A written version of the interactive roadmap above — every station, what you'll learn, and a small thing to build — laid out for reading, reference and search.
Foundations Start here
F1. Statistics & Probability
Beginner · 65 min
Statistics is the grammar of data science — misread it and every conclusion after is suspect. Learn distributions, sampling, expectation and variance, the central limit theorem, confidence intervals and hypothesis testing, plus the p-value everyone quotes and few define correctly.
Skills: Distributions & sampling · Central limit theorem · Confidence intervals · Hypothesis testing & p-values
Build it: A test shows p = 0.03. Write, in one sentence, what that actually means — and what it does NOT mean.
✓ Checkpoint: Explain what a confidence interval does and does not claim — “95% chance the true value is in here” is the usual wrong version.
F2. Python for Data
Beginner · 55 min
Python is the lingua franca of data work. Learn NumPy for vectorized math, pandas for wrangling, and the notebook workflow — the daily tools where 80% of a data scientist’s time is actually spent (cleaning, reshaping, joining), not on the glamorous modeling.
Skills: NumPy vectorization · pandas wrangling · Notebooks · Reshape, join, clean
Build it: Given a messy CSV with nulls and mixed types, produce a clean, typed dataframe ready to model. Which step is most likely to hide a bug?
✓ Checkpoint: Explain why vectorised NumPy beats a Python loop by enough to change what is feasible.
F3. SQL & Data Access
Beginner · 55 min
The data lives in databases, and SQL is how you get it. Learn joins, aggregation, window functions and CTEs well enough to answer real questions without exporting everything to pandas — because the query that runs in the warehouse beats the one that melts your laptop.
Skills: Joins & aggregation · Window functions · CTEs · Query performance
Build it: Compute a 7-day rolling average of signups per country in SQL. Why is doing this in the warehouse better than pulling raw rows?
✓ Checkpoint: Explain what a window function does that GROUP BY cannot, using a running total as the example.
F4. Exploratory Data Analysis
Beginner · 55 min
Before modeling comes looking. Learn to profile a dataset, spot missingness and outliers, understand distributions and correlations, and visualize honestly — because the model is only as good as your understanding of the data feeding it, and EDA is where you earn that understanding.
Skills: Data profiling · Missingness & outliers · Correlation vs causation · Honest visualization
Build it: A feature correlates strongly with your target. List three ways that correlation could be misleading you before you trust it.
✓ Checkpoint: Give a real pair of variables that correlate with no causal link between them, and say what would distinguish the two cases.
F5. Linear Algebra & Calculus
Intermediate · 60 min
The math under the models. Learn vectors and matrices, dot products and matrix multiplication, and gradients — just enough to understand what an algorithm is doing rather than treating it as a black box you feed and pray to. Intuition over proofs, but real intuition.
Skills: Vectors & matrices · Matrix multiplication · Gradients & derivatives · Geometric intuition
Build it: Explain why gradient descent "walks downhill" using nothing but the idea of a derivative. What is the gradient pointing at?
✓ Checkpoint: Explain what a gradient tells you geometrically, and why that is enough to optimise anything.
F6. Data Wrangling at Scale
Intermediate · 50 min
Real data is bigger and messier than a tutorial CSV. Learn to handle data that does not fit in memory, join across sources, manage data types and encodings, and build reproducible pipelines — the unglamorous plumbing that determines whether your analysis is trustworthy.
Skills: Out-of-memory data · Multi-source joins · Encodings & types · Reproducible pipelines
Build it: Your analysis gives different numbers each run. List the three most likely non-determinism sources and how to pin each down.
✓ Checkpoint: Explain what changes about your approach the moment the data stops fitting in memory.
Machine Learning The craft
T1. Supervised Learning
Intermediate · 65 min
The core of applied ML: learn from labeled examples. Learn linear and logistic regression, decision trees, the bias-variance trade-off, and train/validation/test discipline — the workflow and the failure modes (overfitting, leakage) that every model you build will live or die by.
Skills: Regression & classification · Trees & linear models · Bias-variance trade-off · Train/val/test discipline
Build it: Your model scores 99% on training and 70% on test. Name the disease, then two ways to treat it.
✓ Checkpoint: State the bias-variance position of a model scoring 99% on train and 70% on test, and what you would change first.
T2. Model Evaluation
Intermediate · 60 min
Accuracy lies more often than it tells the truth. Learn precision, recall, F1, ROC/AUC, cross-validation, and the crucial skill of choosing the right metric for the problem — because optimizing accuracy on imbalanced data ships a model that predicts "no" and looks brilliant.
Skills: Precision, recall, F1 · ROC/AUC · Cross-validation · Choosing the right metric
Build it: A fraud model is 99.9% accurate. Explain why that could be worthless, and which metric you would actually report.
✓ Checkpoint: Explain why accuracy is the wrong metric on a 1%-positive dataset, and which one you would report instead.
T3. Feature Engineering
Advanced · 60 min
Often the highest-leverage work in ML: the right features beat a fancier model. Learn encoding, scaling, handling missing values, creating interactions, and the discipline of preventing target leakage — the subtle bug that makes offline metrics soar and production crash.
Skills: Encoding & scaling · Handling missingness · Feature creation · Preventing leakage
Build it: A feature secretly encodes the answer (leakage). Give a realistic example and explain how a time-based split would catch it.
