MemLabs

Courses

Beginner

Quantitative Trading Fundamentals

Build the complete foundation for quantitative trading. No programming experience or trading knowledge required. You will learn Python, mathematics, statistics, data analysis, time series, trading fundamentals, and risk management through practical exercises. A central theme of the course is mathematical modelling: markets cannot be represented with 100% real-world accuracy, so quants build simplified versions of market dynamics where models are approximating. You will learn what to predict, understand what a model can and cannot tell you, and use mathematics to turn trading ideas into testable predictions.

9 modules 251 exercises
What you'll learn
  • Python programming
  • Core mathematics and statistics with applications to quant trading.
  • Financial data analysis with Pandas and NumPy
  • Time Series concepts
  • Key trading and risk management metrics
What you'll do
  • Conduct quantitative research.
  • Develop a basic mathematical model to forecast.
  • Perform statistical validation of your mathematical model.
  • Develop a basic automated trading strategy based on your model.
  • Develop a backtest of your strategy.

What you'll cover

  1. 1
    Python Free
    Learn Python with real-world trading exercises so you learn algo trading and Python at the same time.
  2. Mathematics Plus
    Build a deep mathematical foundation: covering core operators, the laws governing calculations, and the intuition to develop basic models.
  3. Statistics Plus
    Learn practical statistics for analysing returns, measuring uncertainty, comparing strategies, and deciding whether observed performance is likely to be signal or noise.
  4. Probability Plus
    Learn the probability concepts behind uncertainty, expected value, distributions, and risk. This module builds the bridge from deterministic maths to statistical reasoning.
  5. Data Analysis Plus
    Learn to load, manipulate, analyse, and export financial data using Pandas, the core tool of every quant researcher.
  6. Time Series Plus
    Understand the structure, behaviour, and properties of financial time series before modelling or trading them.
  7. Mathematical Modelling Plus
    Build mathematical models that turn market state into testable forecasts and trading signals.
  8. Quantitative Research Plus
    Learn how to do empirical research to find statistical edges.
  9. Strategy Plus
    Learn how to turn a statistical edge into a strategy that can execute that edge in the market.

Challenges

1
Build a Profitable Trading Strategy: Easy
Using low-noise time series data from a real asset, build a mathematical model that identifies a signal and turns it into a trading strategy that generates consistent profit over the test period. The asset is anonymised so that no one can look up the answer or reverse-engineer the signal from market history. This introductory challenge helps you apply the fundamentals in a realistic market setting where the signal is easier to identify.
Strategy must be net profitable over the full out-of-sample period.
2
Build a Profitable Trading Strategy: Hard
Using high-noise time series data from a real asset, build a mathematical model that separates a weak signal from the surrounding noise and turns it into a profitable trading strategy. The asset is anonymised so that no one can look up the answer or reverse-engineer the signal from market history. The noise-to-signal ratio is significantly higher than the introductory challenge, so your model will need to be more precise to survive the out-of-sample period.
Strategy must be net profitable over the full out-of-sample period.
Intermediate Coming Soon

Machine Learning Trading Strategies

Learn machine learning to make future predictions and how to use those predictions to make trading strategies.

Prerequisites: Quantitative Trading Fundamentals
4 modules 0 exercises
Coming Soon
What you'll learn
  • Machine Learning fundamentals
  • Teach a machine learning model to learn patterns from market data
  • Create a statistical edge with machine learning
What you'll do
  • Train several machine learning to find several patterns in the market data
  • Develop best practises to avoid data leakage and overfitting.
  • Create a strategy around a ML model's prediction.

What you'll cover

  1. Machine Learning Fundamentals Plus
    Learn the fundamental concepts of machine learning so you can understand how it works under the hood when you train models.
  2. Regression Plus
    Learn how to predict real-valued numbers - such as prices, price deltas, returns and log returns
  3. Clasification Plus
    Learn how to predict labels and what the labels should be
  4. Testing Plus
    Learn how to test a machine learning without any data leakage or overfitting

Challenges

1
Regression Strategy: Maximise Returns
Using anonymous real market data, build a regression-based trading strategy. Your goal is to generate the highest possible total return.
Strategy must be net profitable. Ranked against other submissions by total return.
2
Classification Strategy: Maximise Sharpe
Using the same anonymous real market data, build a classification-based trading strategy. Your goal is the highest risk-adjusted return.
Strategy must maximise risk-adjusted returns. Ranked against other submissions by Sharpe ratio.
Advanced Coming Soon

Advanced Machine Learning Trading Strategies

Build production-grade ML trading strategies with richer features, stronger validation, model ensembles, regime awareness, and portfolio construction techniques designed to survive live markets.

Prerequisites: Machine Learning Trading Strategies
5 modules 0 exercises
Coming Soon
What you'll learn
  • Engineer robust features from price, volume, volatility, order flow, and cross-asset relationships
  • Use walk-forward validation, purged cross-validation, and embargo periods to reduce leakage
  • Combine models with ensembles, stacking, and confidence-weighted signals
  • Adapt models across market regimes using clustering and regime classifiers
  • Turn predictions into position sizing, risk limits, and portfolio allocations
  • Monitor live model decay, drift, and execution-aware performance
What you'll do
  • Research a model-driven strategy with realistic validation and trading constraints.
  • Compare single-model signals with ensemble and regime-aware approaches.
  • Build a full ML trading pipeline from feature generation to portfolio sizing.
  • Stress-test the strategy for overfitting, instability, and changing market conditions.

What you'll cover

  1. neural-network-fundamentals Plus
    Learn the core fundametnals of neural networks so you understand the math and principles of them
  2. Non-linear Regression Plus
    Learn how to use neural networks for non-linear regression
  3. Non-linear Classification Plus
    Learn how to use neural networks for non-linear classification
  4. Sequence Modelling Plus
    Lean how to apply sequence modelling to trading.
  5. Deep Learning Plus
    Lean how to apply deep learning to quant trading strategies and the common problems with applying it to financial markets.

Challenges

1
Ensemble Strategy: Maximise Sharpe
Build an ensemble-based trading strategy and compete on risk-adjusted performance across hidden evaluation periods.
Strategy must be net profitable and maximise Sharpe across out-of-sample evaluation windows.
2
Regime-Aware Strategy
Detect changing market regimes and adapt your model, signal thresholds, or position sizing accordingly.
Strategy must outperform a static baseline while controlling drawdown across multiple regimes.
Advanced Coming Soon

Market Making Strategies

Learn how professional market makers profit from the spread, manage inventory risk, and provide liquidity across markets. Build systematic market making strategies from quote placement to execution.

Prerequisites: Advanced Machine Learning Trading Strategies
5 modules 0 exercises
Coming Soon
What you'll learn
  • Understand how market makers profit from the bid-ask spread
  • Understand how market makers skew their spread
  • Model and manage inventory risk as a market maker
  • Identify and defend against toxic order flow and informed traders
  • Build low-latency execution logic for high-frequency environments
  • Understand order book microstructure
What you'll do
  • Develop a basic market making algorithm
  • Learn how to quote
  • How to manage inventory risk

What you'll cover

  1. Spread Plus
    How market makers make markets using the spread.
  2. Bias Plus
    How market makers bias their prices to minimize adverse selection.
  3. Order Book Dynamics Plus
    Understand order book microstructure, queue priority, and how prices move at the microscopic level.
  4. Inventory Management Plus
    Model and manage inventory risk: the core challenge of running a market making book.
  5. Execution & Latency Plus
    Build low-latency execution logic and understand the role of co-location and order routing.