Data Scientist - Fraud Analytics Models (Public Sector)
First seen by Alion on Oct 28, 2026.
- 1-year contract, renewable
- Government project
- Hybrid work arrangement
Role Overview
The Data Scientist will join the Fraud Analytics Models (FAM) team within the Data Science and AI Division (DSAD). The role supports the maintenance and expansion of FAM 2.0, which detects misuse of public training grants.
Key priorities include addressing the backlog of methodology and threshold reviews, building and operationalising the FAM 2.0 Technical Dashboard, and assessing how new schemes can be progressively included in FAM 2.0’s fraud-risk coverage.
The successful candidate will contribute to reliable fraud-risk analytics, clear methodologies and sustainable implementation, while helping build DSAD’s in-house capability.
Key Responsibilities
Methodology and threshold reviews: Review and recalibrate FAM 2.0 methodologies and thresholds for prioritised backlog items. This includes back-testing, impact assessment, analytical specifications, validation approaches, gap analyses and documentation.
Risk model enhancement: Translate business, policy and scheme requirements into changes to fraud-risk scenarios, indicators, features, thresholds and analytical logic.
Technical Dashboard development: Build and enhance monitoring of model performance, including precision and recall, data drift and concept drift. Develop alert logic and visualisations, and support deployment. Design performance measures that account for delayed or incomplete investigation outcomes.
New scheme assessment: Assess new schemes’ structures, eligibility rules, claims processes and known fraud risks. Map relevant patterns to the existing FAM 2.0 risk taxonomy and recommend how each scheme can be brought into coverage.
Governance and stakeholder engagement: Maintain clear methodology and change records. Communicate findings, trade-offs, dependencies and recommended actions to programme owners, FAM stakeholders, engineers and management.
Documentation and knowledge transfer: Produce reproducible code, analyses and documentation throughout the engagement.
Requirements and Qualifications
Education and ExperienceEducation: Degree in Data Science, Statistics, Mathematics, Computer Science, Engineering, Economics or a related quantitative discipline.
Experience: 3–5 years of hands-on experience in data science, advanced analytics, model validation, fraud or risk analytics, or programme analytics.
Strong hands-on proficiency in Python and SQL for data extraction, transformation and exploratory analysis, with experience building reproducible analytical workflows.
Hands-on experience developing, validating or enhancing predictive, risk-scoring, fraud-detection or anomaly-detection models. This includes feature development, back-testing, threshold calibration and performance evaluation using measures such as precision and recall.
Experience translating business, policy or operational requirements into analytical specifications, model logic, indicators, rules or measurable risk hypotheses.
Experience working with complex, large-scale datasets, including assessing data quality, tracing data lineage, investigating anomalies and documenting analytical assumptions.
Experience addressing technical challenges in fraud or risk modelling, including imbalanced data and delayed, incomplete or evolving outcome labels.
Experience designing or implementing production model-monitoring approaches, including data drift, concept drift and alert thresholds.
Experience building analytical dashboards using Tableau or an equivalent platform.
Experience with CI/CD, MLOps controls or the operational deployment of analytical models.
Experience with Spark or PySpark and enterprise data platforms, particularly AWS Redshift and AWS Glue.
Experience with network or graph analytics to identify related entities or coordinated patterns.
Experience working with workforce, training, grants, claims or regulatory datasets.
Prior experience in Singapore public-sector engagements or familiarity with government data-classification requirements.
Strong analytical and structured problem-solving skills, with a rigorous and detail-oriented approach.
Ability to turn ambiguous requirements into clear assessment, methodology and implementation phases.
Clear written and verbal communication, including the ability to explain technical findings and trade-offs to non-technical stakeholders.
Ability to integrate quickly into an existing team, working independently while collaborating across data science, engineering, platform, programme and business teams.
Proactive management of delivery risks, dependencies and competing business-as-usual and enhancement priorities.
/Ref: 308
Skills
Validation, validation strategies, Dashboard Construction, Oracle Alerts, Operational Requirements, Technical Skills, Risk Modeling, Science and Math, Workflow Analysis, Computer Science, Fraud Analytics, Calibration Management, Backlog Management, Data Science, Education, Fraud Risk Management, Performance Monitoring