Decision Scientist (Planning)

Purpose Statement

• Develop and maintain an accurate rolling 6- 48 months’ supply and demand forecast by analysing historical sales data, demand data, market trends and supply data, considering external factors that have the potential to cause shifts.
• Analyse operations channels performance data to identify opportunities for improvement, and work with other teams to implement process improvements that increase efficiency and improve client experience.
• Track headcount levels across the Capitec’ operations channels to ensure that there are enough resources to meet client demand while minimizing waste and maintaining service levels.
• Use data analytics and visualisation to identify demand and supply problems and empower business owners to make decisions that advance their business goals. Develop solutions and models to positively impact these.
• Track the impact of change drivers on workload and service levels.
• Monitor and report on important changes in demand drivers and business strategies. Propose and implement solutions to improve demand forecast accuracy.
• Simulate future demand and supply scenarios and inform decision making and business priorities.
• Prepare and facilitate month Sales and Operations Planning (S&OP) meetings.

Education (Minimum)

Education (Ideal or Preferred)

Knowledge and Experience

Minimum Knowledge and Experience:
Experience:

• Length of experience required is conditional on the qualifications obtained 
• Experience in statistical (predictive and classification) model development and deployment incl. traditional scoring (logistic regression with binning and missing value replacement e.g. reject inference), machine learning (neural networks, SVM, random forests etc.), and quantitative analysis (time value of money etc.)
• General business know-how: e.g. risk, compliance, operations e.g. NCR, POPIA, SARB
• Business analysis and requirements gathering
• Working in cloud environments e.g. Azure, AWS and large relational databases 
• Experience in at least one ML language (e.g. Python or SAS Viya) 
• Functional business area (e.g. Credit) environment knowledge and experience

Knowledge:

• Understanding of state of the art statistical (predictive and classification) model development and deployment principles and techniques incl. traditional scoring (logistic regression with binning and missing value replacement e.g. reject inference), machine learning (neural networks, SVM, random forests etc.), and quantitative analysis (time value of money etc.).
• Underlying theory and application of machine learning models; able to understand underlying principles and theory. 
• Best practices for decision science such as reusability, reproducibility, continuous monitoring, etc

Ideal Knowledge and Experience:

• Financial sector experience
• Working with multiple teams to deliver predictive models into a production environment
• Capitec Decision Science lifecycle 

Skills

Additional Information