Strategy8 min read
Core guide
Research basics
How to read a backtest without fooling yourself
Profit factor and win rate are useful clues, not a verdict. Learn which parts of a report deserve your attention.
Read articleBack to knowledge
Topic / Data & backtesting
Data & backtesting
Data quality, testing design, walk-forward analysis, and stress tests.
14 guides
Explore this topic.
Strategy8 min read
Core guide
Research process
How to develop an algorithmic trading strategy
A repeatable research process turns a trading idea into a testable hypothesis instead of a collection of indicators.
Read articleStrategy7 min read
Core guide
Validation
Walk-forward analysis explained
Learn how rolling in-sample and out-of-sample windows reveal whether an algorithm survives beyond the period that shaped it.
Read articleStrategy7 min read
Core guide
Strategy families
Trend following vs. mean reversion
These two strategy families respond to different market behaviours. Understanding the difference helps you choose honest tests and expectations.
Read articleStrategy7 min read
Beginner
Research basics
How to define a trading hypothesis
Turn a vague market belief into a precise, falsifiable question that an algorithmic research process can test.
Read articleData & research7 min read
Intermediate
Performance analysis
Expectancy and the distribution of returns
Learn why the average trade, dispersion, streaks, and tail outcomes matter more than a single headline percentage.
Read articleStrategy8 min read
Advanced
Strategy research
Regime awareness without overfitting
Use market conditions to understand where a system works without building a fragile switch that only recognises the past.
Read articleData & research7 min read
Beginner
Data engineering
The data-quality checklist for trading research
Bad timestamps, duplicated bars, missing sessions, and inconsistent symbols can create an edge that exists only in the dataset.
Read articleData & research7 min read
Intermediate
Data engineering
Bars, ticks, and choosing data resolution
Match the data resolution to the strategy's decisions so the backtest does not invent precision the live system cannot use.
Read articleData & 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 articleData & research7 min read
Intermediate
Validation
How to design an honest out-of-sample test
Freeze the rules, protect the holdout, and evaluate the strategy in a way that resembles how it will face the future.
Read articleData & research8 min read
Intermediate
Robustness
Monte Carlo stress testing for trading systems
Use resampled trade sequences and perturbed costs to explore how much of a backtest depends on a favourable path.
Read articleEngineering8 min read
Intermediate
Python & tooling
Build reproducible backtests with Python
A reproducible backtest gives the same answer from the same inputs and makes disagreements easier to diagnose.
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 articleDiscuss data & backtesting
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…