LuceThemis
Audits signal quality in quantitative research.
Examines evidence across costs, out-of-sample survival and confounders.
- For
- Quant research and risk teams
- Engine
- Rust · Python
- Source code
- Closed · shown during a pilot
- Buying
- Written, fixed-price pilot
What is LuceThemis?
LuceThemis is a closed-source tool that audits the quality of evidence behind a quantitative research signal. It tests the signal under fees, slippage and turnover, out of sample and against confounders, and classifies the result into one of six verdicts instead of 'profitable / not profitable'. It does not sell signals or promise returns.
A signal that looks great in hindsight, put to the test.
Representative signal and figures. LuceThemis does not sell trading signals; it only decides whether a signal deserves trust.
How it works
From the product's own documentation. Each number says where and on which version it was measured.
Signal and market state
A candidate signal arrives with the observed market state and is schema-validated.
Causal effect
The effect is estimated with a cross-fitted estimator residualized on market state.
Robustness tests
Walk-forward, purged K-fold, CPCV. Deflated Sharpe and probability of backtest overfitting (PBO).
An explicit verdict
KEEP, WATCH, REJECT_OVERFIT, REJECT_NO_CAUSAL_EFFECT, REJECT_TOO_COMPLEX, NEEDS_MORE_DATA.
- 6 verdicts
- Classifies the quality of evidence instead of 'profitable / not profitable'.
- Cost pressure
- Does the signal survive fees, slippage and turnover?
- MDL penalty
- A signal too complex for the size of its effect is rejected.
- Closed source
- The Rust scoring core and Python research worker are shown during a pilot.
Stack
- Rust (Axum)
- Python
- Pandera
- Next.js
What it does not claim
It does not sell signals, forecast markets or promise returns. It only decides whether a signal deserves trust.
Current boundary
It does not sell trading signals or promise returns.
What a pilot covers
A sample starting scope. Final deliverables and acceptance criteria are fixed in the written proposal.
- Question
- Does a research signal survive costs and stress?
- Likely input
- Signal results, cost assumptions and test periods
- Deliverables
- Out of sample robustness review
- Cost and confounder report
- Evidence brief for research decisions
Before you decide
Can I buy this product today?
A paid pilot and setup proposal can be prepared. Scope, data access, deliverables, timeline and a fixed price are agreed in writing after a discovery call.
Why is there no price?
Data volume, integration and success criteria differ from job to job. After the call you get a fixed-price written proposal; no paid work starts without your approval.
Do I need to upload live data here?
No. This site has no file upload or accounts. Data access, retention and permissions are set only in the pilot agreement.
What is the first step?
Choose LuceThemis in the form and describe the problem you need to solve. The data and pilot boundaries are then set together.
More in this discipline
- Vinctum AegisPython · XGBoost · SHAP
From churn risk to an economically grounded retention decision.
- Calybris CoreRust · Python
Decision infrastructure with replayable proof.
- Churn Report KitPython · XGBoost
Churn analysis with an actionable retention queue.