Upon completion of this course you will:

This course supports this knowledge from a technical perspective giving tools to put in practice its implementation. Build upon your existing skills!

  • Learn the basics of machine learning (ML)

  • Learn how to build Machine Learning models with Python with practical examples and exercises

  • Understand how to productionise ML mode within Adevinta

  • Know the basic workflow of preprocessing data, cross-validation, and model selection.

  • Learn a methodology to build and integrate ML in our products

  • Understand the importance of data, its ethical usage and legal basics of GDPR

  • Have a curated list of material to read and practice on your own time

  • Learn about barriers to scale ML in Adevinta and ML best practices

  • Understand Data in ML model and Data in Adevinta

Course curriculum

A new module will be launched every week until the course is completed

  • 1

    Adevinta ML Strategy

  • 2

    Before we start...

    • To get the most out of this course we recommend you:

    • Course check-in
  • 3

    Introduction to the training

    • Introduction to the training, by Rosangela Fonseca

    • Content and structure, by Manuel Sanchez
  • 4

    Introduction to Machine Learning - Dealing with data

    • Meet your instructor - A message from Francesco Mosconi

    • 01 Machine Learning and AI

    • MLT-01.1- Test your learning

    • 02- Machine Learning Enablers

    • MLT-01.2- Test your learning

    • 03 - Tabular Data

    • MLT-01.3- Test your learning

    • 04-Data Operations in Pandas

    • MLT-01.4- Test your learning

    • 05 -Data Structures

    • MLT-01.5- Test your learning

    • 06 -Input and Output

    • MLT-01.6- Test your learning

    • 07- Selections and Filters

    • MLT-01.7- Test your learning

    • 08 - Feature Engineering

    • MLT-01.8- Test your learning

    • 09- Aggregations

    • MLT-01.9- Test your learning

    • 10- Sort & Pivot

    • MLT-01.10- Test your learning

    • 11- Joins

    • MLT-01.11- Test your learning

    • 12 -Time Series

    • MLT-01.12- Test your learning

    • 13 - Other Commands

    • MLT-01.13- Test your learning

    • 14- Data Visualization

    • MLT-01.14- Test your learning

    • 15 -Common questions

    • 16-How to do the labs

    • 17- Lab Walkthrough

    • 18- Lab Exercise 1

    • 19- Lab Exercise 2
  • 5

    Regression

    • 00- The 3 main techniques in machine learning

    • MLT-02.0- Test your learning

    • 01- Types of machine learning

    • MLT-02.1- Test your learning

    • 02- Supervised and Unsupervised Learning

    • MLT-02.2- Test your learning

    • 03- How to choose ML technique.

