Research Notes OnQuant & AI Trading
Practical writing from the team that builds the engine. Signal research, backtesting discipline, risk mathematics, and the operational reality of running money algorithmically.
Editor's pickWhat Is Quant Trading? A Complete Beginner's Guide
Quant trading replaces gut feeling with statistics, code, and repeatable rules. Here is how the whole machine actually works, from raw tick data to a live order.
AI & MLHow AI Models Actually Predict Market Moves
Not a crystal ball, not magic: gradient boosted trees, sequence models, and feature engineering. A practical look at what AI trading models really do.
StrategyBacktesting vs Forward Testing: Why You Need Both
A backtest tells you a strategy could have worked. A forward test tells you whether it still does. Skipping either one is how accounts die.
PsychologyThe Hidden Cost of Emotion in Trading
Fear and greed do not just feel bad — they have a measurable price tag. Quantifying the cost of hesitation, revenge trading, and premature exits.
Risk ManagementPosition Sizing: The Math That Keeps You Alive
Your edge determines whether you make money. Your sizing determines whether you survive long enough for it to matter. Here are the formulas that matter.
AutomationFrom Manual to Automated: A Practical Migration Plan
You do not flip a switch and become systematic. A staged migration that keeps you profitable while your automation earns the right to run real size.
Run These Ideas OnReal Capital
Reading research is step one. Step two is letting a disciplined engine execute it without emotion. Start a strategy or earn from referring one.