766 deep dives in 24 categories · last updated
15 matching deep dives
Research Lab: these deep dives are AI working drafts unless tagged Reviewed research. Read how review works.
Credit-scoring technologies, decision engines, underwriting data, financial-model tools and methods for evaluating predictions and lending decisions.
Borrowers can improve after taking a loan without the loan causing the improvement. Credit-builder loans, randomized second looks and medical-debt relief show how a study’s treatment, comparison group and take-up define what its results can establish.
Affirm reported more completed purchases after adding transformer-derived credit information to its underwriting. The result concerns a defined experiment; repayment, explanations and the economics of those extra purchases remain separate parts of the evidence.
Fannie Mae’s validation service can reduce paperwork and defined loan-sale exposure. Its latest employment-verification update shows why the evidence, closing date and scope of contractual relief still matter.
Conformal prediction adds calibrated ranges to model forecasts. A worked cash-flow example shows how those ranges are built, why average coverage can conceal weak subgroups, and why changing conditions and delayed outcomes limit the promise.
Two groups can have identical error rates and different approval rates. A worked example separates calibration, mistaken rejection and selection, and shows why statistical equality cannot decide a legal or ethical question.
VantageScore 4.0 is available for eligible Enterprise loans and Fannie Mae has aligned pricing with Classic FICO. FICO 10T remains a future delivery option. Model choice, report coverage and the meaning of a cutoff are separate parts of the transition.
Cash Atlas turns permissioned account data into reports and attributes; NovaScore adds a proprietary risk score. Customer announcements show where those tools are being applied, while seasonal income and connection costs explain the limits of a richer data feed.
Provenir combines data, rules, models and AI-assisted workflows across the customer relationship. Its broad product claims become meaningful only when the task, customer experience and economic comparison are kept distinct.
SAS links model deployment with records of ownership, validation and permitted use. The distinction matters when a technically successful release delivers the wrong version, stale data or an answer that arrives too late.
Taktile combines rules, data, case work and AI agents. Its financial-spreading benchmark shows one kind of measured result; completed applications, consequential errors and time released tell different parts of the story.
Agricultural loans and Brazilian payroll lending show how FICO Platform connects information, models and lending rules. Faster processing is a different result from safer loans or cash savings.
Plaid turns permissioned bank-account activity into reports, income estimates and credit-risk scores. Its newer tools change access and modelling, while leaving the lender responsible for the final answer.
Stratyfy helps lenders turn historical data and staff judgement into lending rules. A community-lender programme offers concrete examples, with important limits on what its reported gains prove.
Zest AI builds machine-learning underwriting for lenders. Idaho Central and First Hawaiian show how automation can change an application, while reported decision rates leave repayment and funding questions open.
PowerCurve turns data, predictive models and a lender’s policies into decisions and customer workflows. Its separate products, real deployments and place within Experian’s Ascend Platform explain what the software does, and what its performance claims cannot establish.
Page 1 of 1 · 1–15 of 15 articles