Our client in the Banking industry is looking for a Snr Data Scientist that will join their team in Sandton.
Role Purpose
To plan, build, optimise and implement innovative quantitative analytical methodologies, procedures, products and advanced mathematical models that provide analytical support and interpret insights, using advanced analytics technologies, to address business opportunities and problems and implement business strategy.
Responsibilities
• Prevent wastage and identify process improvements to contain and reduce costs
• Assess own performance through seeking timely and clear feedback and request training where appropriate
• Utilise, refine and enhance advanced statistical models and data analysis to inform decision making and address business needs
• Develop and implement advanced statistical models and data analysis to optimise processes, inform strategic decisions and meet current and future business requirements, reduce risk and generate profits
• Deliver value add outputs across the analytics value chain in delivery of business strategy
• Implement localised Analytics strategy to address business needs
• Utilise advanced analytics technologies, program own statistical model and apply advanced data modelling methodologies that inform future fit strategic decisions and test current assumptions
• Develop, encourage and nurture collaborative relationships within Company and/or across the Company
• Develop new insights into situations and apply innovative solutions to make organisational improvements
• Focus on providing optimal services and improving service delivery processes to meet or exceed customer expectations
• Contribute to the development of a budget aligned to operational delivery plans, monitor effectiveness and report on variances.
• Ensure compliance to legislative and audit requirements and adherence to relevant processes
• Build working relationships across teams and functional lines to enhance work delivery, collaboration and innovation

Additional Requirements

Machine Learning Knowledge:
• Data Cleaning and Exploration
• Feature Selection Methods
• Feature Engineering
• Unsupervised Methods (Clustering & Topic Modelling)
• Supervised Methods (Regression & Classification)
• Model Performance Evaluation
Hands-on Experience with:
• SQL
• Python – specifically the following Machine Learning libraries:
• Pytorch
• TensorFlow
• Keras
• Spacy
• Huggingface
Personal skills:
• Communication: Must be able to communicate findings to stakeholders in a concise and understandable way.
• Adaptable: Must be able to adapt methodologies to conform to available data and resources.
• Planning: Must be able to commit to deadlines and to plan accordingly.
• Collaboration: Must be able to work as part of a team.
Qualifications and Experience
Minimum Qualification – B Degree Maths, Stats, Engineering, Computer Science, Econometrics, Physics or Actuarial Science
Preferred Qualification – Honours Degree
Experience – 3 – 5 years’ experience in a data environment, of which 1 – 2 years ideally at a at junior (entry level) management level
Additional Knowledge – Deep domain knowledge with regards to financial services: Credit, Pricing, Marketing, CVM, Trading etc.
• Design thinking
• Analytics Ops, Agile and SAFe concepts will assist
• Concepts such as: Exploratory data analysis, Data Science Pipeline lines
• Hands on experience using model such as: Naïve Bayes, Support Vector Machines, Classifications, Boosting Algorithms, Time Series, Feature Engineering and
• Dimensionality Reduction
• Data and Information Management topics e.g. structure, dimensions, storage
• Object-oriented programming
• Big data modelling
• Database management
• Python, SQL, MATLAB, SAS, S-PLUS or R (used for statistical analysis)
• Monte Carlo techniques
• Machine learning
• Data mining and data modelling
• C++ (used for high-frequency trading applications)
• Scala and Spark
• C#/Java, .NET or VBA, Excel
• Mathematical skills
• Calculus (including differential, integral and stochastic)
• Linear algebra and differential equations
• Numerical linear algebra
• Probability and statistics
• Game theory
• Portfolio theory
• Equity and interest rate derivatives, including exotics
• Systematic and discretionary trading practices
• Credit-risk products
• Financial modelling
• Data visualisation and reporting