Backtest engines

Two Backtest Engines, One Pipeline

Search and validation want opposite things: search wants throughput across a huge parameter space, validation wants full realism on a handful of survivors. We run two purpose-built engines instead of compromising on one, and combine them for anything complex enough to need both.

Vector Engine

01

Vector Engine

One parameter grid, run at once - not bar by bar.

The whole strategy is expressed as array operations and compiled kernels - there is no per-bar loop at all. Best for trend-following scenarios and any coarse parameter sweep: thousands of indicator/threshold combinations across the full history, ranked in seconds. Its job is not the final answer - it is to cut a huge search space down to a short-list of candidate configurations and the market slices (regimes, time windows) worth a detailed look.

  • Vectorized / compiled
  • No per-bar loop
  • Trend scenarios
  • Market-slice pre-filter

Faster than open-source engines

One identical parameter sweep - 150k bars, 80 indicator combinations, trade count locked to the same value - how many times faster our GPU engine runs it than each open-source engine, measured on a MacBook M2 Max.

  1. 273× faster than vectorbt
  2. 12,000× faster than backtesting.py
  3. 141,000× faster than backtrader
  4. 260,000× faster than bt

bar length: log scale

Event Engine

02

Event Engine

Bar by bar, tick by tick - every fill earns its place.

A per-bar / per-tick replay against trades and full order books, with candles, footprint (order-flow per price level) and volume profile layered in as needed. This is where a strategy meets realistic fills, slippage, margin and queue position - and where an AI or news-analysis agent gets to make one decision per candle, exactly as it would live. It is also the only engine we trust for HFT strategies, where the order book and latency are the strategy. Slower by design: that per-event cost is the price of realism, and for a short-list of survivors it is negligible.

  • Trades + order book
  • Footprint / volume profile
  • AI / news per-candle
  • HFT-ready
Two Backtest Engines, One Pipeline
AttributeVector EngineEvent Engine
PrincipleOne parameter grid, run at once - not bar by bar.Bar by bar, tick by tick - every fill earns its place.
Profile
  • Vectorized / compiled
  • No per-bar loop
  • Trend scenarios
  • Market-slice pre-filter
  • Trades + order book
  • Footprint / volume profile
  • AI / news per-candle
  • HFT-ready
Checks-
  • Full L2/L3 order book, replayed trade by trade
  • One AI or news decision per candle - hourly down to tick-level
  • Every shortlisted candidate re-checked in full detail before it can go live

Questions about the engines?

Talk to the team - we usually reply fast.

Get in touch