HejuruUbuyobozi bukurikira
Icyerekezo cy'ibikoresho ku Mikoreshereze y'Ubwenge bw'Ikoranabuhanga
Tekiniki
Ubuyobozi bwa tekiniki
Kubogama kwamateka bibaho mugihe imiterere yamakuru yashize yerekana ubusumbane bwimiterere cyangwa ivangura ryashize, kandi icyitegererezo cyiga kubyara.
Umva iki gitaboAI-byavuzwe · ~3 min
Irashobora gukomeza nubwo amakuru yakusanyirijwe hamwe akapimwa neza, kuko inzira yamateka ubwayo ntiyari ingana. Icyitegererezo rero gishobora gukoresha imiterere ishaje murwego runini mugihe igaragara nkintego.
Historical bias is a source of harm that arises before or during model development because the data encode inequities that already exist. Suresh and Guttag’s machine-learning lifecycle framework distinguishes this from representation bias, measurement choices, aggregation, learning, evaluation, and deployment harms. A dataset can represent its source population accurately and still preserve unfair social structures. More data from the same process may make the pattern more statistically stable without making it fair. The mechanism depends on the target and data-generating process. If a hiring system predicts prior hiring decisions, it may treat past choices as a definition of merit. If a credit model uses variables shaped by segregation or exclusion, those variables can carry historical differences into future decisions even when race is omitted. In health care, Obermeyer and colleagues found that a widely used population-health algorithm used health-care cost as a proxy for need; because less money had historically been spent on Black patients with comparable illness, the score understated their need. The result was a target-design problem tied to structural differences, not simply an incorrectly measured feature. Historical bias differs from a data-coverage problem: adding more records of the same decisions may not address a discriminatory target. It also differs from label bias caused by annotator judgments, although both can be present together. Teams should ask what outcome the model is trained to predict, who had access to the opportunity in the past, and which institutional choices produced the labels. Mitigation starts by questioning the target and decision process. Use outcomes closer to the intended goal, examine whether historic labels are suitable, test subgroup impacts, and consider whether the institution should change the process rather than automate it. A fairness metric alone cannot decide what outcome is legitimate. Document the historical context, affected groups, and remaining uncertainty before deployment.
A résumé model trained on past hiring records learns to rank candidates from women’s colleges lower because the company hired few of them historically.
Icyitegererezo cyinguzanyo gikoresha amateka yabaturanyi yashizweho no kugabanya kandi igaha amagambo mabi kubasabye kuva mu turere twavuzwe mbere.
Icyitegererezo cyo kuzamurwa mu ntera kimenya ko abakozi b'igihe gito batazamuwe mu ntera kandi bagasubiramo ubwo buryo batabanje gusuzuma niba ibyemezo by'amateka byari byiza.
Sisitemu yumutekano rusange yatojwe kubyabaye irashobora kwibeshya uburyo bwo kubahiriza gukwirakwiza imyitwarire mibi.
Historical patterns change slowly and can re-enter models through refreshed labels, vendors, or workflow feedback. Reassess targets and outcomes after policy changes, not only after retraining. Keep an auditable account of the data-generating process and provide affected people a route to challenge decisions. Monitoring can reveal drift but cannot determine by itself whether a historical outcome is fair. Recheck subgroup effects when labels or policies change. Keep an appeal process so affected people can surface recurring errors. Review appeals for repeated patterns.
Ibaruwa y'amakuru y'ubuntu
Inkuru eshatu zizewe za AI buri gitondo cy'iminsi y'akazi, zanditse mu rurimi rworoshye. Ubuntu iteka ryose, nta kwamamaza.
Imeri imwe buri munsi y'akazi. Kwiyimura mu buryo bumwe. Ntitwigera tugurisha cyangwa ngo dusangire aderesi yawe.
Isuzume
Ibisubizo ako kanya kuri buri kibazo, n'icyemezo gishobora gusangirwa gifite ID yagenzurwa umaze gutsinda isomo.
Fasha uburezi bwa AI bw'ubuntu. AI Understanding ni umuryango utegamiye kuri leta wa 501(c)(3) — nta kwamamaza, nta kwishyura, iteka ryose. Tanga impano
Historical bias occurs when patterns in past data reflect structural inequities or past discrimination, and a model learns to reproduce them. It can persist even when data are collected and measured accurately, because the historical process itself was unequal. A model can therefore automate old patterns at greater scale while appearing objective.
The model reproduces inequity already present in the historical decision process.
More observations can stabilize patterns produced by an unequal process without correcting that process.
The study found cost as a proxy for need led to lower scores for Black patients who were sicker at comparable risk scores.
Historical bias analysis examines the outcomes and institutional choices that generated labels.
A dataset can cover its source population yet still encode inequitable past outcomes.
Komeza wige
Abandi bayobozi batoranijwe kuriyi ngingo
HejuruUbuyobozi bukurikira
Icyerekezo cy'ibikoresho ku Mikoreshereze y'Ubwenge bw'Ikoranabuhanga
Tekiniki