Senior Data Scientist

As a Senior Data Scientist, you will play a pivotal role in assessing, analysing, and mitigating credit risks within the MCA Credit Analytics team at GoTyme. You will be responsible for overseeing and completing the full model development cycle, from extracting data through to presenting findings to relevant stakeholders. Working end-to-end from data exploration through to production-aligned features and monitoring, you will use data, feature engineering, and experimentation to improve credit decisioning and portfolio performance for our Merchant Cash Advance product. This position requires a keen understanding of data and modelling standards, credit scoring principles, and machine learning techniques. The role is also accountable for ensuring that models are appropriately governed, validated, deployed, monitored, and reviewed throughout their lifecycle, with strong controls over data quality, implementation accuracy, and ongoing model performance. You will provide guidance and mentorship to junior team members and contribute to the strategic direction of the portfolio.

Credit Risk Modelling

• Lead the development, implementation, and maintenance of acquisition scorecards and models across the credit lifecycle to evaluate MCA applicants.
• Own and drive credit risk feature engineering and model inputs (behavioural signals, affordability proxies, stability-tested transformations), providing technical direction to the team and partnering with data engineering.
• Lead the development and improvement of predictive models using modern machine learning approaches, with a focus on robustness, stability, and deployability. Oversee and participate in model development, review, and maintenance activities.
• 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.
• Develop and lead stress testing scenarios and sensitivity analyses to assess the resilience of the MCA portfolio under various economic conditions.

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

• Ensure that all data science models are developed, reviewed, documented, and governed in line with model risk management standards for governance forums and periodic model reviews. Lead governance documentation including model inputs, feature catalogues, monitoring evidence, and change logs.
• Ensure all modelling work meets internal standards and applicable BSP regulatory requirements, including IFRS 9 principles and ECL methodologies where applicable. Support independent model validation activities by providing clear development documentation, data definitions, assumptions, limitations, and performance results. Work with data engineering and technology teams to support the deployment of models and decisioning logic into production environments, ensuring implementation testing is completed and model outputs are reconciled. Prepare and present reports to senior management, highlighting key risk metrics, trends, and recommendations. Provide guidance and mentorship to junior team members, fostering a culture of continuous learning within the team.

Key Performance Indicators (KPIs)

• Model Quality: Scorecard Gini/KS performance; stability metrics (PSI); calibration accuracy
• Portfolio Health: Early warning indicator accuracy; vintage performance vs. expectations
• Monitoring and Governance: Timeliness and completeness of model monitoring reports; governance documentation currency
• Experimentation: Number of policy experiments executed and reviewed; measurable improvement in risk-adjusted approval rates
• Data Quality: Reduction in data quality issues; pipeline reliability
• Stakeholder Collaboration: Timely delivery of analytical insights to credit risk, product, and finance teams