← Todos los empleosData Scientist
Middle8000 SGD · periodo no indicadoSingapore, SGhace 3 sem.
Detalles
- Experiencia
- 3+ años
- Prácticas
- CI/CD, MLOps
- Formación
- Estudios superiores
Postular
Abre la empresa y el enlace de arriba: tu candidatura va directamente al sistema de selección de la empresa, sin intermediarios.
Descripción
Role Overview The Data Scientist is embedded within the Data Science and AI Division (DSAD), working as part of the Fraud Analytics Models (FAM) team.
Sobre el puesto
The role
will support the maintenance and expansion of FAM 2.0, which detects misuse of public training grant. This includes addressing the methodology and threshold review backlog; building and operationalising the FAM 2.0 Technical Dashboard; and assessing how new schemes can be progressively brought within FAM 2.0's fraud-risk coverage. The candidate is expected to contribute to reliable fraud-risk analytics, clear methodology and sustainable implementation and to build up in-house capability along the way.
Key
Responsabilidades
Responsibilities
- Methodology and Threshold Review: Review and recalibrate FAM 2.0 model methodologies and thresholds for prioritised backlog items. This includes backtesting, 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 Build: Build and enhance monitoring for model performance (precision, recall), data drift and concept drift, including alert logic, visualisations and deployment support. Design performance measures that account for delayed and incomplete investigation outcomes. • New Scheme Assessment: Assess new schemes' structures, eligibility rules, claims processes a
Descripción completa, empresa y enlace para postular: después de iniciar sesión.
Iniciar sesiónLos contactos del empleador (correo/teléfono/telegram) están ocultos en la vista previa pública.