Data Science for Business
Overview
This unit provides students with a practical foundation in contemporary data science techniques used in industry, using Python. It offers a hands-on introduction to programming paradigms and fundamental techniques for financial data analysis. Key topics include data cleaning and validation, data transformation, algorithm design, text analytics, and data visualisation. Real-world case studies and datasets from finance and economics will be used to illustrate how data science supports decision-making and market analysis. Students will gain hands-on experience with widely used Python libraries such as Pandas, Matplotlib, and the Natural Language Toolkit (NLTK).
Requisites
31-May-2026
Learning outcomes
Students who successfully complete this unit will be able to:
- Apply coherent and advanced knowledge of how to read, clean, and manipulate data sets.
- Critically evaluate existing toolkits, and learn how to construct custom algorithms when necessary.
- Identify research questions and create project outlines that use data science to support decision making process
- Analyse data sets using statistical techniques, visualisations, regression analysis, and text analytics to derive insights and support data-driven financial decision-making
Teaching methods
Hawthorn
| Type | Hours per week | Number of weeks | Total (number of hours) |
|---|---|---|---|
| On-campus Class |
3.00 | 12 weeks | 12 |
| Unspecified Activities Various |
9.5 | 12 weeks | 114 |
| TOTAL | 150 |
Assessment
| Type | Task | Weighting | ULO's |
|---|---|---|---|
| Assignment 1 | Individual | 40-60% | 1,2,4 |
| Assignment 2 | Individual | 40-60% | 1,2,3,4 |
Content
- Basic programming theory
- Data science best practices
- Data structures, access and usage
- Data cleaning and validation
- Data Visualisation
- How to validate results
- Working with Text data (Text Analysis)
- Data science tools
Study resources
Reading materials
A list of reading materials and/or required textbooks will be available in the Unit Outline on Canvas.