omputational models and concepts for business analytics need to be implemented with tools and technologies.
Students will learn about computational thinking, experimental methodology and empirical methods for training, validation and testing models. This course will cover the preparation of datasets, and introduce students to simple examples of both supervised and unsupervised methods. The importance of plotting and visualisation for decision support will be emphasised.
Lab sessions will begin with a general introduction to programming in Python using Jupyter Notebooks. We will introduce programming for students and the content will be covered sufficiently fast that we can reach a point where you will be able to apply this knowledge to your research at the end of the course, and we will not try to hide away the niggling details that you will encounter in real programming.
There will also be an opportunity for students to familiaries themselves with other data analytics software packages including Matlab, RStudio and Stata and Tableau.
Upon successful completion of the module, students will be able to:
- Understand computational thinking
- Be able to explore data and programme simple algorithms
- Evaluate computational approaches to data analytics problems
- Visualise data for business analytics
- Assess performance of algorithms
- Data types and structures
- Data preparation and exploratory data analysis
- Experimental methods
- Introduction to methods for large data sets
- Implementation of supervised learning algorithms
- Plotting, visualisation and decision support
- Implementation of unsupervised learning algorithms
- Performance, evaluation and overfitting
- Simple complexity and runtime analysis
The course has the following assessment components:
- 60% individual coursework;
- 40% group coursework
Current students should refer to Moodle for specific details of the current year’s assessment.
Data Science for Business: What you Need to Know about Data Mining and Data Analytic Thinking, T. Fawcett and F. Provost, O’Reilly, 201