Intermediate level Data and Machine Learning

Build and Validate Real Predictive Models

Go beyond your first model. Engineer features, validate without fooling yourself, handle imbalanced data and time series, explain what a model learned, and track experiments reproducibly, finishing with a predictive-model report reviewed by the NIBVEDA team.

  • 40hours of work
  • 19parts
  • Reviewedcapstone
  • Lifetimeaccess
  • Feature engineering
  • Cross-validation
  • Gradient boosting
  • Imbalanced data
  • Time-series forecasting
  • Model interpretation
  • Experiment tracking

At a glance

Who it is for

Learners who have trained a first model with pandas and scikit-learn (for example the Beginner programme) and want a trustworthy, professional workflow.

Before you start

Python, pandas, matplotlib and basic scikit-learn (train/test split, a classifier, a regressor). Python 3.10 or newer with Jupyter or a code editor. The Beginner programme or equivalent experience is recommended.

How you finish

Pass the quizzes and labs, then submit a capstone project. The NIBVEDA team reviews it and either accepts it or sends it back with comments you can act on.

What you will be able to do

  1. 01Create and select features inside leak-free scikit-learn pipelines
  2. 02Validate models with cross-validation and avoid data leakage
  3. 03Train tree ensembles and gradient boosting and tune them sensibly
  4. 04Handle imbalanced classes and choose metrics and thresholds that match the cost of errors
  5. 05Forecast time series with proper baselines and backtesting
  6. 06Explain predictions and record experiments so results can be reproduced

Curriculum 40 hours in 19 parts

Select a kind to highlight its parts.

Stage 1A validated tabular model7 parts · 11 h
  1. 1
    Feature engineering that helpsLesson · Short, focused reading with questions to check yourself.
    1 hFree
  2. 2
    Validation and model selectionLesson · Short, focused reading with questions to check yourself.
    1 h
  3. 3
    Leak-free feature pipelines in scikit-learnWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  4. 4
    Trees, forests and gradient boostingLesson · Short, focused reading with questions to check yourself.
    1 h
  5. 5
    Gradient boosting and hyperparameter searchWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  6. 6
    Check yourself: features and validationQuiz · Twelve questions, marked at once, with the reason behind each answer.
    1 h
  7. 7
    A validated tabular modelLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
Stage 2A forecasting project6 parts · 10 h
  1. 8
    Imbalanced classes and metrics that match the costLesson · Short, focused reading with questions to check yourself.
    1 h
  2. 9
    Imbalanced classification and threshold tuningWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  3. 10
    Time series: forecasting without cheatingLesson · Short, focused reading with questions to check yourself.
    1 h
  4. 11
    Forecasting with baselines and backtestingWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  5. 12
    Check yourself: imbalance and time seriesQuiz · Twelve questions, marked at once, with the reason behind each answer.
    1 h
  6. 13
    A forecasting projectLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
Stage 3A tracked, reproducible experiment4 parts · 8 h
  1. 14
    Explaining what a model learnedWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  2. 15
    Reproducible experiments and trackingWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  3. 16
    Check yourself: interpretation and reproducibilityQuiz · Twelve questions, marked at once, with the reason behind each answer.
    1 h
  4. 17
    A tracked, reproducible experimentLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
Stage 4Error analysis and fairness by slice1 part · 3 h
  1. 18
    Error analysis and fairness by sliceLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
FinishCapstone project1 part · 8 h
  1. 19
    A predictive model you can defendCapstone · A full project for your portfolio.
    8 h
Free lessonFeature engineering that helps
What you take away

An internship certificate with your skills on it.

Made for you automatically when you finish the last part, it names the internship programme, the level and the 40 hours, lists what you showed, and carries a number and a QR code. Anyone can check it on the NIBVEDA verification page, and it shows as withdrawn there if it is ever revoked.

  • Proof you completed all 40 hours of this internship programme
  • An Internship badge for your profile, CV or portfolio
  • Not a job, a stipend or an academic degree, and it says so

See how verification works

More in Data and Machine Learning

Keep building.

3 programmes in this track, from beginner to expert. Buy the learning path and save 15%.

BeginnerBeginner40 h From a Spreadsheet to Your First Model

Learn Python for data, clean and explore a real dataset, and train and honestly evaluate your first machine-learning model, finishing with a short report of your own.

  • Python
  • pandas
  • Data cleaning
Rs. 349 + GST
ExpertExpert42 h Deep Learning and Production ML Systems

Train neural networks, work with text, then take a model into production: serve it, test it, monitor it for drift, schedule data pipelines, design experiments properly and review risks, finishing with an end-to-end ML system reviewed by the NIBVEDA team.

  • PyTorch
  • NLP
  • Model serving
Rs. 999 + GST

See all 3 programmes in Data and Machine Learning Take the placement test

Before you enrol

Quick answers.

The policies have the full detail.

Refund policy Terms of use

Is this a real internship?

It is a virtual internship programme: a structured, self-paced course built around a real project, with checked assessments and a certificate. It is not employment, it does not carry a stipend and it is not an academic or AICTE-approved qualification. What it gives you is verified, project-based evidence of skills.

How does self-paced work?

You start when you like and move at your own speed. Each part unlocks when you finish the one before it. There are no live classes and no deadlines. Your access is shown on each programme page.

How is my work checked?

Quizzes are marked as soon as you submit them. Labs use a tick-list of tasks. Intermediate and Expert programmes finish with a capstone that the NIBVEDA team reviews and either accepts or sends back with comments.

Can I get a refund?

Please read the refund policy before you buy. It explains when a refund is possible.

Ready to start?

Rs. 765.82 including GST. Lifetime access. Read the first lesson free before you decide.

Compare programmes