Algorithm Registry

Purpose

Rank students for a given role based on verified skills, projects and stage experience.

Audience: Recruiters searching for candidates. The student can read the explanation for any match concerning them.

Inputs used

• •Required skills — from Job posting
• •Preferred skills — from Job posting
• •Student verified skills — from SkillDelta graph
• •Student skills (self-declared) — from Student profile
• •Verified projects — from Project + ProfessorEndorsement
• •Stage supervisor ratings — from StageExperience
• •Graduation year — from Student profile
• •Location — from Student profile

Never used

• Gender
• Nationality
• Ethnicity
• Religion
• Age (beyond graduation-year class)
• Photo / any biometric inference
• GPA — never used: it earns no points in the score, and the minimum-GPA search parameter is accepted by the API but not applied to the query

Scoring weights

Points out of a 100-point match score. Verified skills count at full weight, self-declared ones at 0.6.

Human oversight

Matching runs without a human step in front of it. Review happens after the fact: you can contest a match from its explanation page, which opens a request with a reference and a date, and the reviewer's outcome is written back onto the stored explanation.

Your rights as a subject

• →Right to see the explanation for any match concerning you (/matches/[id]/why). A record is stored for every candidate a search scores, not only the ones the recruiter was shown — your own list shows the matches you were surfaced in, and your data export contains the rest.
• →Right to contest a match and ask for human review, from the match page or /dashboard/student/privacy/requests. You get a reference and the date we owe you an answer by; the outcome is recorded against the explanation itself.

Bias testing

None. Gender and ethnicity are not fields in our schema, so no parity test across them is possible. We do hold nationality and date of birth as optional CV fields, and university, degree and graduation year — parity across those could be tested on data we already have, and is not.

Purpose

Estimate a student's probability of securing a job offer within 6 months post-graduation.

Audience: The student and their university career service. No recruiter surface shows the number: the badge left the candidate page and the decision-pack header on 2026-09-02, and the same day the two doors that had been missed were closed — the compare view, where it was relabelled "fit score" and used to rank candidates against each other, and the portfolio Trust Score, which carried it as a tenth of its weight (defaulting to 30 out of 100 for the majority of students, who have no prediction at all). /api/predictions is now readable by the student themselves, their career service and admins only; the RECRUITER role is refused. It still appears in the decision-pack PDF, where it is labelled "Fit signal" and carries the note that the weights are hand-set, never fitted to data, and not a probability of being hired. The underlying factors still render to recruiters; the headline percentage does not.

Inputs used

• •Hireability score — from SkillPathRecommendation
• •Verified project ratio — from Project.verificationStatus
• •AI project analysis (innovation, complexity, market relevance) — from Project
• •High-priority skill gaps (lowers the estimate) — from SkillPathRecommendation
• •Verified professor endorsements — from ProfessorEndorsement
• •Discipline market demand — from Project.discipline, scored against a hand-set constant per discipline — not derived from live job postings
• •Prior confirmed placements — from Placement

Never used

• Gender
• Nationality
• Ethnicity
• Religion
• Family background
• Socio-economic data
• GPA

Scoring weights

Share of the estimated probability, in percentage points. The base rate applies before any signal; skill gaps subtract rather than add; the placement bonus is flat once a student has at least one confirmed placement and does not scale with the count. A student with no skill-path record, or one whose record lists no gaps, is scored at half gap severity; a student with no projects is scored at a mid-range discipline demand. Both are defaults applied when the data is missing, not measurements.

Human oversight

The prediction is advisory and is not by itself a decision. It is no longer reachable by a recruiter at all — not as a badge, a fit score, a trust-score component or an API response — so the oversight question is now confined to the student and the career service reading their own figure, and to the labelled "Fit signal" in the decision-pack PDF.

Your rights as a subject

• →Right to view your own prediction and the signals behind it
• →Right to contest it and ask for human review, from /dashboard/student/privacy/requests

Bias testing

None.