    • MLT-02.3- Test your learning

    • 04-Regression

    • MLT-02.4- Test your learning

    • 05- Loss minimization

    • MLT-02.5- Test your learning

    • 06- Machine Learning Workflow

    • MLT-02.6- Test your learning

    • 07-The R Square Score

    • MLT-02.7- Test your learning

    • 08-Generalization and Overfitting

    • MLT-02.8- Test your learning

    • 09 Scikit Learn

    • 10- Scikit Learn Components

    • MLT-02.10- Test your learning

    • 11- Scikit Learn Pipelines

    • MLT-02.11- Test your learning

    • 12- Scikit Learn Regression Models

    • 13 -Common questions

    • 14- Lab Walkthrough

    • 15- Lab Exercise 1

    • 16- Lab Exercise 2

    • 17- Lab Exercise 3

    • 18-Jupyter debug magic
  • 6

    Classification

    • 00 Classification

    • 01 Classification Labels

    • MLT-03.1- Test your learning

    • 02 Binary Classification with Decision Tree

    • MLT-03.2- Test your learning

    • 03 Advantages of Decision Trees

    • MLT-03.3- Test your learning

    • 04 History of ML models

    • 05 KNearest Neighbors

    • MLT-03.5- Test your learning

    • 06 Logistic Regression

    • MLT-03.6- Test your learning

    • 07 Neural Networks

    • MLT-03.7- Test your learning

    • 08 Support Vector Machines

    • MLT-03.8- Test your learning

    • 09 Ensembles and bagging

    • MLT-03.9- Test your learning

    • 10 Random Forest and Boosting

    • MLT-03.10- Test your learning

    • 11 Scikit Learn

    • 12 Model Evaluation

    • MLT-03.12- Test your learning

    • 13 Confusion Matrix

    • MLT-03.13- Test your learning

    • 14 Multi-class Classification

    • MLT-03.14- Test your learning

    • 15 -Common questions

    • 16- Lab Walkthrough

    • 17- Lab Exercise 1

    • 18- Lab Exercise 2

    • 19- Lab Exercise 3
  • 7

    Clustering

    • 00- Introduction to clustering

    • 00- Test your learning

    • 01- Distance and Similarity

    • MLT-04.1- Test your learning

    • 02- K-Means

    • MLT-04.2- Test your learning

    • 03- Model Evaluation

    • MLT-04.3- Test your learning

    • 04- Elbow Method

    • MLT-04.4- Test your learning

    • 05- Silhouette Score

    • MLT-04.5- Test your learning

    • 06-Other clustering methods

    • MLT-04.6- Test your learning

    • 07-Scikit Learn clustering

    • MLT-04.7- Test your learning

    • 08-Scikit Learn implementation

    • MLT-04.8- Test your learning

    • 09 -Common questions

    • 10- Lab Walkthrough

    • 11- Lab Exercise 1

    • 12- Lab Exercise 2

    • 13- Lab Exercise 3
  • 8

    Course Check- in

    • Say it like it it- Course Survey

  • 9

    Feature Engineering

    • 00- Feature Engineering

    • 00- Test your learning

    • 01- Missing Data

    • 01- Test your learning

    • 02- How to deal with missing data

    • 02- Test your learning

    • 03-Standardization and Normalization

    • 03- Test your learning

    • 04- Categorical Features.

    • 04- Test your learning

    • 05-High cardinality features

    • 05- Test your learning

    • 06- Feature selection

    • 06- Test your learning

    • 07- Scikit Learn

    • 07- Test your learning

    • 08- Common questions

    • 08- Test your learning

    • 09- Lab Walkthrough

    • 10- Lab Exercise 1

    • 11- Lab Exercise 2

    • 12- Lab Exercise 3
  • 10

    Model Evaluation

    • 00- Introduction

    • 01- Baselines.

    • 01- Test your learning

    • 02- An anecdote on baselines

    • 03- Performance

    • 03- Test your learning

    • 04- Crossvalidation

    • 04- Test your learning

    • 05- Train Validation Test split

    • 05- Test your learning

    • 06-ROC Curve

    • 06- Test your learning

    • 07- Learning Curves

    • 07- Test your learning

    • 08- Dimensionality Reduction

    • 08- Test your learning

    • 09 - t-SNE

    • 09- Test your learning

    • 10- Scikit Learn Pipelines

    • 10- Test your learning

    • 11- Scikit Learn Flowchart

    • 12- Common questions

    • 13- Lab Walkthrough

    • 14- Lab Exercise 1

    • 15- Lab Exercise 2

    • 16- Lab Exercise 3
  • 11

    Data in Adevinta

    • 00- Introduction to Data in Adevinta

    • 1.1- What means Data in Adevinta

    • 1.2 - Sharing Data in Adevinta , Data Highway

    • 1.3 - Metrics

    • 1.4 - Recap

    • MLB08 - Test your learning- Lesson 1

    • 2.1 - Introduction to datasets, producers, consumers and lineage

    • 2.2 - Principles of managing datasets

    • 2.3 -Tagging Plans

    • 2.4 -Schemas

    • 2.5-Describing datasets

    • 2.6 -Recap

    • MLB08 - Test your learning- Lesson 2

    • 3.1 & 3.2 -Data quality dimensions and Data quality and lineage (Optional)

    • 3.3 -The harm of bad data

    • 3.4 -Why does low quality data happen?

    • 3.5 - Data quality lifecycle

    • MLB08 - Test your learning- Lesson 3

    • 4.1 - Tools to colect data

    • 4.2 - Tools for data exploration

    • 4.3 - Recap

    • 4.4 - Schema validation

    • 4.5 - Anomaly detection and data quality check

    • 4.6 - Alerting and reporting

    • 4.7 - Recap

    • MLB08 - Test your learning- Lesson 4

    • ML8- 5 - BONUS CONTENT ondata in monoliths, and more on mapping

    • MLB08 - Test your learning- Lesson 5
  • 12

    Privacy in Adevinta

    • 00- Introduction to Privacy in Adevinta

    • MLB08.1 - Test your learning- Lesson 1

    • 01- Personal Data

    • MLB08.1 - Test your learning- Lesson 2

    • 02- Privacy: Purpose

    • MLB08.1 - Test your learning- Lesson 3

    • 03- Privacy: User rights

    • MLB08.1 - Test your learning- Lesson 4

    • 04- Privacy: Incidents

    • MLB08.1 - Test your learning- Lesson 5

    • 05- Privacy: Anonymous

    • MLB08.1 - Test your learning- Lesson 6

    • 06- Privacy: Recap

    • 07- Privacy in Machine Learning - part I

    • MLB08.1 - Test your learning- Lesson 8

    • 08- Privacy: Minimization techniques

    • MLB08.1 - Test your learning- Lesson 9
  • 13

    Natural language processing

    • 00- Introduction to NLP

    • MLB10.0 - Test your learning

    • 01- Machine Learning on Text

    • MLB10.1 - Test your learning

    • 02- Bag of Words

    • MLB10.2 - Test your learning

    • 03- Features from text

    • MLB10.3 - Test your learning

    • 04-Text Vectorizers

    • MLB10.4 - Test your learning

    • 05- Lab 1 Walktrhough

    • 06- Lab 1 Exercise 1

    • 07- Lab 1 Exercise 2

    • 08- Natural Language Processing

    • MLB10.8 - Test your learning

    • 09- Lab 2 Walktrhough

    • 10- Lab 2 Exercise 1

    • 11- Lab 2 Exercise 2

    • 12 -Word Embeddings

    • MLB10.12 - Test your learning

    • 13- Self-supervised Learning.

