| Module Code | STU44003 |
| Module Name | Data Analytics |
| ECTS Weighting[1] | 10 ECTS |
| Semester taught | Semester 1 & 2 |
| Module Coordinator/s | Profs. Alessio Benavoli (semester I) and Athanasios Georgiadis (semester II) |
| Academic Year | 2026-2027 |
Module Learning Outcomes
On successful completion of this module, students will be able to:
LO1. Identify, compare and select appropriate analysis and modelling techniques for a range of applications.
LO2. Deploy and document appropriate set of self-selected analysis techniques in response to the defined problem areas.
LO3. Demonstrate utilization of the appropriate statistical packages (in either R or Python) to perform and effectively present and interpret the analysis results.
LO4. Apply and critically evaluate key methods in unsupervised learning, including clustering, kernel-based clustering and principal component analysis, with emphasis on their foundational theoretical properties.
LO5. Implement and critically assess nonparametric methods for density estimation and regression, including their theoretical principles.
Module Content
- Overview of the field
- Review of Probability Theory
- Review of Hypothesis Testing
- Analysis of Categorical Data
- Concepts of Information Theory, Entropy, Mutual Information, Conditional Entropy, and Information Gain
- Bayesian Network and Sum-Product Networks
- Classification and Regression Tree
- Neural Networks
- Overfitting and the corresponding techniques to avoid overfitting (Cross Validation, Bagging, Boosting, Random Forest, …)
- Rule Fit Procedure, and Model Evaluation
- Handling Unbalanced Dataset
- Concept of Similarity and Distance
- Distance Measures for Various Data Types
- Concepts of Data Missingness and Its Mechanism
- Methods of Missing Data Imputation
- Nonparametric methods
- K-means Clustering
- K-medians and K-medoids
- Reproducing Kernel Hilbert Spaces (RKHS)
- Kernel K-means
- Principal Component Analysis (PCA)
- Principal Component Regression (PCR)
- Kernel Density Estimation
- Function Spaces and Regularity
- Nadaraya–Watson Regression
Teaching and learning Methods
Lectures and lab sessions.
Assessment Details
| Assessment Component | Brief Description | Learning Outcomes Addressed | % of total | Week set | Week Due |
| Coursework | semester I | All | 15% | ||
| Coursework | semester II | All | 15% | ||
| Examination | in-person (2 hours) | All | 70% | Exam session in Semester 2 |
Reassessment Details
Examination (2 hours, 100%)
Contact Hours and Indicative Student Workload
| Contact Hours (scheduled hours per student over full module), broken down by: | 58 hours |
| Lecture | 44 hours |
| Laboratory | 14 hours |
| Independent study (outside scheduled contact hours), broken down by: | 40 hours |
| Preparation for classes and review of material (including preparation for examination, if applicable | 30 hours |
| Completion of assessments (including examination, if applicable) | 10 hours |
| Total Hours | 98 hours |
Recommended Reading List
- Murphy, Kevin P. Probabilistic machine learning: an introduction. MIT Press, 2022.
- James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021). An introduction to statistical learning: with applications in R (Vol. 2). New York, Springer.
- James, G., Witten, D., Hastie, T., Tibshirani, R., & Taylor, J. (2023). An introduction to statistical learning: Python edition.
- C. M. Bishop. Pattern Recognition and Machine Learning. Springer, 2006.
- A. B. Tsybakov. Introduction to Nonparametric Estimation. Springer, New York, 2009.
- Peharz, Robert. Foundations of sum-product networks for probabilistic modeling. Diss. PhD thesis, Medical University of Graz, 2015.
Module Pre-requisites
Prerequisite modules: This is a year 4 module.
Other/alternative non-module prerequisites: NA
Module Co-requisites
None