What we do

Turning fragmented, multi-source price data into a single reliable signal.

Most markets don't have one price — they have many, one per venue, each updating on its own clock. That fragmentation hides useful structure: which venue is setting the price, which is lagging, and where the gap between them is real rather than an artifact. We make that structure measurable.

Multi-source ingestion

We pull time-stamped prices for the same asset from many venues and normalize them into one clean, comparable series.

Movement & divergence detection

We reconstruct the full price path, measure which venue leads and which lags, and surface where prices dislocate.

Signal, not noise

Every candidate move is checked against liquidity, reversion and cross-source consensus, so artifacts are filtered out before anything is called a signal.

Validation against outcomes

Each read is measured against what the market did next. A method that isn't measured against outcomes is a hunch; ours is measured.

Where it applies

One method, many markets.

Case study

Crypto — cross-exchange price discovery

Reconstructing how BTC and ETH move across exchanges — separating the structural stablecoin basis from genuine, short-lived dislocations.

Read the analysis →

Research direction

Retail & e-commerce price intelligence

The same cross-source method applied to competitive price monitoring: which seller moves first, who lags, and where a product is mispriced across sources.

Methodology

Financial time-series

Execution-quality thinking — implementation shortfall and slippage — applied to multi-venue price data. Methodology and research only.

Case study = built and shown. Research direction = an honest extension, not yet delivered work. Methodology = capability we apply, kept at research level.