Postgraduate Diploma in Data Science

Purpose

The Postgraduate Diploma in Data Science aims at growing local expertise through a work-integrated academic-practical infused diploma, to respond to the increasing business demand for skills in data science.

The choice of modules complements one another to form a coherent qualification with a focus on producing well-rounded professionals in Data Science. The curriculum emphasizes the development of learners with the attributes outlined in the outcomes through the way in which the modules are taught and assessed.

Rationale

The qualification aims to respond to industry needs by bridging the gap between academic training and business application. In a world where every type of job involves working with data, there is a challenge for academic degree holders from different educational backgrounds to turn overwhelming amounts of data into actionable insights for industries. Industries thus need an analytical skill enhancement qualification for such employees. Still, their employees themselves also need to enhance their analytical skills for their career development within the industry (or elsewhere). The industry thus looks to institutions of higher education to provide updated skills enhancement qualifications in data analytics.

Unfortunately, not all post-bachelor degree learners in Computer Science or related fields satisfy the prerequisite requirements to apply for entry into an honours degree or master's degree in Statistics or Data Science. Moreover, there is no work-integrated Data Science qualification to develop such bachelor degree holders in South Africa. This Postgraduate Diploma qualification is thus uniquely aimed at catering for such needs.

Learners will have an undergraduate degree with at least two years of data handling/management/analysis work experience. This module has an industry focus with particular emphasis being given to preparing the learner for data mining/analytics in the industry.

Recognition of Prior Learning (RPL)

The institution's RPL Policy will guide some admissions and learners who have attained a level of competence considered adequate by the institution's Senate will grant them access into postgraduate studies. Therefore, in line with this policy, the Discipline of Statistics will assess the level of competence of prospective learners through its internal structures before seeking the approval of the College Academic Affairs Board and the Senate for each learner.

Since all learners will have experience in the industry, RPL for access will be done based on a submission of a portfolio of evidence of their work experience in Data Analytics. The portfolio must show that the learner has sufficient disciplinary learning in the field of Data Analytics to qualify for access. A fundamental principle that must inform RPL practice is that learning outcomes must not be compromised as a result of RPL practice.

Entry Requirements

The minimum entry requirement for this qualification is

• Bachelor's degree in Computer Science or related field, NQF Level 7 with at least two years of industry data management experience.

This qualification consists of the following compulsory modules at NQF Level 8 totalling 128 Credits.

Compulsory Modules, Level 8, 128 Credits

• Applied Generalized Linear Model Analysis, 16 Credits.
• Time Series and Forecasting Econometrics, 16 Credits.
• Data Mining: Descriptive Analytics, 16 Credits.
• Applied Longitudinal and Geospatial Analysis, 16 Credits.
• Machine Learning and Predictive Modelling Techniques for Business, 16 Credits.
• Applied Binary Classification and Matching, 16 Credits.
• Industry Project, 32 Credits.

1. Collect, explore and analyse industry, business and government data using relevant statistical techniques.
2. Demonstrate an understanding of the theories, research methodologies, methods and techniques in data science relevant to the field; and an understanding of how to apply such knowledge.
3. Derive and effectively communicate actionable insights from a vast quantity and variety of data.
4. Tackle genuine problems with data provided by industry and government sponsors using industry-standard tools and in so-doing prove their ability to solve problems, through the use of statistical packages.
5. Identify, analyse and address complex and abstract problems and produce papers or presentations/ seminars on their findings.
6. Demonstrate that they have developed into skilled, productive individuals, with a strong personal and work ethic, and a desire to contribute towards and effect change in the community and wider work environment.
7. Demonstrate the ability to identify and address ethical issues based on critical reflection on the suitability of different ethical value systems.
8. Demonstrate a profound knowledge and understanding of the GLM techniques.
9. Demonstrate an appreciation for and understanding of the theory and application of time series and econometric techniques to business data.
10. Demonstrate an understanding of the process of data mining, starting with descriptive analytics using SAS, Excel and other software.
11. Understand both theoretical and practical concepts of Longitudinal and Geospatial Analysis.
12. Demonstrate an appreciation for and understanding of the theory and application of machine learning and predictive modelling techniques to business/industry practices.
13. Demonstrate a marketplace- based understanding of the terminology being used in data classification and matching, and in the customer-service industry.

