transparent, auditable, and explainable.
result Comparable interpretability can be achieved with machine learning while maintaining predictive power.
This paper uses graph neural networks to predict SME default risk using transaction and ownership networks.
problem Predicting credit risk for SMEs facing limited financial histories and collateral constraints.
method Graph Neural Networks applied to multilayer network data of SME transactions and ownership.
result Combining network data with traditional data improves credit scoring and models contagion risk.