Machine Learning tutorials and worked examples

Fit probabilities and inspect thresholded errors.

• Logistic regression from scratch: fit probabilities and inspect errors

  Implement stable binary cross entropy and its gradient in NumPy, train on invented data and compare held-out predictions with a constant baseline.

  tutorial · 4 min read

Choose transformations that match feature meaning and model geometry.

• Scaling vs normalization: feature statistics or row lengths

  Compare StandardScaler, MinMaxScaler and Normalizer inside a fixed training split, and show why the word normalization needs a precise definition.

  comparison · 4 min read

Calculate splits and evaluate tree complexity.

• Decision-tree split criteria: calculate weighted Gini impurity

  Enumerate thresholds on an explicit binary dataset, fit a one-level tree and compare held-out performance with a majority baseline.

  tutorial · 4 min read

Measure reliance while checking what an explanation can support.

• Permutation feature importance: measure reliance and inspect correlated features

  Fit a reproducible regression task, calculate held-out permutation importance and jointly shuffle correlated columns to expose an interpretation limit.

  tutorial · 4 min read

Compare future predictions using chronological baselines.

• Time series forecasting in machine learning: start with persistence and seasonal baselines

  Compare fixed-origin persistence and weekly seasonal-naive forecasts on chronological development and test windows, with explicit dates and errors.

  tutorial · 4 min read

Rank available items and test relevance at a declared budget.

• Build a content-based recommendation system and test its top results

  Rank an original miniature catalogue with TF-IDF and cosine similarity, exclude the seed item and evaluate top-k relevance without pretending to measure user satisfaction.

  tutorial · 4 min read

Choose metrics, splits and diagnostic experiments that support valid conclusions.

• Cross-validation for groups and time: check what a split holds out

  Audit random, grouped and chronological folds on the same small table, and choose a split that matches the prediction you intend to make.

  tutorial · 4 min read

• ROC AUC vs PR AUC: inspect what changes with class balance

  Compare ROC AUC, average precision and trapezoidal PR area on an explicit ranking, then change prevalence while preserving class-conditional scores.

  comparison · 4 min read

• Data leakage in machine learning: examples and prevention

  Spot target leakage, preprocessing leakage and train-test overlap. See concrete examples and a Python pipeline that keeps fitted transformations separate.

  troubleshooting · 6 min read

• Overfitting vs underfitting: examples and how to fix each

  Tell overfitting from underfitting using training and validation error. Work through a demand example, diagnose the cause and choose a sensible next experiment.

  troubleshooting · 6 min read

Fit predictions for numerical targets and inspect their errors.

• Linear regression in machine learning: a worked Python example with a baseline

  Learn linear regression with a worked prediction, runnable Python, a held-out test and a baseline. Explain coefficients and check where a line can fail.

  tutorial · 6 min read

Find structure and unusual records without pretending clusters supply their own validation.

• Machine learning for outlier detection: an Isolation Forest example in Python

  Use machine learning to flag unusual rows for review. Run an Isolation Forest example, compare simple rules and understand thresholds and false alarms.

  tutorial · 6 min read

• Machine learning for unlabeled data: a clustering example and how to check it

  Explore unlabeled data with a runnable clustering example. Understand cluster IDs, scaling, useful checks and when you still need human labels.

  tutorial · 6 min read

Connect a prediction to a decision and a complete experiment.

• Machine learning for business analytics: start with the decision, then the model

  Plan a useful machine learning project for business analytics: define a decision, compare a rule, choose data and evaluate errors with a worked example.

  explanation · 6 min read

• Machine learning for non-technical people: how to read a model report and what to ask

  Understand machine learning without coding: follow a worked example, read a model report and ask useful questions before starting a project.

  explanation · 6 min read

• Machine learning for predictive analytics: define the target, beat a baseline, test fairly

  Learn predictive analytics through a clear target, prediction-time inputs, a baseline and held-out evaluation. Work through a forecast example and common errors.

  tutorial · 6 min read

Plan useful model artifacts with explicit baselines and evaluation.

• Machine learning projects for your portfolio: three briefs with evaluation plans

  Build an ML portfolio with three practical project briefs covering prediction, document search and image classification, with baselines and clear deliverables.

  project · 5 min read

Choose prerequisites and a sequence of skills with concrete checkpoints.

• Where to start with machine learning: a beginner's four-step path

  Start machine learning with a four-step learning path: Python, data tools, maths and statistics, then models. Check your progress with practical tasks.

  learning path · 8 min read

• How to learn AI from scratch: a practical beginner's plan

  Learn AI from scratch with a week-by-week plan: Python, data tools, maths, statistics, a first machine learning model and a small generative AI project, with a checkpoint for each stage and free resources.

  learning path · 11 min read

• Machine learning engineer roadmap: seven stages, each with a checkpoint

  A machine learning engineer roadmap in seven stages: Python as software, data tools, the maths a model uses, classical ML, production habits, deep learning and a portfolio. Each stage links to free lessons and ends in a checkpoint.

  learning path · 11 min read

• How to get an AI or machine learning internship: what to learn, build and explain

  A student's plan for an AI or machine learning internship: the foundations interviewers test, two projects worth building, the questions your project will raise, and how to apply without overclaiming.

  learning path · 7 min read

• AI engineer vs machine learning engineer: the difference, and what to learn for each

  A machine learning engineer trains and deploys models; an AI engineer builds products on existing models. How the work, skills and maths differ, the foundations both share, and a learning order for each.

  comparison · 7 min read

Practise explaining modeling choices and their limitations.

• Machine learning interview questions: how to prepare, with worked answers

  Prepare for a machine learning interview with worked questions on splits, leakage, baselines, metrics and regression, plus a practical revision plan.

  interview guide · 7 min read