Data & signals
- Prepare datasets and document their limitations.
- Explore features, signals and testable hypotheses.
Quantitative research & strategy optimization
Test the idea
Test the idea
Understand the evidence
Evaluate a new strategy or challenge an existing one with reproducible research, realistic backtests and clear findings.
Agreed scope · Reproducible work · Documented handover
What we deliver
Research you can inspect and build on.
A focused study, an independent review or an extension of your existing research process.
Backtesting & validation
- Evaluate out-of-sample results with agreed trading costs.
- Check parameter sensitivity, leakage and robustness.
Portfolio & findings
- Compare sizing, allocation and portfolio constraints.
- Receive research code, results and a concise decision report.
Methods, datasets and acceptance checks are agreed upfront. Data licences and ongoing research are scoped separately.
How it works
From a clear question to a useful answer.
Define
Agree the research question, available data and success criteria.
Test
Run reproducible experiments and challenge the assumptions behind the results.
Explain
Review the findings, limitations and next steps. Hand over code and documentation.
Selected work
Relevant projects.
Order-Book Foundation Model for Slippage & Fill-Probability Prediction
Marsbridge delivered a model-driven execution-support system that predicts limit-order fill likelihood and short-horizon slippage from order-book...
Read case study →
Long-Horizon Futures Portfolio Optimization & Risk Management
Marsbridge audited and re-engineered a long-horizon futures portfolio framework, removing sources of data leakage, rebuilding tests on adjusted...
Read case study →
Start a conversation
What do you want to test?
Share your hypothesis, instruments and available data. We’ll reply within one business day.
We’ll confirm fit, then propose a scope, timeline and cost.