Applied Data Analytics November 2025

Applied Data Analytics - November 2025

This course covers essential techniques, methodologies, and practical skills for extracting meaningful insights from data. It is designed for doctoral students from various faculties at Université Paris Cité and provides a strong foundation in data science, analytics, machine learning, deep learning, and data mining.

Format of Lectures

This intensive course runs over one week in the fall, from Monday to Friday, between 10:00 AM and 1:00 PM, totalling approximately 15 hours.

Instruction includes slides, hands-on Google Colaboratory exercises, and questionnaires.

On the final day, students will present analysis challenges related to their theses.

The course is conducted via Zoom.

Information

Interested students can enrol through https://u-paris.fr/doctorat/applied-data-analytics/.

Enrolled students will receive access to course materials via email.

Learning Outcomes

By the end of this course, students will:

• Understand the basics of data preparation and supervised learning.

• Gain proficiency in regression and classification techniques.

• Explore advanced topics such as neural networks and deep learning.

• Apply unsupervised learning methods and generative models.

• Present and discuss their data analysis challenges and link them to the topics of the course.

Instruction Methods

• Lectures via Zoom using slides

• Practical exercises with Google Colaboratory

• Interactive polls and Q&A sessions

Assessment

• Participation in class discussions and polls

• Presentation of data analysis challenges on the final day

Zoom link

Here is the Zoom link to follow the lectures live.
You will also find the passwords required to access the recorded lectures.

Course Material

Enrolled students who need access to course materials should contact me via email. 

• Lecture 1: Introduction

  • Zoom recording 1

• Lecture 2: Data Preparation

  • Zoom recording 2

  • Colaboratory Notebooks:

    • Log10 Transformation of Features

    • Data Preparation

• Lecture 3: Classic Supervised Learning: Machine Learning Algorithms, Boosted Decision Trees, Multi Layer Perceptrons

  • Zoom recording 3

  • Colaboratory Notebooks:

    • Comparison of different classifiers

    • Binary Classification

    • Data-driven imputation for missing data

    • Techniques to handle imbalanced datasets

    • Classic Supervised Learning - Regression and Ensemble Learning

    • Multi-label Classification

    • Classification of written digits with an MLP

    • Classification of fashion images with an MLP

• Lecture 4: Deep Learning

  • Zoom recording 4

  • Colaboratory Notebooks:

    • Image Analysis: 

      •  Data Augmentation

      • Exploring the MNIST dataset with a CNN

      • Classification of fashion images with a CNN

      • Image Classifier with the Cats and Dogs dataset with a CNN and the Pre-Trained CNN-based MobileNetV2 

      • Using the DINOv2 META AI transformer-based model for a galaxy classification task

    • Time Series:

      • Time Series Forecasting with Recurrent Neural Networks

• Lecture 5:  Unsupervised Learning

  • Zoom recording 5

  • Colaboratory Notebooks: 

    • Pseudo-labelling of tabular data through dimensionality reduction and clustering with UMAP and HDBSCAN

    • Finding outliers in data through UMAP and HDBSCAN

    • Exploring High-Dimensional Representations with UMAP and Inverse Transformations 

Daily Attendance Polls 

Monday Poll

Tuesday Poll

Wednesday Poll

Thursday Poll

Friday Poll