Quantitative thinking. Simplified.
Data-driven observations, charts and quantitative analysis.
Featured insight
5 Sep 2026From data to signal: building robust models.
An overview of a quantitative research process: data, feature engineering, modelling and validation.
Read the full insightIllustrative articleMarket data
- Price
- Volume
- Open interest
- Technical indicators
- Derived features
Feature engineering
Changes, not levels · scaled for the regime · no future informationModel
Regularised regression · sequence modelsSignal
Judged out of sample, rolling forwardData & statistics
Fat tails
Simulated: 3,000 daily returns with fat tails, scaled to 1% daily volatility. Not market data.
- Simulated returns
- Normal, same volatility
View data table
| Daily return | Simulated | Normal |
|---|---|---|
| −4.0% to −3.5% | 0.3% | 0.0% |
| −3.5% to −3.0% | 0.4% | 0.1% |
| −3.0% to −2.5% | 0.6% | 0.5% |
| −2.5% to −2.0% | 1.2% | 1.7% |
| −2.0% to −1.5% | 2.7% | 4.4% |
| −1.5% to −1.0% | 7.0% | 9.2% |
| −1.0% to −0.5% | 14.9% | 15.0% |
| −0.5% to 0.0% | 24.1% | 19.1% |
| 0.0% to +0.5% | 23.1% | 19.1% |
| +0.5% to +1.0% | 14.0% | 15.0% |
| +1.0% to +1.5% | 6.6% | 9.2% |
| +1.5% to +2.0% | 2.3% | 4.4% |
| +2.0% to +2.5% | 1.7% | 1.7% |
| +2.5% to +3.0% | 0.5% | 0.5% |
| +3.0% to +3.5% | 0.2% | 0.1% |
| +3.5% to +4.0% | 0.2% | 0.0% |
Diversification and correlation
Volatility of an equal-weight portfolio, as a share of one strategy's, for three average correlations. Computed from the formula, not results.
- Correlation 0
- Correlation 0.2
- Correlation 0.5
View data table
| Strategies | Correlation 0 | Correlation 0.2 | Correlation 0.5 |
|---|---|---|---|
| 1 | 100% | 100% | 100% |
| 2 | 71% | 77% | 87% |
| 3 | 58% | 68% | 82% |
| 4 | 50% | 63% | 79% |
| 5 | 45% | 60% | 77% |
| 6 | 41% | 58% | 76% |
| 7 | 38% | 56% | 76% |
| 8 | 35% | 55% | 75% |
| 9 | 33% | 54% | 75% |
| 10 | 32% | 53% | 74% |
What a real signal looks like
Simulated: 260 observations of a signal with a true correlation of 0.12 to the next-period return. Not market data.
- Observations
- Fitted line
View data table
| Measure | Value |
|---|---|
| Observations | 260 |
| True correlation | 0.12 |
| Sample correlation | 0.13 |
| Variation explained | 1.8% |
| Fitted slope | 0.14 |
Models & methods
Regression models
Regularised regression and careful feature selection.
Sequence models
Models for ordered data, from functional-link networks to recurrent models.
Model validation
Out-of-sample testing, rolling forward through time.
Feature engineering
Transformations that survive outside the sample they were found in.
Quantitative library
View allFeature engineering for financial time series.
Building features from price, volume, open interest and derived indicators that survive outside the sample they were found in.
Read moreIllustrative articleUnderstanding correlation and diversification.
Why the correlation between strategies matters as much as the quality of each one.
Read moreIllustrative articleMean reversion in financial markets.
Statistical foundations, testing frameworks and the practical considerations behind relative-value strategies.
Read moreIllustrative articleMathematics. Data. Markets.
A systematic approach to opportunity.
We use quantitative methods to find structure in market data, and build strategies that can be tested and repeated.