Let's Build a Quant Trading Strategy: Part 2 - Strategy Development

MemLabs · Beginner ·📐 ML Fundamentals ·9mo ago

About this lesson

*Let's Build a Quant Trading Strategy: Part 2 - Strategy Development* In this video, we take the machine learning model from Part 1 and develop a strategy based on the model's predictions. We tackle *3 critical decisions* for our strategy: 1. *Entry/Exit Signals* – How do we know when to enter and exit a trade? 2. *Trade Sizing* – What's the optimal trade size? 3. *Leverage* – Should we amplify returns, and if so, how much? You'll see how combining a *statistical edge* with *compounding trade sizing* and *leverage* can generate *exceptional returns* – even with a low win rate. *NEW HERE?* This video stands alone, but Part 1 covers the ML model we use here: https://youtu.be/iWSDY8_5N3U *WANT DEEPER CONCEPTS?* Check out *"Introduction to Quantitative Trading"* for foundational knowledge on machine learning, Sharpe ratio, market making, taker/maker strategies, expected value, and more: https://youtu.be/mkzcntzznMc *FOLLOW ALONG WITH CODE* Full code available at: https://github.com/memlabs-research/build-a-quant-trading-strategy 💬 Join our Discord community: https://discord.gg/BBp9EqUNNa --- *TIMESTAMPS* 00:00 Introduction 01:40 Key Strategy Questions 03:44 Machine Learning Model Recap 20:24 Entry/Exit Signal 33:44 Trade Sizing 35:14 Constant Trade Sizing 59:23 Compounding Trade Sizing 01:17:18 Leverage 01:28:30 Modelling Liquidation *TOPICS COVERED* - Using the machine learning model's prediction to create trades - Entry and exit signal generation - Trade Sizing - Leverage mechanics *WHAT'S NEXT?* Part 3: Implementation – We implement this strategy and put it live with real money. --- ⚠️ *RISK DISCLAIMER* Leverage amplifies both gains and losses. Always understand your risk before trading real capital.

Original Description

*Let's Build a Quant Trading Strategy: Part 2 - Strategy Development* In this video, we take the machine learning model from Part 1 and develop a strategy based on the model's predictions. We tackle *3 critical decisions* for our strategy: 1. *Entry/Exit Signals* – How do we know when to enter and exit a trade? 2. *Trade Sizing* – What's the optimal trade size? 3. *Leverage* – Should we amplify returns, and if so, how much? You'll see how combining a *statistical edge* with *compounding trade sizing* and *leverage* can generate *exceptional returns* – even with a low win rate. *NEW HERE?* This video stands alone, but Part 1 covers the ML model we use here: https://youtu.be/iWSDY8_5N3U *WANT DEEPER CONCEPTS?* Check out *"Introduction to Quantitative Trading"* for foundational knowledge on machine learning, Sharpe ratio, market making, taker/maker strategies, expected value, and more: https://youtu.be/mkzcntzznMc *FOLLOW ALONG WITH CODE* Full code available at: https://github.com/memlabs-research/build-a-quant-trading-strategy 💬 Join our Discord community: https://discord.gg/BBp9EqUNNa --- *TIMESTAMPS* 00:00 Introduction 01:40 Key Strategy Questions 03:44 Machine Learning Model Recap 20:24 Entry/Exit Signal 33:44 Trade Sizing 35:14 Constant Trade Sizing 59:23 Compounding Trade Sizing 01:17:18 Leverage 01:28:30 Modelling Liquidation *TOPICS COVERED* - Using the machine learning model's prediction to create trades - Entry and exit signal generation - Trade Sizing - Leverage mechanics *WHAT'S NEXT?* Part 3: Implementation – We implement this strategy and put it live with real money. --- ⚠️ *RISK DISCLAIMER* Leverage amplifies both gains and losses. Always understand your risk before trading real capital.

Watch on YouTube ↗ (saves to browser)

Sign in to unlock AI tutor explanation · ⚡30

Related Reads

The End of XGBoost? No. The End of Three Weeks of Tuning.

Learn how Google's TabFM predicts on tabular data with zero training, potentially reducing the need for extensive XGBoost tuning

Medium · Data Science

The Day the Machine Met a Stranger

Discover how machine learning can be applied to understand new, unseen data, just like meeting a stranger for the first time.

Medium · Machine Learning

Decoding the Link Between Pretraining and Reinforcement Learning

Discover how pretraining and reinforcement learning are connected, and why this matters for AI development

Dev.to · Pneumetron

Learning the Loop — #101 | What Is Machine Learning, Really?

Understand the fundamentals of machine learning and its core concepts

Chapters (9)

Introduction

1:40 Key Strategy Questions

3:44 Machine Learning Model Recap

20:24 Entry/Exit Signal

33:44 Trade Sizing

35:14 Constant Trade Sizing

59:23 Compounding Trade Sizing

1:17:18 Leverage

1:28:30 Modelling Liquidation

SQLite3 Tutorial - Learn SQL for Python in 17 Minutes