Tender document analyser

The brief

Contractors read long tender documents to find the dates, values and penalties that matter. Build a pipeline that classifies tenders by type and extracts key dates, estimated value, security deposit and penalty clauses into structured data. Good looks like: accuracy per field on labelled tenders, clause extraction with page references, and a summary sheet per tender.

What you will build

1. Collect public tender documents
2. Classify tenders by type of work
3. Extract dates, values and penalty clauses with an LLM
4. Validate and measure accuracy per field
5. Produce a one-page summary per tender

Free, open data to build it with

• eProcurement (CPPP) ↗ Government of India

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.