School of Computer Science BCS accreditation 2021 - 2026

Computer Science (Human Computer Interaction) BSc (Hons) - COMP13212 Data Science

2.1.1 Knowledge and understanding of facts, concepts, principles & theories

This course is an introduction to data science, where data science refers to a set of concepts, techniques, and theories for extracting knowledge and information from data using computers.

Assesement : Examination, Lab work

2.1.3 Problem solving strategies

The specific problems concern the use of data to address questions. A number of techniques are investigated. When their use is appropriate is part is the most important concept for the student to learn.

Assesement : Examination, Lab work

2.1.6 Recognise legal, social, ethical & professional issues

The ethical use of data, and the validity of the assumptions used to draw conclusions from data is covered briefly.

Assesement : Examination

2.2.2 Evaluate systems in terms of quality and trade-offs

The course covers topics relevant to objective evaluation of systems: concept and quantification of uncertainty in measured and experimental data, visualization of data, hypothesis generation and testing, and basic statistical tests. These topics constitute a substantial part of the course. One objective of the course is that on successful completion, the student should be able to design and carry out a valid experiment to test a hypothesis.

Assesement : Examination, Lab work

2.2.4 Deploy tools effectively

The lab work of this course, as well as the demonstrated examples, are carried out in python using the following tools: Jupyter notebooks, matplotlib.pyplot, numpy, pandas, scikit-learn. The students cannot carry out the labs without effectively deploying these tools. This is only assessed in practical lab sessions; it is not examined.

Assesement : Lab work

2.3.2 Development of general transferable skills

The outcomes of the assessed labs are reports in the form of Jupyter Notebooks. In producing these from the lab scripts (which are themselves Jupyter Notebooks), the students are "walked through" the act of producing a valid report.

Assesement : Lab work

3.1.2 Methods, techniques and tools for information modelling, management and security

A substantial part of the course is about modelling data to extract information from it. Model techniques include probabilistic models of data, Bayesian reasoning, and rudimentary machine learning models, such as linear models, polynomial models, and Bayesian models.

Assesement : Examination, Lab work

3.1.4 Knowledge and understanding of mathematical and/or statistical principles

The course covers statistical principles, including quantification of uncertainty and hypothesis testing. Probabilistic reasoning including Bayesian reasoning is covered.

Assesement : Examination, Lab work

3.2.2 Defining problems, managing design process and evaluating outcomes

As stated earlier, the course gives background in the experimental evaluation of outcomes. The course material embodies the "Data Science process" which has some overlaps with the process described above, but specific to the use of data to address a problem. It is: Define the problem, get data to address the problem, clean the data, visualize the data, build a model to address the problem, evaluate the validity of the assumptions being used, evaluate the outcomes of the model quantitatively, and report on the work. No time is spend on customer or user needs, not on cost drivers.

Assesement : Examination, Lab work

4.1.1 Knowledge and understanding of scientific and engineering principles

The understanding of uncertainty in experimental measurements and sampled data, how uncertainty is quantified, how it propagated through computations, and how it affects the comparative evaluation between systems is covered. How to make statistically sound comparisons is covered.

Assesement : Examination, Lab work

4.1.2 Knowledge and understanding of mathematical principles

4.1.3 Knowledge and understanding of computational modelling

Computational modelling of data is covered. The statistical bootstrap and simulation which both use computational modelling to address statistical questions are covered.

Assesement : Examination, Lab work