Learning Program

Quantitative Analysis & Machine Learning

Structured around the way practitioners actually work - not around textbook chapters. Each module covers a specific problem type, uses real datasets, and expects you to get things wrong before getting them right.

Quantitative analysis and machine learning lecture materials

What the program covers

Six modules, one coherent arc

Each module builds on the previous without assuming you memorised every detail. The sequence moves from probability and statistical inference through to supervised learning, model evaluation, and time-series forecasting - topics that appear together in real analytical work, not in isolation.

6 Modules covering the full analytical pipeline

18 Structured lectures with worked examples

40+ Exercises using real-world datasets

Module 01 Probability & Statistical Inference

Covers distributions, hypothesis testing, and confidence intervals. Uses Python and SciPy throughout - no hand-calculation exercises.

Module 02 Exploratory Data Analysis

Structured methods for understanding a dataset before modelling. Covers missing data patterns, outlier detection, and correlation analysis using pandas and matplotlib.

Module 03 Regression & Classification

Linear and logistic regression, decision trees, and k-nearest neighbours. Emphasis on understanding what each model actually optimises.

Module 04–06 Advanced Topics

Ensemble methods, neural network fundamentals, and time-series forecasting with ARIMA and Prophet. Each module includes a graded project on a provided dataset.

Instructor working through quantitative methods with students

2021 Founded in Dublin to serve learners who need analytical skills without a full academic detour

How the lectures are structured

Sequential delivery, not a syllabus dump

Each lecture opens with a problem statement drawn from finance, public data, or logistics - something with a concrete question attached. The theory follows from the problem, not the other way around. This makes it easier to remember why a method exists, not just how to apply it.

Sessions are recorded and captioned. Exercises are submitted through the platform and reviewed within a few days. Feedback is specific to the submission, not generic.

1
Problem-first framing
Every concept is introduced through a dataset or scenario that motivates it. You see the question before you see the formula.
2
Worked examples in Python
Code is shown incrementally, with deliberate mistakes included and corrected on screen. Watching someone debug is more instructive than watching clean runs.
3
Graded module projects
Each module ends with a project using a dataset you have not seen in the lectures. Solutions are compared and discussed in a group review session.
4
Specific written feedback
Submissions receive line-level comments, not a score alone. The focus is on reasoning and code clarity, not just whether the output is numerically correct.