Masters in Statistical Science (with Specialisation in Data Science)On 28 March 2018, the Statistics and Population Studies Department at UWC in collaboration with the Centre for Business, Mathematics and Informatics (BMI) at Northwest University (NWU), launched an industry directed one-year Master’s programme in Statistical Science with specialisation in Data Science. Funding to launch this joint programme was provided by Sanlam and SAS® provided the needed specialised software to help us train the students. As part of the training, students do an internship at a company during the second semester which forms the basis of their industry directed research thesis. The Department of Statistics and Population Studies staff joined forces with the NWU lecturers to make this unique training opportunity a great success.
NEW FROM 2021!
We recently received new funding from Imvelo Ventures a Venture Capital investment company founded by Capitec Bank (www.capitecbank.co.za) and Empowerment Capital Investment Partners (www.empowerment.capital) to support students and further develop and expand our Data Science programmes. Bursaries will be offered to the top deserving honours and masters students in our Statistical/Data Science programmes. The bursary recipients will be identified by the academic team and selected in collaboration with Imvelo Ventures.
The link to the Data Science brochure: Click Here
For more information about this new and exciting Data Science programme that spans a bridge from academia to industry, contact Prof Rénette Blignaut (firstname.lastname@example.org) from the Department of Statistics and Population Studies or her colleagues Dr Julia Keddie, Dr Retha Luus, Dr Humphrey Brydon, Mrs Leonor Bosman and Mrs Rechelle Jacobs. The team is strengthened by the well-known Prof Machiel Kruger and Prof Sarel Steel. This team has worked diligently and enthusiastically to get the Data Science programme off the ground in record time.
See all international SAS accredited master’s programmes: Click Here
What do our 2022 students say about our Data Science master’s programme:
Sem Kalobo: https://vimeo.com/748685630
Buhle Kuse: https://vimeo.com/748656324
Brent Eachells: https://vimeo.com/748656187
Dionah Tshabalala: https://youtu.be/Q64Bq_4XP9M
Mogamat-Yushly Collop: https://youtu.be/GnoD5BD6cL4
Samuel Mubenga: https://youtu.be/I44md3AYPBw"
Admission requirements for the MSc in Statistical Science (with specialisation in Data Science)
- Honours degree or equivalent in Statistical or Computer Science.
During the final selection process preference will be given to applicants who have completed:
- Third-year level Statistics;
- Second-year level Mathematics;
- Advanced Statistical Learning or Machine Learning; and
- Programming skills.
|STA841||BUSINESS INTELLIGENCE 841||Semester 1||15.00|
|STA842||CONTEMPORARY ISSUES IN BUSINESS ANALYSIS 842||Semester 1||15.00|
|COF827||FINANCIAL RISK MANAGEMENT||Semester 1||15.00|
|STA843||MULTICRITERIA DECISION MAKING 843||Semester 1||15.00|
|STA810||RESEARCH METHODOLOGY 810||Semester 1||15.00|
|STA800||DATA MINING II 800||Semester 2||15.00|
|STA839||RESEARCH PROJECT 839 (students spend 3 days per week at industry partner office)||Semester 2||90.00|
- Business Intelligence, including framework design and architecture and the mastering of data management.
- Database fundamentals and warehouses.
- Dimensional modelling (building blocks of data models)
- Relational databases.
- SAS macros; SAS SQL; SAS OLAP cubes.
- Pivot tables in MS Excel.
- SAS Enterprise Guide.
- Calculate marketing metrics, such as traditional customer metrics, customer acquisition metrics, customer activity metrics, value metrics, etc.
- Conduct recency, frequency, monetary-value (RFM) segmentation.
- Understand customer lifetime value (CLV), such as past customer value, formulate CLV, understand and apply retention and migration CLV models, etc.
- Analytical customer relationship modelling (CRM) techniques to manage customers, such as customer acquisition and costs, customer retention – cross selling and up-selling, balancing acquisition and retention, customer churn prediction and reduction to churn.
- Extensions of the RFM model.
- Estimate revenue streams.
- Data ethics
- Critical understanding and development of predictive models (i.e. scorecards) in the field of retail credit risk.
- Employ supervised and unsupervised learning methods.
- Specialised knowledge with regards to the use of logistic regression as a supervised method in the field of retail credit risk.
- Credit risk management.
- Design and develop scorecards to solve problems in the field of retail credit risk.
- Unsupervised methods such as clustering used for scorecard development.
- Conduct research according to standard protocol and employ appropriate protocols, conventions, processes,
- procedures and techniques to solve problems in the field of credit risk.
- The ability to identify, select, apply, interpret, and critically judge the appropriateness of a range of mathematical programming formulations in solving complex optimisation problems relevant in finance.
- Use the designated software package to capture the mathematical models associated with a specific problem, apply suitable optimisation algorithms to find solutions, and select the most effective course of action based on a critical assessment of the results.
- Study the correct use of terminology appropriate to the field of multicriteria decision making.
- Practical project management, such as formulation, planning, scheduling, costing, scoping, execution and monitoring, documenting and presenting results.
- Critical path analysis.
- Identify, formulate and solve business problems using quantitative and qualitative tools.
- Demonstrate creative insight, rigorous interpretation of solutions with the development of technical writing skills.
- Manage project from conception to execution.
- Meeting management and etiquette (agendas, minutes, meeting documentation packs, group work, and professionalism).
- Write proposals and effectively document project results.
- Effective listening skills development.
- Data preparation, such as transformations and the incorporation of non-numeric data.
- Data mining principals and models.
- Conceptually design and develop data mining models.
- Variable selection, categorical input consolidation.
- Analysis of decision trees, regression analyses and neural networks.
- Model assessment and implementation.
- Pattern discovery and cluster analysis.
- Ensemble and surrogate modelling.
- The use of high-performance distributed computing.
- Apply random forests, bagging, boosting.
- Integrated knowledge and understanding of practical project management, such as formulation, planning, scheduling and costing of the project, the determination of a base line, the execution and monitoring of the project, documentation and the presentation of the results, etc.
- Identify, formulate and solve business problems using appropriate qualitative and quantitative tools.
- Effectively present and communicate, orally and in writing, relevant academic and professional information – including creative insight, rigorous interpretations, and solutions to problems – to a range of audiences with the use of appropriate technology.
- Operate independently and take full responsibility for his or her own work. Individually manage a project from conception to execution.
- Effectively manage meetings through tools such as meeting agendas, minutes and meeting document packs. Demonstrate high levels of autonomy and initiative in research and professional conduct.
MSc Statistical Sciences (with Specialisation in Data Science)
For more information contact:Prof. Rénette Blignaut
Tel: (+27) 21 959 3024/2