Apply supervised and unsupervised machine learning to financial datasets using feature engineering, purged cross-validation and disciplined, leakage-aware evaluation.
Duration7 weeks
LevelIntermediate
Modules7
Lessons28
This course covers the full machine learning workflow for financial data, from feature construction and labeling through model selection, validation and interpretation. You will work with tree ensembles, regularized linear models and clustering, and learn validation techniques designed for overlapping, time-ordered observations. Throughout, the focus is on building research pipelines whose results can be reproduced and stress-tested rather than on headline metrics.
7 modules · 28 lessons · 7 weeks. Curriculum preview; the final syllabus may change before enrollment opens.
Build a feature store of technical and fundamental features with point-in-time joins
Compare regularized regression, random forest and gradient boosting models under purged cross-validation
Produce a model interpretability report that explains feature contributions and their stability over time
Quantzivo certificates are completion credentials issued by Quantzivo, not accredited qualifications. Courses teach technical and research skills; they do not promise investment returns or provide investment advice.
8 weeks8 modulesBuild and evaluate deep learning models for financial time series in PyTorch, from recurrent networks to temporal convolutions and transformers, with rigorous validation.
7 weeks7 modulesApply rigorous validation methods to trading strategies: walk-forward and cross-validation, overfitting diagnostics, multiple testing control and robust parameter optimization.
8 weeks8 modulesResearch, construct and evaluate factor models using cross-sectional regressions, portfolio sorts and risk attribution, with careful handling of biases and multiple testing.
Reserve your place in a few steps, or ask us anything about the curriculum, schedule and format first.
