MétaCan
Menu
Back to cohort
Record W4226354324 · doi:10.3390/jrfm15040165

Time to Assess Bias in Machine Learning Models for Credit Decisions

2022· article· en· W4226354324 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueJournal of risk and financial management · 2022
Typearticle
Languageen
FieldComputer Science
TopicLaw, AI, and Intellectual Property
Canadian institutionsnot available
Fundersnot available
KeywordsUnderwritingLoanAnalyticsCompliance (psychology)Actuarial scienceCredit scoreComputer scienceFinanceBusinessArtificial intelligenceData sciencePsychology

Abstract

fetched live from OpenAlex

Focus on fair lending has become more intensified recently as bank and non-bank lenders apply artificial-intelligence (AI)-based credit determination approaches. The data analytics technique behind AI and machine learning (ML) has proven to be powerful in many application areas. However, ML can be less transparent and explainable than traditional regression models, which may raise unique questions about its compliance with fair lending laws. ML may also reduce potential for discrimination, by reducing discretionary and judgmental decisions. As financial institutions continue to explore ML applications in loan underwriting and pricing, the fair lending assessments typically led by compliance and legal functions will likely continue to evolve. In this paper, the author discusses unique considerations around ML in the existing fair lending risk assessment practice for underwriting and pricing models and proposes consideration of additional evaluations to be added in the present practice.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.922
Threshold uncertainty score0.262

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.068
GPT teacher head0.257
Teacher spread0.189 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it