    • MLB10.13 - Test your learning

    • 14 - Word2Vec and Glove

    • MLB10.14 - Test your learning

    • 15- Lab 3 Walkthroug

    • 16 - Lab 3 Exercise 1
  • 14

    Barriers for scaling ML in Adevinta

    • 01- Introduction- What does scaling mean

    • 02- Status of ML in Adevinta

    • 03- Lack of knowledge and skills

    • 04-Machine learning and software development

    • 05- Inmmaturity of Machine learning tooling

    • 05.1 - Regulation and social responsability

    • 06- Data as an asset

    • 07- Problems of centralized data approach

    • 08- Distributed data approach

    • 09- Importance of data culture

    • 10- Going from experimentation to production

    • MLT11. 10- Test your learning
  • 15

    Productionising a ML model

    • 01- Going to production

    • MLT12.1- Test your learning

    • 02- Scaling & performance- vertically or horizontally

    • 03 - Scaling & performance- caching & Gpu's

    • MLT12.2- Test your learning

    • 05 - Deploy your model into common platform- Lesson 1

    • MLT12.1.1- Test your learning

    • 06 - Deploy your model into common platform- Lesson 2

    • MLT12.1.2- Test your learning

    • 07 - Deploy your model into common platform- Lesson 3

    • MLT12.1.3- Test your learning

    • 08 - Deploy your model into common platform- Lesson 4

    • MLT12.1.4- Test your learning

    • 09 - Deploy your model into common platform- Lesson 5

    • MLT12.1.5- Test your learning

    • 11 - Deploy your model into common platform- Lesson 6

    • 12 - Deploy your model into common platform- Lesson 7

    • MLT12.1.7- Test your learning

    • 12 - Deploy your model into common platform- Lesson 8

    • MLT12.1.6- Test your learning
  • 16

    Real world Machine Learning

    • ML12- Tech 00 Lab Exercise 1

    • ML12- Tech 01 Lab Exercise 1 Solution

    • ML12- Tech 02 Lab Exercise 2

    • ML12- Tech 03 Lab Exercise 2 Solution

    • ML12- Tech 04 Lab Exercise 3

    • ML12- Tech 05 Lab Exercise 3 Solution

    • ML12- Tech 06 Lab Exercise 4

    • ML12- Tech 07 Lab Exercise 4 Solution

    • ML12- Tech 08 Lab Exercise 5

    • ML12- Tech 09 Lab Exercise 5 Solution

    • ML12- Tech 10 Lab Exercise 6

    • ML12- Tech 11 Lab Exercise 6 Solution

    • ML12- Tech 12 Lab Exercise 7

    • ML12- Tech 13 Lab Exercise 7 Solution

    • ML12- Tech 14 Lab Exercise 8

    • ML12- Tech 15 Lab Exercise 8 Solution

    • ML12- Tech 16 Lab Exercise 9

    • ML12- Tech 17 Lab Exercise 9 Solution

    • ML12- Tech 18 Lab Exercise 10

    • ML12- Tech 19 Lab Exercise 10 Solution

    • ML12- Tech 20 Lab Exercise 11

    • ML12- Tech 21 Lab Exercise 11 Solution

    • ML12- Tech 22 Lab Exercise 12 Part 1

    • ML12- Tech 23 Lab Exercise 12 Part 1 Solution

    • ML12- Tech 24 Lab Exercise 12 Part 2

    • ML12- Tech 25 Lab Exercise 12 Part 2 Solution

    • ML12- Tech 26 Lab Exercise 13

    • ML12- Tech 27 Lab Exercise 13 Solution

    • ML12- Tech 28 Lab Exercise 14

    • ML12- Tech 29 Lab Exercise 14 Solution

    • ML12- Tech 30 Lab Exercise 15

    • ML12- Tech 31 Lab Exercise 15 Solution

    • ML12- Tech 32 Lab Exercise 16

    • ML12- Tech 33 Lab Exercise 16 Solution

    • ML12- Tech 34 Lab Exercise 17

    • ML12- Tech 35 Lab Exercise 17 Solution

    • ML12- Tech 36 Lab Exercise 18

    • ML12- Tech 37 Lab Exercise 18 Solution

    • ML12- Tech 38 Lab Exercise 19

    • ML12- Tech 39 Lab Exercise 19 Solution

    • Tech 40 Lab Exercise 20

    • ML12- Tech 41 Lab Exercise 20 Solution

    • ML12- Tech 42 Lab Next Steps

    • ML12- Tech 43 Lab 2 Walkthrough

    • ML12- Tech 44 Lab 2 Solution Walkthrough

    • ML12- Tech 45 Lab 2 Solution Ideas Implementation

    • ML12- Tech 46 Lab 2 Solution Bonus Embeddings
  • 17

    Next steps

    • Congrats! Here's what's next...

Reviews from our students

star rating

Read Less
5 star rating

Nice introduction to Panda

Sébastien Georget

Read Less
5 star rating

Great course!

Manuel Sanchez

I like very much how Francesco does it.

I like very much how Francesco does it.

Read Less
star rating

Read Less
Watch Intro Video

How to navigate & rate the course