MétaCan
Menu
Back to cohort
Record W4402130453 · doi:10.1080/0960085x.2024.2395531

Reducing the incidence of biased algorithmic decisions through feature importance transparency: an empirical study

2024· article· en· W4402130453 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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueEuropean Journal of Information Systems · 2024
Typearticle
Languageen
FieldComputer Science
TopicExplainable Artificial Intelligence (XAI)
Canadian institutionsUniversity of WindsorMcMaster UniversityUniversity of Waterloo
FundersSocial Sciences and Humanities Research Council of Canada
KeywordsTransparency (behavior)Computer scienceStrategic information systemEmpirical researchFeature (linguistics)Data scienceInformation systemManagement information systemsComputer securityStatisticsMathematicsEngineering

Abstract

fetched live from OpenAlex

As firms move towards data-driven decision-making using algorithmic systems, concerns are raised regarding the lack of transparency of these systems which could have ramifications related to users’ trust and the potential for provoking discriminatory decisions. Although previous research has developed methods to improve algorithmic transparency, little empirical evidence exists regarding the extent of the effectiveness of these approaches. Drawing upon Rest’s theory of ethical decision-making and the literature on algorithmic transparency and bias, we investigate the effectiveness of feature importance (FI), a common transparency-enhancing approach, which illustrates the nature and the weights of the features utilised by an algorithm. Through an online experiment employing a fictitious tool that provided recommendations for selecting employees for a promotion-related training programme, we find that FI is effective when biased recommendations include direct discrimination (i.e. when individuals are treated less favourably on protected grounds such as gender); but is of little assistance when discrimination is indirect (i.e. when a criterion or practice that is apparently neutral, disadvantages a group of individuals who are of a protected class). Additionally, we propose a new transparency approach, using aggregated demographic information, to accompany FI in indirect discrimination circumstances and report the results of testing its effects.

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)0.005
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: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.797
Threshold uncertainty score0.677

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.006
Open science0.0020.000
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 head0.065
GPT teacher head0.332
Teacher spread0.267 · 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