Predictive Analytics
Dr Bhatia MDS Predictor
A data-driven predictor using historical admission data to forecast MDS counselling outcomes.
Overview
Problem
MDS aspirants going through counselling had no reliable, data-backed way to estimate admission chances at a given rank and category.
Solution
A predictor that models historical counselling round data — rank, category, and college outcomes — into a data-backed estimate of likely placement.
Architecture
Client
Next.js form for rank/category input and results visualization.
API
Prediction endpoint querying historical outcome data via Prisma.
Data
MongoDB storing structured historical counselling round outcomes.
Feature Breakdown
- Rank and category-based prediction of likely counselling outcomes
- Predictions grounded in historical outcomes, not a black-box model
- Clear results view for a non-technical audience under time pressure
Implementation Detail
async function predictOutcome(rank: number, category: Category) {
const comparable = await prisma.counsellingRound.findMany({
where: { category, rank: { gte: rank - 500, lte: rank + 500 } },
});
return summarizeOutcomes(comparable);
}Challenge & Solution
Predictions needed to be trustworthy and explainable for a real admission decision, using historical data that was inconsistent across sources.
Grounded predictions in comparable historical outcomes rather than an opaque model, and normalized rank/category/outcome fields into one schema via Prisma at ingestion.
Results
- Aspirants get an estimate traceable to real comparable outcomes, not forum guesswork.
- Previously inconsistent data across sources is now normalized into one usable schema.