Associated Assessment Criteria for Exit Level Outcome 1

• Apply fundamental and specialist knowledge in data collection, exploration and analysis to solve industry/business and government problems.
• Communicate concepts, ideas using visual analytics.
• Select and use appropriate exploration and analysis tools for the data at hand.

Associated Assessment Criteria for Exit Level Outcome 2

• Apply statistical theories and methods by solving business/industry problems.
• Use techniques, principles and methods in at least one first hand industrial/business problem.

Associated Assessment Criteria for Exit Level Outcome 3

• Communicate concepts, ideas and theories with the aid of visual analytics and oral presentations.
• Derive actionable insights from vast quantities and variety of data.

Associated Assessment Criteria for Exit Level Outcome 4

• Apply data visualizations at a deeper level to identify weaknesses, trends, or opportunities for industry.
• Use industry data and exploration tools to identify problems and propose solutions.
• Design and maintain data systems, databases; analytic tools; programming, and fix coding errors.
• Select and use appropriate exploration and analysis tools for the data at hand.

Associated Assessment Criteria for Exit Level Outcome 5

• Apply statistical tools to interpret data sets, by paying particular attention to the peculiarity in the data that adds value to the industry.
• Communicate findings to relevant stakeholders.

Associated Assessment Criteria for Exit Level Outcome 6

• Take personal responsibility and be accountable for actions in the workplace, such as effective work (for example, punctuality, keeping to deadlines and time/workload management).
• Make responsible decisions that consider the interests of the larger community.
• Assume responsibility when mistakes are made and learn from them in future situations.
• Apply principles of data privacy and security in their practice

Associated Assessment Criteria for Exit Level Outcome 7

• Apply ethics in professional practice.
• Identify different value systems in different contexts
• Communicate in language appropriate for the work environment.

Associated Assessment Criteria for Exit Level Outcome 8

• Apply GLM methods in industry, including problem design, data analysis, and interpretation.
• Identify industry problems, and develop GLM-based solutions.

Associated Assessment Criteria for Exit Level Outcome 9

• Discuss and elaborate on univariate time series modelling/testing techniques.
• Undertake an econometric analysis using professional conventions.
• Obtain appropriate industry data and model them appropriately using the software package.

Associated Assessment Criteria for Exit Level Outcome 10

• Mine data from primary and secondary sources.
• Reorganise said data in a format that can be easily read by either human or machine.

Associated Assessment Criteria for Exit Level Outcome 11

• Apply knowledge of geospatial data mining and mapping using a wide range of geospatial data visualization methods and quantitative analysis of geospatial phenomena.

Associated Assessment Criteria for Exit Level Outcome 12

• Use statistical tools to interpret data sets, paying particular attention to trends and patterns that could be valuable for diagnostic and predictive analytics efforts.

Associated Assessment Criteria for Exit Level Outcome 13

• Use statistical methods to solve general customer classification and matching problems in industry.
• Integrate theoretical knowledge in preparing data files for classification analysis
• Compile a report on the findings.

Integrated Assessment

Learners will be assessed on all six taught modules and the Industry project module. The taught modules will be assessed through assignments, practical exercises and class presentations, well as examinations. Exercise and presentations may be formative or summative.

In five of the modules, the examination comprises 50% of the assessment and in the sixth module the examination comprises 60% of the examination. The seventh module, a completed industry project, shall be assessed based on the report as well as an oral presentation. The guidelines provided in the policy will be adhered to in the assessment across the qualification.