Overview
Data Scientist Jobs in Cape Town, Western Cape, South Africa at GoTyme Bank
Title: Data Scientist
Company: GoTyme Bank
Location: Cape Town, Western Cape, South Africa
GoTyme MCA (SA): The Data Scientist will play a pivotal role in assessing, analyzing, and mitigating credit risk within the GoTyme MCA (SA) Credit Analytics team. Working end-to-end—from data exploration and feature engineering to production-ready models, monitoring, and experimentation—the role leverages data-driven insights to enhance credit decisioning, optimize portfolio performance, and support the continued growth of the Merchant Cash Advance (MCA) product.
Requirements
Required Competencies and Skills
Essential
- Strong background in statistical modelling, machine learning, and predictive analytics
- Proficiency in Python and/or SQL
- Experience building and validating credit risk models, including scorecards and provisioning models
- Solid grounding in predictive model evaluation — ranking performance, calibration, and stability — and business impact measurement
- Exposure to advanced machine learning concepts (ensemble methods, cross-validation, hyperparameter tuning) and the ability to apply them responsibly in production settings
- Strong business acumen with the ability to communicate insights to both technical and non-technical stakeholders
- Curious and pragmatic, focused on measurable outcomes; comfortable working in detail and iterating quickly while maintaining quality
- Collaborative and able to work across markets and time zones
Desirable
- Experience in SME lending, merchant cash advances, or alternative credit products
- Familiarity with IFRS 9, Basel, or equivalent credit risk regulatory frameworks
- Experience with bureau data, open banking/transactional data, device/behavioural signals, or alternative data sources
- Exposure to cloud-based data platforms (Databricks, BigQuery, Snowflake, AWS, GCP, or Azure) and version control (Git/Bitbucket)
- Familiarity with model monitoring, governance, and documentation practices in regulated environments
Qualifications
- Degree in Data Science, Statistics, Mathematics, or a related quantitative field
- Professional Qualification and/or Regulatory, Licensing requirements (if any)
- None mandated, though familiarity with SARB credit risk guidelines and IFRS 9 is advantageous
- Relevant Work Experience
- 3+ years of experience in data science, credit analytics, or credit risk management within a bank, fintech, lender, or consulting environment
Key Responsibilities
Credit Risk Modelling
- Develop, implement, and maintain acquisition scorecards and models to evaluate MCA applicants
- Build and iterate credit risk features and model inputs (behavioural signals, affordability proxies, stability-tested transformations), partnering closely with senior modellers and engineering
- Contribute to the development and improvement of predictive models using modern machine learning approaches, with a focus on robustness, stability, and deployability
- Monitor provision models aligned with regulatory and accounting standards
- Enhance portfolio monitoring tools and dashboards to track credit performance and early warning signals, including drift, stability, segment performance, and data quality checks
Data Analysis & Insights
- Analyse customer, transactional, repayment, and business health data to identify drivers of risk, loss, approval rates, and customer outcomes
- Identify trends, correlations, and anomalies that impact take up rate, credit performance and portfolio stability
- Support portfolio analytics: vintage analysis, roll-rates, migration, early warning indicators, collections funnel analytics, and loss driver deep-dives
- Collaborate with product, finance, and operations teams to embed data-driven decision-making.
Credit Policy & Experimentation
- Design, run, and evaluate credit policy experiments (cut-offs, limits, pricing/risk trade-offs, segment strategies), including post-implementation reviews
- Develop segmentation and behavioural models to drive proactive portfolio management
- Support stress testing and scenario analysis
Innovation & Automation
- Design and deploy machine learning models for predictive credit risk assessment
- Leverage advanced analytics to streamline underwriting and risk monitoring processes
- Continuously explore new data sources and analytical methods to improve risk evaluation
- Work with Data/Engineering to improve data definitions, quality, lineage, and reproducible pipelines; document feature logic and assumptions
Governance & Documentation
- Contribute to governance documentation including model inputs, feature catalogues, monitoring evidence, and change logs
- Ensure all modelling work meets internal standards and applicable regulatory requirements