✓ Checkpoint: Explain why fitting an encoder or scaler before the split leaks the test set, and how the leak shows up as an optimistic score.
T4. Ensembles & Gradient Boosting
Advanced · 60 min
The models that win on tabular data. Learn random forests and gradient boosting (XGBoost, LightGBM), why combining weak learners beats one strong one, and when a boosted-tree model — not a neural network — is still the correct, boring, effective answer for structured data.
Skills: Random forests · Gradient boosting (XGBoost) · Weak learners combined · Tabular > deep learning
Build it: For a tabular business dataset, argue why XGBoost is likely the right first model over a neural net. When would that flip?
✓ Checkpoint: Explain how boosting turns weak learners into a strong one, and why that makes it easier to overfit than bagging.
T5. Unsupervised Learning
Advanced · 55 min
Finding structure with no labels. Learn clustering (k-means, hierarchical), dimensionality reduction (PCA, t-SNE/UMAP), and anomaly detection — the tools for segmenting customers, compressing features, and surfacing the weird points that supervised learning never labeled.
Skills: Clustering · PCA & dimensionality reduction · Anomaly detection · Embeddings & structure
Build it: You have customers but no segments. Design a clustering approach — and explain how you would judge whether the clusters mean anything.
✓ Checkpoint: Explain how you would judge whether a clustering found real structure or just partitioned noise.
T6. Deep Learning
Advanced · 65 min
When the data is unstructured — images, text, audio — neural networks take over. Learn the building blocks (layers, activations, backprop), when deep learning is worth its cost over classic ML, and the frameworks (PyTorch) that turn the math into models you can actually train.
Skills: Neural network basics · Backprop & activations · When deep learning wins · PyTorch
Build it: Given a project, decide: classic ML or deep learning? List the signals in the data and problem that push you each way.
✓ Checkpoint: Explain when deep learning is worth it over a gradient-boosted tree on tabular data — the honest answer is “often not”.
Impact & the LLM Era Turn models into decisions
P1. Experimentation & A/B Testing
Advanced · 65 min
The skill that most directly drives business decisions. Learn experiment design, sample-size and power calculations, avoiding peeking and p-hacking, and interpreting results honestly — because a badly run A/B test does worse than nothing: it launders a bad decision as data.
Skills: Experiment design · Power & sample size · Peeking & p-hacking · Honest interpretation
Build it: A PM wants to stop the test early because it "looks significant". Explain the danger and what rule should govern stopping.
✓ Checkpoint: Explain what goes wrong when you check an experiment early and stop as soon as it looks significant.
P2. Causal Inference
Advanced · 60 min
Correlation is easy; causation is where decisions live and where careers are made. Learn confounders, the potential-outcomes framework, and quasi-experimental methods (difference-in-differences, instrumental variables) for when you cannot run an A/B test but still must answer "did it actually work?"
Skills: Confounders · Potential outcomes · Diff-in-diff & IV · Observational causality
Build it: Users who use feature X retain better. Design how you would tell "X causes retention" from "retained users use X".
✓ Checkpoint: Name a confounder that would make an obvious causal story wrong, and how you would probe for it without an experiment.
P3. Communicating Results
Intermediate · 55 min
A brilliant analysis nobody understands changes nothing. Learn to tell the story in the data, visualize for a decision (not for decoration), tailor depth to the audience, and state uncertainty honestly — the storytelling that turns a model into an action someone takes.
Skills: Data storytelling · Decision-focused viz · Audience tailoring · Communicating uncertainty
Build it: Present a churn model to executives in three slides. What is on them — and what technical detail did you deliberately leave off?
✓ Checkpoint: State the “so what” of a recent analysis in one sentence, before any numbers.
P4. MLOps & Productionizing
Advanced · 60 min
A model in a notebook helps no one. Learn to deploy models as services, monitor for data and concept drift, retrain on schedule, and version data and models — the engineering that turns a one-off analysis into a system that keeps making good predictions next quarter.
Skills: Model deployment · Drift monitoring · Retraining pipelines · Data & model versioning
Build it: Your live model’s accuracy quietly drops over two months. Name the likely cause and the monitoring that would have caught it early.
✓ Checkpoint: Explain how you would notice a deployed model degrading before a stakeholder complains.
P5. Data Science with LLMs
Advanced · 60 min
LLMs rewired the field. Learn where they help — text classification and extraction without labeled data, synthetic data, exploratory analysis by prompting — and where classic ML still wins, plus the honest evaluation that keeps a fluent-but-wrong model out of your decisions.
Skills: LLMs for classification/extraction · Zero-shot vs fine-tune · Synthetic data · Evaluating LLM outputs
Build it: You need to categorize 50K support tickets with no labels. Compare an LLM zero-shot approach vs training a classic model — costs and risks.
✓ Checkpoint: Explain when an LLM beats a trained classifier for an extraction task, and when it is the expensive wrong tool.
P6. The Data Science Career
Intermediate · 45 min
Data science splits into flavors — analytics, ML engineering, research, decision science — and knowing your lane matters. Learn the archetypes, the business acumen that separates senior from junior, how to pick high-impact problems, and how to grow from running analyses to shaping strategy.
Skills: DS archetypes · Business acumen · Picking high-impact work · IC to leadership
Build it: Map your next six months: one stats/ML skill, one engineering skill, one communication skill — and the project that proves each.
✓ Checkpoint: Name which data-science archetype your last six months resembled, and whether that is the one you want.