1. Data infrastructure
Quantitative research begins with trustworthy data. We ingest and normalise tick-level order-book data, trade prints, on-chain flows, derivatives positioning, funding rates, basis, and ancillary reference data across a curated universe of deeply liquid spot pairs on regulated and tier-one venues. All data are stored in a time-series warehouse with strict point-in-time discipline: every research backtest and every production decision sees only the information that was available at the corresponding historical moment.
We monitor data quality continuously. Gaps, outliers and venue outages are tagged, not silently imputed. Our research code treats missing data as first-class information rather than a nuisance to be papered over.
2. Signal generation
Our signal library spans three families:
- Factor models — cross-sectional and time-series factors rooted in market microstructure, carry, momentum, value, and liquidity. Each factor is specified ex ante with a clear economic thesis before any empirical test is run.
- Statistical learning — non-parametric and tree-based models constructed with leakage-free feature engineering, nested cross-validation, and explicit regularisation to control for the well-known pitfalls of machine learning in noisy, non-stationary markets.
- Microstructural signals — order-flow imbalance, queue dynamics, cross-venue dislocation and derivatives-spot basis, used primarily for execution timing and short-horizon alpha.
3. Validation discipline
A signal that looks good in-sample is not a signal. We impose:
- Out-of-sample segregation. A reserved period — never touched during development — is used as the final arbiter before any signal enters production.
- Combinatorial purged cross-validation. We adapt the Lopez de Prado methodology to address the serial correlation and overlapping-label issues that make naïve k-fold validation dangerously optimistic in financial data.
- Capacity stress tests. Each strategy is evaluated under realistic slippage, participation-rate limits, and latency models. A paper Sharpe that collapses under 5 bps of slippage is discarded.
- Regime analysis. Performance is decomposed across volatility regimes, funding environments and correlation structures. We expect honest attribution, not a single number.
4. Portfolio construction
Signals are translated into target positions through a portfolio optimisation layer that balances expected return, realised and forecast covariance, turnover, capacity, and hard risk limits. We prefer simple, explainable optimisers over opaque ones: every position we take must be attributable to an identifiable combination of signal, constraint, and risk bound.
5. Execution
Execution is an alpha centre, not a cost centre. Our in-house smart order router prioritises maker liquidity, adapts to venue conditions, and preserves information by avoiding predictable trading patterns. Live execution is instrumented with its own KPIs — arrival-slippage, participation rate, venue fill quality — which are fed back into signal design so that our alphas remain implementable at target capacity.
6. Risk & governance
Risk is a pre-trade discipline, not a post-mortem exercise. Every strategy runs inside explicit VaR, stress, concentration and venue-exposure limits. A dedicated monitoring layer acts on breaches automatically; a second, human layer reviews every breach and every regime transition the following business day.
Operational risk is treated with the same seriousness as market risk. Venue due diligence, wallet segregation, key ceremony, incident rehearsal and counterparty-exit playbooks are written, tested and periodically updated. DFI Labs moved off FTX in early 2022; the event reinforced a culture of proactive rather than reactive governance.
7. Research culture
Finally, methodology is only as good as the culture that sustains it. We run weekly research reviews, maintain a peer-critique requirement before any signal promotion, and track a living postmortem of decisions that did not work as expected — because improvement requires naming what broke. Small team, flat organisation, written thinking.
Want the detail behind the method?
We are happy to walk professional and institutional investors through our research process under appropriate confidentiality. Conversations are best had on a call.