Workshops for Students and Researchers

Aim and Content

Organised by the Iscte Business Analytics & Data Science Lab, the course Machine Learning for PhD Research introduces key methods in machine learning for analysing scientific data across a wide range of fields. It covers data cleaning, data transformation, the fundamentals of machine learning (including labels, variables, parameter optimisation, overfitting, and cross-validation), key supervised and unsupervised learning methods, and data visualisation. 

Course Contents

1. Introduction
2. Data preprocessing and Data transformation
3. Machine Learning
   • Supervised learning
     • Classification
     • Regression
   • Unsupervised learning
     • Principal Component Analysis
     • Clustering
4. Visualisation

Learning Outcomes

1. Understand key machine learning concepts and methods.
2. Develop/adapt/extend a computer-based software method for analysis of relevant data.
3. Propose relevant analysis methods for scientific data science problems.
4. Design, critique and build honest visualizations in Python, choosing encodings and chart types that fit the data and the task, and recognising how charts can mislead.
5. Consider inter-disciplinary data science methods in PhD research projects.

Target Group

The course is intended for PhD students whose research involves data analysis or could benefit from the application of machine learning methods. Preference will be given to students who are at an early stage of their doctoral research. 

Pre-requisites

• We use Python for the examples and exercises, but Python programming experience is not a prerequisite for this course. Some familiarity with Python may make the practical components more comfortable, but the course is designed to be accessible to students with no prior programming experience. 

• Participants must bring their own laptops with either Anaconda or Visual Studio Code installed and configured to run Jupyter Notebooks. Additional software requirements and installation instructions will be provided before the course. 

Methods

Four full days of interactive, hands-on lectures and exercises. For each topic, students will gain hands-on experience applying and modifying analysis methods, with practical examples implemented in Python using Jupyter notebooks. 

Certificate

A certificate will be awarded to participants who attend the full training. 

Lecturers

Ana Catarina Nunes, Dept. Quantitative Methods, BA&DS Lab 

Mafalda Ponte, Business Research Unit, BA&DS Lab

Tomás Alves, Business Research Unit, BA&DS Lab

You can apply for the course through the online application form.

Course fee

The course is free of charge. When applying, participants must provide proof of enrolment in an Iscte PhD programme. 

Contact person

Should you have any questions or require additional information please contact Prof. Ana Catarina Nunes: catarina.nunes@iscte-iul.pt