· Services ·
What Illuma actually does.
Manage your saved list like a sheet: swap schools, set ED, edit fit notes, jump into supplements.
What it does
College list
Input your profile. An ML model trained on top-30 admit data produces a tiered list, with counselor playbooks layered on for impacted majors, ED/EA strategy, and school-specific risk.
Output includes
- Tier assignment using top-30 ML prediction
- Per-school fit + risk notes
- ED / EA strategy recommendation
- Autofill admit %, SAT policy, and supplements
Under the hood
ML models + calibration layers, not a ChatGPT wrapper.
Tier labels and admit probabilities are computed in Python before the language model runs, using a trained regression and each school's CDS bands. The numbers are calibrated.
1
Admit-probability regression (per school, per round)
Trained on top-30 cycle outcomes, returns RD, ED, and EA probabilities calibrated to CDS.
2
Profile-score rubric
Initiative, EC impact, and spike domain scored 0 to 100, fed back into the regression.
3
Mechanical tier assignment
Reach, Match, and Safety derived from ML probability plus the school's 25th and 75th percentile bands.
4
Counselor-curated archetype guidance
Pool-pattern guidance matched by archetype and injected as context, not improvised.
5
ED-leverage scoring
Ratio of ED to RD probability flags ED candidates above 2x and ED-redundant below 1.5x.
Ready to try it?
First eval free. No credit card required to sign up.