Head of Data - Financial Services
Company Name - Omni
Location: Lagos, Nigeria
Reports to: Head of Data (who reports to the Head of Business Excellence)
Direct reports: Data Engineers, Data Analysts, Data Scientists
Employment type: Full-time, senior leadership
1. Company overview :
Omni operates a B2B commerce and financial services platform serving the FMCG value chain in Nigeria - manufacturers, distributors, stock points, and a Customer Network of retailers, HoReCa outlets and modern trade stores.
Omni Financial Services provides this network with payments and collections (wallet, POS, cards), lending, value chain financing, inventory and asset financing, and CASA/savings products. Because the platform sees every customer's daily trading activity - orders, stock movement, wallet flows, repayments - Omni can extend credit and financial services to businesses that traditional banks cannot underwrite.
2. Position summary :
The Head of Data - Financial Services owns the data strategy, governance, analytics and model development for Omni's financial services business, and is accountable for seeing every model and data product through to deployment and stable operation in production. The role leads a multidisciplinary team of data engineers, analysts and data scientists across five areas of responsibility: data strategy and governance; credit risk and model development; growth analytics; fraud, anomaly detection and control using early warning signals; and team leadership.
The role holder is measured on business outcomes - lower non-performing assets, higher customer acquisition and product adoption, faster data-led and automated decisions, and fewer fraud and anomaly losses - while ensuring the data function meets the standards expected of a regulated financial institution.
3. Key responsibilities :
1. Data strategy and governance :
- Define and execute the FS data strategy and roadmap, aligned to lending, payments and savings targets, and deliver it as production-ready data products rather than analyses
- Establish and enforce data governance: data ownership, quality standards, master data, lineage, retention, access control and audit readiness
- Implement data policies for customer data protection, consent, privacy and regulatory compliance (NDPR and applicable CBN guidelines)
- Own the FS data architecture on Snowflake - domain models for customer, ledger, loan, repayment, wallet, POS and agent - and the reliability, monitoring and cost of the pipelines feeding reporting, models and decision systems
- Deliver decision-grade reporting on portfolio health, collections, product economics and acquisition, and advise executive leadership on credit appetite, pricing and growth based on the evidence
2. Credit risk and model development :
- Lead the development, validation, deployment and monitoring of credit scoring, affordability, limit-setting, DPD / roll-rate, behavioural and collections models, and PD / LGD / EAD estimates for every FS product
- Ensure models are deployed into production decisioning - via APIs and decision engines with explainability, override capture and human-in-the-loop controls - so that credit approvals, limit reviews and collections prioritisation run automated, auditable and fast
- Establish model risk management in line with global banking practice: documentation, independent validation, back-testing, champion/challenger, performance and drift monitoring, and scheduled recalibration
- Partner with FS Risk and Credit Policy on risk appetite, cut-offs, exposure limits and portfolio stress testing
- Set standards for responsible AI: fairness, bias testing and monitoring of automated credit decisions
3. Growth analytics :
- Build and deploy propensity, cross-sell, churn and next-best-offer models across wallet, POS, lending, financing and savings, integrated into agent tools and in-app journeys
- Own customer segmentation across distributors, retailers, HoReCa and modern trade, and keep it operational for Product, Commercial and the agency acquisition network
- Provide funnel and conversion analytics for the agency distribution model and digital onboarding, run controlled experiments, and measure uplift and revenue impact of every data-driven intervention
- Advise Product and Commercial on segment-level economics - where to expand, what to price, and which products to lead with
4. Fraud, anomaly detection and control using early warning signals :
- Own the Early Warning Signals (EWS) engine - signal catalogue, pillar weighting, threshold calibration and the WATCH / WARN / ACT feedback loop with Risk and Collections - and keep it deployed and recalibrated against actual loan-book outcomes
- Design and operate anomaly and fraud detection across transactions, repayments, loyalty schemes and agent activity - collusion, ghost outlets, round-tripping, first-payment default patterns and data integrity faults
- Establish alerting, case investigation and resolution workflows with Risk, Operations and the field team, with time-to-detection and time-to-resolution tracked
- Own automated reconciliation and control reporting between ledger, wallet, POS and core systems
- Embed AI-driven screening into onboarding, disbursement and repayment flows to stop losses before they occur
5. Team leadership :
- Lead, coach and develop the data team; set objectives, manage performance and hire against capability gaps
