Quantitative Analyst at Capitec Bank

As a Quantitative Analyst specialising in Machine Learning & Data Science you will develop, implement, monitor, and enhance machine learning and advanced analytical models that support strategic decision-making across the Bank. You will apply statistical and machine learning techniques to solve business problems, generate insights from large datasets, and contribute to the development of data-driven products, risk strategies, and customer solutions.


What you'll be doing


Develop and maintain machine learning, predictive, and statistical models to address business challenges.
Analyse large datasets to identify trends, patterns, risks, and opportunities.
Perform data extraction, preparation, cleansing, and feature engineering activities.
Apply machine learning techniques including:
Decision Trees
Random Forest
XGBoost
Classification Models
Regression Models
Clustering Techniques
Evaluate model performance and recommend enhancements.
Support model deployment and production monitoring activities.
Conduct model testing and performance validation.
Develop analytical reports, dashboards, and data visualisations.
Collaborate with stakeholders to translate business problems into analytical solutions.
Contribute to model documentation, governance, and audit requirements.
Stay current with developments in machine learning, artificial intelligence, and advanced analytics.


Experience
Minimum:


2 to 4 years' experience in a quantitative, data science, machine learning, or advanced analytics role.
Experience developing, testing, and deploying analytical or machine learning models.
Experience working with large and complex datasets using Python and SQL.


Ideal:


Experience within banking, financial services, fintech, telecommunications, or a highly data-driven environment.
Exposure to credit risk, customer analytics, propensity modelling, fraud analytics, or financial crime analytics.


Knowledge
Essential:


Strong Python programming skills.
Strong SQL querying and data manipulation skills.
Understanding of machine learning methodologies and model evaluation techniques.
Statistical analysis and hypothesis testing.
Data wrangling and feature engineering.
Ability to work with structured and unstructured datasets.
Data storytelling and presentation skills.
Strong analytical and problem-solving abilities.


Preferred:
Exposure to:


TensorFlow
PyTorch
Databricks
AWS, Azure, or GCP
MLOps principles
Credit Risk Modelling
Fraud Analytics
Financial Crime Analytics


Location


Stellenbosch AND Sandton based will be accepted


Conditions of Employment


Clear criminal and credit record