[Library](https://stochastly.com/library)

# Machine learning in finance

Where machine learning helps on financial data, where it overfits, and the protocols that tell the two apart.

## What this shelf covers

Machine learning meets two obstacles on market data: a low signal-to-noise ratio and labels that overlap in time. These notes cover the protocols built for both, purged and embargoed cross-validation, sample weights by label uniqueness, the triple-barrier method and meta-labeling, along with probability calibration for position sizing and the evidence on when large models help. Each note states what the method controls and which leak remains open.

## 9 notes

[A Backtesting Protocol for the Machine Learning Era](https://stochastly.com/library/machine-learning/a-backtesting-protocol-in-the-era-of-machine-learning)

[Can Machines Learn Finance? The Sober Answer](https://stochastly.com/library/machine-learning/can-machines-learn-finance)

[Conformal Prediction: Intervals With a Guarantee and No Distributional Assumption](https://stochastly.com/library/machine-learning/conformal-prediction-intervals-without-assumptions)

[Deep Learning on the Order Book, and Why It Does Not Apply Here](https://stochastly.com/library/machine-learning/deep-learning-on-the-order-book)

[Machine Learning in Finance: Which Textbook Answers Which Question](https://stochastly.com/library/machine-learning/machine-learning-in-finance-textbooks)

[The Virtue of Complexity Debate: More Parameters Than Observations](https://stochastly.com/library/machine-learning/the-virtue-of-complexity-debate)

[Two Cultures, and No Free Lunch](https://stochastly.com/library/machine-learning/two-cultures-and-no-free-lunch)

[Variable Importance Is Biased, and Permutation Extrapolates](https://stochastly.com/library/machine-learning/variable-importance-is-biased-and-extrapolates)

[When Cross-Validation Is Valid on Time Series, and When It Is Not](https://stochastly.com/library/machine-learning/when-cross-validation-is-valid-on-time-series)

---
Source: https://stochastly.com/library/machine-learning
