PIN Approximation
Approx. PIN flow-toxicity estimator.
What it measures
An approximation of the probability of informed trading (PIN). The classical PIN requires maximum-likelihood estimation of a structural sequential-trade model; Easley, López de Prado & O'Hara (2012) showed it can be approximated directly from order-flow imbalance relative to total volume. This signal serves that flow-based approximation: an estimation-free read on how likely the current flow is to be information-driven rather than noise, computable at market speed.
References: Easley-LdP-O’Hara 2012.
Point-in-time, leak-free
Like every QUANT_API feature, flow.pin_approx is computed point-in-time: each value uses only data that had actually arrived at the timestamp you query — live or historical. No restatements, no backfills that quietly rewrite the past, no look-ahead. The value your backtest sees at a given stamp is the value the live API would have returned at that stamp. How we enforce this is documented on the methodology page.
Windows & transforms
The signal is computed over rolling windows; each window can be served raw or through a transform (z-score, percentile rank, delta…). Which windows and transforms you can query depends on your plan — the signal itself supports:
Plan & access
flow.pin_approx unlocks on the Signal plan ($99/mo) and every plan above it. Every new account starts with a 14-day free trial of the Signal plan — no card required.
Example call
Resolve the latest value for BTC (5m window, delta transform — both available on the Signal plan):
curl -G https://api.quant-api.dev/v1/features/live \
-H "Authorization: Bearer fk_live_<your_key>" \
--data-urlencode "asset=BTC" \
--data-urlencode "features=flow.pin_approx@5m:delta"Same key works on /v1/features/historical for point-in-time backtesting — see the API docs.