Tanishk Yadav
Resume

Projects / PinSight

Options engine

PinSight: 0DTE Options Engine and No-Lookahead Paper Trader

Tanishk Yadav, New York University

Code on GitHub

Infers the risk-neutral density of SPY same-day options and runs a scheduled live paper-trading loop, built as the reference implementation of a no-lookahead architecture.

Key facts

3 runs a day
scheduled at 09:35, 12:30 and 16:10 ET, plus a continuous poll
20 tests
including a future-data injection test
4 layers
every read is stamped with the moment it became knowable

How it works

  • Risk-neutral densities from SPY option chains (Breeden-Litzenberger with SVI smoothing), model-free moments, and contract pricing against the density.
  • Every decision is a pure function of state and an as-of timestamp; a test appends future snapshots and proves past decisions do not change.
  • Market price and model probability are separate quantities throughout: Kelly sizing needs an explicit probability estimate and never falls back to the quoted price.
  • A structured event log records every fit, signal and trade, and a read-only dashboard shows the live state.

Built with

Python, yfinance option chains, pandas, Parquet, pytest, macOS launchd

What it does not show

  • No trading performance is claimed. The paper record was reset after model-error and stale-quote fixes, and it is not a track record.

Tanishk Yadav

MS Financial Engineering at New York University, graduating May 2027, and looking for full-time quantitative research roles. My master's thesis measures, in real time, when US debt dynamics turn self-reinforcing.

See all my workThe thesisResume

Related

Related work

Working paperJuly 2026

VolEdge: The Variance Risk Premium

A full-stack platform that extracts risk-neutral moments from live option chains without a pricing model; a GARCH vol-targeted sleeve beat SPY on risk (Sharpe 0.85 vs 0.68) while naive short-variance harvesting lost money.

Read the paperPDF
Prediction markets

DriftEdge

Sizes Polymarket and Kalshi binary contracts with Kelly on an empirical-Bayes win probability whose prior is a zero-edge bet, so no evidence means no position. Deterministic replay audits every strategy change; 64 tests with CI.

See the project