Articles

Metrics to Monitor in Lending and Credit Underwriting

Speed and conversion metrics shape how well a lender performs in underwriting. If you do not track the right ones, you can miss friction in the application flow, delay funding, and lose good customers before they reach a decision. This article explains four core underwriting metrics, how they differ, and why improving them gives lenders a real competitive edge.

Typical Underwriting Policy in Consumer Lending and Buy Now, Pay Later

Underwriting policy in consumer lending and BNPL looks tidy on paper, but in practice it is built from losses, fraud cases, regulatory pressure, and collections outcomes. This article breaks down the core components: age and eligibility gates, identity and blacklist checks, credit risk and affordability logic, and how those parts become operational decision logic.

The Typical Org Chart of a Consumer Lending Company

This article maps the typical org chart of a consumer lending company. It explains who owns sales, product and marketing, underwriting, collections, risk, operations, and IT. You will see how these teams apply decision logic across acquisition, servicing, and compliance.

Tracing Models and Decisions

Protect Your Lending App with Device Fingerprinting, App Behavioral Data, and Face Recognition

Prevent identity and synthetic fraud in consumer lending

Identity fraud in consumer lending puts pressure on risk management from several angles. It increases PR exposure, fraud losses, and credit risk. It also damages customer trust and adds operational workload.

Risk-Based Pricing: Why Lenders Do It and How the Rate Is Built

One rate can lose your strongest applicants to a competitor that prices by risk, and you are left with the customers it priced higher or turned down. Set each customer’s rate from the funding, risk, acquisition, and other costs that customer brings to your book.

Face recognition and comparison for onboarding

Deep learning has made face recognition central to remote identity verification. This article explains how online face comparison fits into onboarding, which photo types are involved such as user uploads, selfies, and liveness captures, which matching sources are used such as government identity services or ID photos, and where common validation checks reach their limits, including error level analysis, EXIF metadata inspection, and saved-quality heuristics.

MaxMind minFraud Insights checks and risk scores

minFraud Insights returns the checks behind its fraud score, including details about the IP, email, addresses, card, phone and device. In live calls, an anonymous cloud IP and a billing address thousands of kilometres from the IP both scored below MaxMind's example accept line while the checks flagged them.

MaxMind minFraud Score and changing risk scores

minFraud Score returns an overall transaction risk score and a separate IP risk score. The readings reflect the history of the addresses, emails, and IPs in the order, including your own test traffic, so set thresholds against your own orders.