AI Self-Learning Models for NBFC Collections: How the Technology Works
TL;DR A propensity model deployed on a personal loan portfolio in January was trained on 18 months of historical payment data. At deployment, its scores were accurate. Recovery rates improved through the first quarter. By August, the picture has changed. Payment rates in the mid-propensity band have dropped. The model continues to route accounts to […]
Champion-Challenger Testing for SA Banks and Credit Providers
TL;DR A collections model has been running at a South African bank for ten months. It was built on 24 months of payment data, the bulk of it pre-pandemic. It performed well in the first two quarters after deployment. Recovery rates in the 30-60 DPD bucket improved. Cost per recovery came down. In the last […]
Champion-Challenger Testing in AI Collections: A Practical Guide for US Banks
TL;DR A collections manager at a mid-size regional bank has been running the same contact strategy for three years. Recovery rates on early bucket accounts have drifted down four percentage points over that period. The strategy still looks reasonable in the monthly report. The segmentation logic has not changed. The contact sequences are the same […]
RBI Model Validation Requirements for AI Collections: A Practical NBFC Guide
A bridge designed by the same team that built it, inspected by the same firm that constructed it, and opened to traffic on the builder’s own assurance of quality is a structural liability. The work might be excellent. The materials might be sound. But without an independent party verifying both, there is no objective basis […]
The End of the “Black Box”: Why Explainable AI is a Must-Have for Financial Services
Artificial intelligence is no longer a futuristic concept; it is an integral part of the financial services industry, powering everything from fraud detection to loan approvals. While the efficiency and speed of AI are undeniable, the complex, opaque nature of many AI models, often referred to as the “black box”, has created significant challenges. For […]
Why Model Risk Management Matters
Artificial intelligence has moved from experimentation to boardroom priority in a remarkably short time. Most large enterprises now run multiple AI initiatives — fraud detection systems, predictive analytics platforms, generative AI copilots, and customer intelligence tools. Yet one pattern has become increasingly clear to me over the past decade. Many organizations can build AI models. […]
Basel III Model Validation for South African Banks: Meeting Prudential Authority Standards for AI Credit Risk and Collections Models
TL;DR On 24 November 2025, the Prudential Authority of the South African Reserve Bank and the Financial Sector Conduct Authority jointly published a report on artificial intelligence in South Africa’s financial sector. The report drew on analysis conducted throughout 2024 and set out, for the first time in a formal joint publication, the regulators’ view […]
Model Governance for AI Collections in South Africa: Meeting FSCA Validation Standards and Basel III Requirements
TL;DR The KPMG South Africa Ten Key Regulatory Challenges for 2025 places AI model validation and continuous monitoring at the centre of the financial services governance agenda, identifying these as the most critical technical requirements that South African banks must address for AI systems: rigorous testing and validation before deployment, continuous monitoring after deployment, and […]
Model Risk Management for AI Collections: The Framework US Banks Are Missing
TL;DR Your bank almost certainly has a model risk management program. Your model risk management program was almost certainly built around credit scoring models. Those two facts together describe the compliance gap that is showing up in AI model examinations across US banking in 2025 and 2026. The model risk those collections AI systems carry […]
Building a Propensity Model for Collections: How US Banks Predict Payment Behaviour Before Default
TL;DR Once an account transitions to default, the probability of curing it drops to 7%. That single figure, drawn from research on consumer credit default transitions, is the entire business case for propensity modelling in collections. The probability of a current account transitioning to default sits at 23%. The probability of recovering an account that […]
