Same algorithm.
Different code.
The strategy is fixed. You compete on how fast your code executes it. The leaderboard ranks p50, p99, and p999 latency of a single function call, on the same dataset, on the same machine.
the typical call, when cache and branch predictor are warm
the slow 1% — where most rankings are decided
end-to-end throughput on the held-out dataset
Five steps from sign-in to leaderboard.
- 01
Get the cohort kit
Download the starter pack and the strategy spec. The strategy is fixed; you just implement it.
- 02
Implement the spec, exactly
Per-symbol rolling window of 64 mid-prices, z-score |z| ≥ 2.0 entry, |z| ≤ 0.5 exit, one unit of position per symbol. The cohort owns the algorithm. You own the speed.
- 03
Submit your build
./submit.sh strategy.sofrom your terminal, or drag and drop on the dashboard. One submission per participant per ten minutes. - 04
Correctness, then latency
Your code is replayed against a held-out 10 M tick dataset. If a single emitted order disagrees with the reference, you do not rank. If you pass, every
on_tick(...)call is timed. - 05
The leaderboard updates
p50 is 40% of the score. p99 is 40%. Throughput is 15%. Compliance is 5%. Trading P&L is identical across correct submissions, so it is never part of rank.
Currently leading
Measure, don't guess.