Proceedings ArticleDOI
Credit limit management using action-effect models
Shubhamoy Dey
- pp 112-115
TLDR
In this article, a new type of model (termed action-effect model) is proposed to study the effect of credit limit increase/decision making on the profitability of the portfolio.Abstract:
Management (i.e. initial allocation and subsequent increase / decrease) of credit limits is one of the most critical decisions related to credit card accounts. It affects a number of variables that have direct or indirect influence on the profitability of the portfolio. This paper proposes the use of a new type of model (termed action-effect model) to study the effect of credit limit increase / decrease actions. Complex interactions between conflicting variables like credit risk, probability of attrition, credit limit utilization and revenue generated are studied. The possibility of using simulation along with action-effect models to arrive at an ‘optimum’ credit limit for each credit card account in a portfolio is discussed.read more
Citations
More filters
Journal ArticleDOI
Using reinforcement learning to optimize the acceptance threshold of a credit scoring model
TL;DR: A dynamic reinforcement learning system that constantly adapts the threshold in response to live data feedback in order to maximize a company’s profits is developed.
Posted Content
Intelligent Credit Limit Management in Consumer Loans Based on Causal Inference.
TL;DR: A data-driven approach to manage the credit limit intelligently by incorporating the diminishing marginal effect and a well-designed metric is proposed to properly measure the performances of compared methods.
Journal ArticleDOI
Modeling the Combined Effects of Credit Limit Management and Pricing Actions on Profitability of Credit Card Operations
TL;DR: In this paper, the combined effects of credit limit management, and pricing actions on profitability using asystem of empirical behavioral models for the individual factors are investigated. But the authors focus on the combined effect of credit risk, probability of attrition, propensity to revolve, credit limit utilization and revenue generated.
Dissertation
Optimizing acceptance threshold in credit scoring using reinforcement learning
TL;DR: This document summarizes current capabilities, research and operational priorities, and plans for further studies that were established at the 2015 USGS workshop on quantitative hazard assessments of earthquake-triggered landsliding and liquefaction in the Central American region.
References
More filters
Journal ArticleDOI
Economic Benefit of Powerful Credit Scoring
TL;DR: In this paper, the authors study the economic benefits of using credit scoring models and derive the profit-maximizing cuttoff regime and pricing curve of a credit scoring model.
Journal ArticleDOI
Does reject inference really improve the performance of application scoring models
Jonathan Crook,John Banasik +1 more
TL;DR: This paper uses a rare sample that includes those who would normally be rejected to examine the extent to which the exclusion of rejected applicants undermines the predictive performance of a scorecard based only on accepted applicants.
Journal ArticleDOI
Economic Benefit of Powerful Credit Scoring
TL;DR: In this paper, the authors study the economic benefits of using credit scoring models and derive the profit-maximizing cutoff and pricing curve for a stylized loan market model with banks differing in the quality of their credit scoring model.
Journal ArticleDOI
Credit scoring for profitability objectives
TL;DR: The results show models of continuous financial behaviour to outperform classification approaches and demonstrate that scoring functions developed to specifically optimize profit contribution, using genetic algorithms, outperform scoring functions derived from optimizing more general functions such as sum of squared error.
Journal ArticleDOI
Quantile regression for modelling distributions of profit and loss
Mark Somers,Joe Whittaker +1 more
TL;DR: In this paper, quantile regression is used to estimate the distribution of property values realised on repossession that is then used to calculate loss given default estimates, where the low tail of the house value is much more relevant for estimating likely losses than estimates of the average value where in most cases no loss is realised.