KM Kanav Mehta Quantitative Researcher

Agentic Research · Systems

An alpha engine that AI agents can run end-to-end.

Every capability is an MCP tool, so any capable agent can run the full research loop on US equities using only public data.

Back to Projects GitHub ↗

Thesis

Desk tools as agent tools

The agentic platform I build at QuantLink AI needs a proving ground: a complete research stack where an AI agent can propose a strategy, backtest it, optimize it, read the attribution, and iterate, with no human glue step in between.

  • Public data only, so the full loop is reproducible by anyone: no vendor feeds, no keys required for the core path.
  • Spec-driven datasets keep the pipeline honest: YAML specs declare identity, schema, constraints, and lineage once, and drive DDL, dbt tests, and the catalog.

Build

Pipeline architecture

StageWhat it does
Ingestyfinance primary with Stooq fallback; S&P 500 constituents from Wikipedia.
Transformdbt owns all raw → staging → mart SQL with generated tests.
FactorsKen French (3/5F, momentum, reversals), Treasury CMT, AQR (QMJ/BAB), and the JKP 153-factor library.
BacktestCross-sectional and weighted backtests in vectorbt; event-driven runs in backtesting.py.
OptimizeMVO and HRP via PyPortfolioOpt, skfolio strategies, equal-weight benchmarks.