Enter your profile
Example data table
| Profile | GPA | GRE Q | GRE V | Research (mo) | Pubs | Projects | Work (yr) | Fit | Target | Estimated |
|---|---|---|---|---|---|---|---|---|---|---|
| Profile A | 3.8 | 167 | 158 | 12 | 1 | 2 | 1 | 4 | Moderate | 84.1% |
| Profile B | 3.4 | 160 | 152 | 6 | 0 | 3 | 2 | 3 | Strong | 58.1% |
| Profile C | 3.1 | 155 | 148 | 0 | 0 | 4 | 2 | 2 | Safety | 71.7% |
Examples are illustrative and use the default model weights.
Formula used
The calculator uses a weighted logistic model. Each input is normalized to a 0–1 range, then centered by subtracting 0.5. Selectivity sets the baseline intercept.
For example: GPAnorm = GPA / 4, GREQnorm = (GREQ − 130) / 40, Researchnorm = min(months, 24) / 24.
score = b0 + Σ wi(xi,norm − 0.5) − 0.35(1 − completeness)
probability = 1 / (1 + e−score)
Missing fields are treated as neutral (0.5) and reduce completeness.
How to use this calculator
- Enter your metrics and strength ratings as honestly as possible.
- Select your target program selectivity level.
- Optionally open “Advanced” to tune weights for your context.
- Press “Estimate Probability” to view results above the form.
- Use the driver list to prioritize your next improvements.
To compare options, adjust one variable at a time and re-submit. Use exports to keep track of scenarios across different programs.
What the model estimates
This calculator estimates the probability of admission using a weighted logistic model that turns your profile into a single score. Academic metrics, research exposure, fit, and communication are normalized to comparable 0–1 ranges, then centered around an average applicant. The model applies a selectivity baseline so the same profile yields different outcomes for elite, strong, moderate, and safety programs. Missing fields are treated as neutral but reduce confidence for practical planning purposes.
Inputs that move outcomes most
GPA and quantitative preparedness typically carry the largest effect because they correlate with first‑year rigor. Research months, publications, and shipped projects strengthen evidence of sustained work. Portfolio strength captures reproducibility, documentation quality, and measurable impact. Program fit influences outcomes by aligning goals with faculty, labs, and curriculum. Recommendations and statements matter most when they provide concrete examples, leadership, and intellectual independence, not generic praise. Treat ratings as calibrated estimates, not optimism carefully.
Interpreting scenarios by selectivity
Scenario results show how the same applicant performs under different competitiveness assumptions. Elite programs impose a lower baseline, so probabilities compress and improvement priorities become sharper. Strong programs are selective but provide more headroom for portfolio and fit advantages. Moderate programs are balanced and reward completeness of evidence across academics and projects. Safety programs still value clarity, but baseline odds increase. Use scenarios to shortlist realistic targets while keeping ambitious options strategically.
Improvement planning with sensitivity
The key‑driver panel ranks positive and negative contributors so you can plan interventions with high leverage. If your largest negatives are math foundation or ML readiness, invest in graded coursework, rigorous projects, and documented evaluation. If fit is weak, refine your research interests and map them to labs before writing. If the profile is incomplete, add standardized scores or portfolio artifacts. Re‑submit after one change to see sensitivity and avoid confounding effects.
Exporting results for application tracking
Exports turn a single estimate into a decision tool. Download CSV to compare multiple programs, deadlines, and profile versions in a spreadsheet. Download PDF to attach a snapshot to your planning notes or mentorship review. Save scenarios for each target selectivity and track how improvements shift probabilities over weeks. Use the example table as a benchmark for realistic inputs. The goal is consistency: measurable progress, documented evidence, and aligned applications over time.
FAQs
Is this probability an official decision?
No. It is a statistical estimate based on the inputs you provide and typical admissions signals. Use it for planning and prioritization, not as a guarantee of acceptance or rejection.
What if I do not have test scores?
Leave the fields blank. The model treats missing values as neutral and reduces completeness, which slightly lowers the estimate. Consider adding alternative evidence, such as graded coursework, certifications, or strong project evaluations.
How should I rate portfolio strength?
Rate based on reproducibility, documentation, measurable results, and clarity. A strong portfolio includes clean repositories, experiments, metrics, and a short write‑up explaining decisions, tradeoffs, and lessons learned.
Can I customize weights safely?
Yes. Use the advanced weights when you understand what your target programs emphasize. Change one weight at a time, re‑submit, and compare scenarios. Avoid extreme settings; they can overstate one factor and hide weaknesses.
Why does completeness change my score?
Completeness reflects how much evidence you provided. With many blanks, the estimate becomes less reliable, so the model applies a conservative adjustment. Filling key fields improves both accuracy and the clarity of driver insights.
How do I track multiple programs?
Run the calculator per program tier, download CSV, and store each row with the program name and deadline. Use the PDF export for a snapshot you can share with mentors or keep in your planning notes.