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.

168,694 papers · 148 categories

Trend · papers per month

1122 · Sep 202019922001200920172026
15 results for delinquency

Logit-link models reveal socio-temporal effects on microfinance delinquency.

problem Understanding and quantifying socio-temporal factors affecting microfinance loan delinquency.
method Developed and evaluated discrete-time logit-link models with fixed-effects and frailty extensions.
result Simple random intercept structures capture latent heterogeneity in microfinance repayment behavior.

Proposes a new model to analyze mortgage delinquency transitions.

problem Analyzing mortgage delinquency transitions in a flexible yet identifiable way.
method Combines structured additive predictor with neural network for complex interactions, orthogonalising components for identifiability.
result The semi-structured model provides modest gains in discrimination compared to a structured model, especially in the early prediction spans.

The paper reduces estimation error in predicting borrower repayment by accounting for lender's credit decisions.

problem Estimation error in predicting borrower repayment due to confounding effects.
method Proposes new estimators to reduce estimation error, combining theoretical analysis and numerical testing.
result The proposed estimators are unbiased, consistent, and robust, showing substantial reduction in estimation error.

In this paper we introduce a generalized extension of the Eisenberg-Noe model of financial contagion to allow for time dynamics of the interbank liabilities, including a dynamic examination of default risk. This framework separates the cash account and long-term capital account to more accurately model the health of a …

2018-01-06abs ↗pdf ↗

Study develops and improves risk models using machine learning methods.

problem Classifying business delinquency using machine learning.
method Exploring several machine learning methods including regularization, hyper-parameter optimization, and model ensembling.
result Bagging on KNN with K=9 is the optimal model for risk classification.

We present a novel subset scan method to detect if a probabilistic binary classifier has statistically significant bias -- over or under predicting the risk -- for some subgroup, and identify the characteristics of this subgroup. This form of model checking and goodness-of-fit test provides a way to interpretably detec…

2016-11-24abs ↗pdf ↗

We develop a deep learning model of multi-period mortgage risk and use it to analyze an unprecedented dataset of origination and monthly performance records for over 120 million mortgages originated across the US between 1995 and 2014. Our estimators of term structures of conditional probabilities of prepayment, forecl…

2016-07-08abs ↗pdf ↗

Study uses AI to refine loan assessments, improving credit default predictions.

problem Improving credit default prediction accuracy using AI-refined text.
method Comparative analysis of human-written and AI-refined loan assessments using deep learning techniques.
result AI-refined texts significantly enhance credit default predictions, especially when combined with structured data.

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.

We redefine SICR-events for better loan classification under IFRS 9.

problem Ambiguity in SICR-event definition under IFRS 9.
method Proposed alternative framework with three parameters: delinquency, stickiness, and outcome period. Varying these parameters, we generated 27 unique SICR-definitions and fitted logistic regression models.
result The proposed SICR-models outperform the PD-comparison approach as an early-warning system for credit losses.

Model predicts cannabis use disorder risk for adolescents and young adults.

problem Predicting cannabis use disorder progression in adolescents and young adults.
method Bayesian machine learning model trained on longitudinal data.
result Model provides personalized risk assessment with AUC of 0.68-0.75 and E/O ratio of 0.95-1.