Data & research8 min read
Intermediate
Research hygiene
Look-ahead bias and data snooping
The fastest way to improve a backtest is often to accidentally use information that would not have been known at the time.
Read articleBack to knowledge
Topic / Machine learning
Machine learning
Features, labels, leakage, validation, and realistic uses of ML in trading.
6 guides
Explore this topic.
Data & research8 min read
Intermediate
Machine learning
Machine learning for trading: a realistic starting point
ML can help with classification, ranking, or regime description, but it does not remove the need for clean data and honest validation.
Read articleData & research8 min read
Advanced
Machine learning
Feature engineering without leakage
Create useful features from trading data while keeping the future out of the input and the live pipeline reproducible.
Read articleData & research8 min read
Advanced
Machine learning
Walk-forward validation for machine-learning models
Use rolling training and validation windows to test whether an ML pipeline adapts without learning from the future.
Read articleStrategy7 min read
Advanced
Machine learning
Classification vs. regression in trading
Choose a model target that maps clearly to a decision, and measure whether it improves the trade process after costs.
Read articleData & research6 min read
Intermediate
Machine learning
When not to use machine learning
Sometimes a clear rule, better data, or better execution solves the problem more reliably than a model.
Read articleDiscuss machine learning
Ask a setup question, share a backtest, or compare notes with other algorithmic traders. Use a display name; your email remains private.
Create an account or sign in above to join the conversation.
Loading discussion…