QuantLab, part 3 of 6
Models.
Model families and when to use them, linear against trees, hyperparameters, forecasting.
5 articles, about 38 minutes in order. Foundational first, then applied, then advanced.
- 01
Classification, regression, clustering, dimensionality reduction, anomaly detection
The five model families a research workspace actually needs, and which question each one answers in a financial dataset.
- 02
Choosing between linear and tree-based models
Why a Ridge regression and a Random Forest can see the same data completely differently, and how to decide which one belongs in a given research question.
- 03
Why more models is not better
The arithmetic of multiple testing: why trying more estimators, more features and more thresholds makes the best result look better and mean less.
- 04
Hyperparameters that actually matter
Which knobs on the workspace's model families genuinely change generalisation, and how a grid search separates a real improvement from a lucky fold.
- 05
Forecasting versus prediction: what you can and can't claim
Why a one-step-ahead forecast has to beat tomorrow-equals-today before it means anything, and how the skill score makes that comparison honest.
Other parts of QuantLab
- 01FoundationsWhat quantitative research is, the loop it runs in, and how a result fools you.
- 02Data and featuresPreparing financial time series, building features without leakage, choosing a benchmark.
- 04ValidationChronological splits, purging and embargoing, walk-forward folds, the naive baseline, overfitting.
- 05Portfolio and riskOptimisation from first principles, risk metrics that matter, stress testing, explainability.
- 06PracticeReproducibility, checkable reports, re-runnable workflows, presenting work, teaching a term.
Read it here, then run it in the workspace.
Every article links to the platform page that implements the idea. Beta access is free and opens by cohort.