RESEARCH LAB

Interactive quant research

Run Python, change assumptions, inspect results, and learn how research becomes into a profitable trading strategy

Sign in to launch free
Python 3 · Runs in browser
research.ipynb

returns = df['close'].pct_change()

signal = model.predict(features)

p_value = test(edge).pvalue

# test, challenge, refine

EQUITY CURVE+12.8%

Choose how you learn

Buy one notebook or unlock everything

Own a focused research notebook for life, or subscribe for the complete MemLabs curriculum, every premium notebook, competitions, exercises, and new releases.

Buy individually

£50

per premium notebook

One payment with lifetime access to the notebook you choose.

Choose a notebook

MemLabs All Access

£200/month

Every notebook and course

Access the entire platform and everything released while you are subscribed.

Notebook library

Choose a research workflow

Every notebook is editable, executable, and designed around a real quantitative question.

.ipynb
Machine learning Premium

Classification vs Regression

Compare logistic classification with linear regression on crypto returns, and explore how win rate, return magnitude, and trading performance relate.

Intermediate · Python 3
.py
Strategy Deployment Premium

Conditional Mean Trading Bot

The live Hyperliquid bot behind the conditional mean strategy: how a basic statistical forecast becomes code that trades.

Intermediate · Python 3
.ipynb
Alpha Research Premium

How to Create a Mean Reversion Strategy

Build the kind of mean reversion model used at quantitative firms using basic statistics and mathematics instead of machine learning.

Beginner · Python 3
.ipynb
Alpha Research Premium

How to Find a Statistical Anomaly

An example of researching a basic statistical anomaly using high-school statistics.

Beginner · Python 3
.ipynb
Alpha Research Premium

How to Handle Regime Shifts

Explore different models that can adapt to changes in the distribution of price returns (regime changes).

Intermediate · Python 3
.ipynb
Alpha Research Premium

Improve Trading with Cross Returns

Find a predictive edge in other assets' lagged returns when an asset's own past returns have none.

Intermediate · Python 3
.ipynb
Returns decomposed into direction and magnitude: r = sign(r) × |r|.
Alpha Research Premium

Improve Trading with Decomposed Returns

Model return direction and magnitude separately, compare decomposed forecasts with direct regression, and use the predictions to set market-making quotes.

Advanced · Python 3
.ipynb
Machine learning Premium

Improve Trading with Model Stacking

Can stacking models on top of each other improve model performance?

Intermediate · Python 3
.ipynb
Machine learning Premium

Prediction Error, MAE and MSE

Understand prediction error, compare MAE and MSE, and explore how large misses affect model scores using ALGO daily return forecasts.

Beginner · Python 3
.ipynb
Machine learning Premium

Researching Calendar Effects with XGBoost

Train an XGBoost model on calendar features, validate its predictions, and test whether the apparent edge remains after fees.

Intermediate · Python 3
.ipynb
Alpha Research Premium

Trading Conditional Expectation Based on Basic Statistics

Condition the expected return on a basic statistic, without machine learning, and test whether it beats the unconditional mean benchmark.

Beginner · Python 3
.ipynb
Alpha Research Premium

Trading the Unconditional Mean

Can the average daily return of a coin be traded, or is it only a benchmark to beat?

Beginner · Python 3
.py
Strategy Deployment Premium

Unconditional Mean Trading Bot

The live Hyperliquid bot behind the unconditional mean strategy: how a research idea becomes code that trades.

Intermediate · Python 3
.ipynb
Alpha Research Free

What Is Overfitting?

Learn how an in-sample relationship can fail to generalise by comparing Bitcoin returns across training and testing periods.

Beginner · Python 3
Sign in to open
01

Open

Launch a configured Python notebook directly in your browser.

02

Experiment

Change the code, assumptions, features, and execution model.

03

Interpret

Inspect the evidence and decide whether the result is robust enough to matter.