- Operate a skill-based levelling and succession framework for Data Engineer, Data Analyst and Data Scientist tracks
- Establish engineering and delivery standards - code review, version control, testing, orchestration, MLOps, documentation and cost management - so that what the team builds reaches production and stays there
- Build a culture where the team owns business outcomes, not just models and dashboards
4. Key performance indicators and deliverables :
- Area: Data strategy and governance | Deliverables in production: Approved FS data strategy and roadmap; governance and data-protection policies enforced; Snowflake FS domain model live; executive portfolio and collections reporting | Business KPIs: Data quality SLA >=98%; pipeline on-time >=99%; zero overdue audit findings; warehouse cost per transaction down; roadmap delivery >=85%
- Area: Credit risk and model development | Deliverables in production: Application and behavioural scorecards, DPD / roll-rate and PD / LGD / EAD models deployed via decision API; model risk management framework with all models validated | Business KPIs: Reduction in NPA / PAR; delinquency in scored cohorts vs. baseline; Gini >=0.45 and PSI <0.10; straight-through processing rate; decision turnaround time; override rate <10%
- Area: Growth analytics | Deliverables in production: Propensity / NBO models live in agent tools and app; operational segmentation adopted; agency funnel analytics | Business KPIs: Active FS customer growth; onboarding-to-first-transaction conversion; NBO uplift vs. control >=1.5x; cross-sell ratio; wallet / POS penetration
- Area: Fraud, anomaly detection and EWS | Deliverables in production: EWS engine recalibrated and live; anomaly detection across transactions, repayments, loyalty and agents; case-management workflow; automated reconciliation | Business KPIs: Fraud loss rate; % of fraud detected pre-loss; EWS recall >=70%; time-to-detection <24h; time-to-resolution <5 days; reconciliation break rate <0.5%
- Area: Team leadership | Deliverables in production: Career and succession framework in operation; engineering and MLOps standards adopted; capability coverage across critical skills | Business KPIs: Team retention; framework adoption 100%; stakeholder satisfaction >=4/5
5. Qualifications and experience :
- Bachelor's degree in Statistics, Mathematics, Computer Science, Engineering, Economics or a related quantitative field; Master's degree preferred
- 5+ years in data science, analytics or data engineering, including 3+ years leading a multidisciplinary data team in banking, lending or fintech
- Proven experience building and deploying credit risk models (application and behavioural scoring, PD/LGD/EAD, early-warning systems) on transactional and alternative data
- Demonstrated delivery of propensity, cross-sell and churn models and customer segmentation from financial transaction data, with measured revenue impact
- Experience designing and running fraud and anomaly detection on payments, lending or loyalty data
- Working knowledge of model risk management, data governance and regulatory expectations in financial services
- Experience implementing AI/ML-driven automation in credit or operations processes
- Experience in SME, retail or informal-sector lending in Africa or comparable emerging markets is an advantage
- Professional certifications (e.g. FRM, CQF, cloud or Snowflake certifications) are an advantage
6. Technical skills :
Required:
- SQL - expert; complex analytical queries, data modelling, performance tuning
- Python - expert; pandas, NumPy, scikit-learn, statsmodels; production-quality code
- Snowflake - data warehouse design, security and access control, cost management, integration with BI and ML tools
- Power BI - data modelling, DAX, governed datasets and executive reporting
- Big data / PySpark - distributed data processing and feature engineering on large transaction datasets
- Machine learning - supervised and unsupervised methods, gradient boosting, time series, anomaly detection; model validation and monitoring
- Data engineering - ELT pipelines, orchestration (Airflow or equivalent), dbt or similar, data quality frameworks, CI/CD for data
- MLOps - model deployment, versioning, monitoring, drift detection, experiment tracking
- Cloud platforms - AWS, Azure or GCP data services
- Decision automation - exposing models via APIs / decision engines, rules and workflow integration
Desirable:
- Graph analytics for network and collusion fraud
- LLM and generative AI applications in analytics and operations
- Real-time / streaming data (Kafka or similar)
- Embedded analytics tools (e.g. ThoughtSpot)
- Credit bureau, KYC and payment-switch data integration
7. Core competencies :
- Strategic thinking with strong commercial judgement
- Ability to translate complex analysis into clear recommendations for senior leadership
- Hands-on technical leadership - sets standards and can review and debug the team's work
- Strong stakeholder management across Risk, Product, Commercial, Operations and Engineering
- High integrity in handling customer data and credit decisions
- Comfort with ambiguity and imperfect field-collected data
8. Key relationships :
FS Risk, Credit Policy and Collections - FS Product and Commercial - Platform Engineering - Field Operations and agency network - Finance - Compliance
Omni is an equal opportunity employer.
Didn’t find the job appropriate? Report this Job
