57 Data Scientist Continuous Vetting Program L3

SISP Position 30: Statistician/Data Scientist, Skill Level 3 (NGA Washington DC)Overall Assignment Description: Data Scientist – Continuous Vetting ProgramDuties include:• (U) Prepare annual reports summarizing the findings and lessons learned related toSEAD 3 reportable anomalies reported and unreported, percentage of filers who were compliant, final actions referred to CE/CV for investigation and trends in customer feedback• (U) Prepare monthly reports on status of performance metrics, due to the SISPV leadership• (U) Leveraging lessons learned, propose process improvements to the SISPV Branch Chief• (U) Data Science will use Commercial off the Shelf Software (COTS) in combination with all available CE/CV reportable information (polygraphs, eReport, walk-ins, referrals, Rap Back, DNI CE alerts, emails, and EAFR) to produce sophisticated analytic models, Triage capabilities, and dashboard metrics for CE/CV Investigators.• (U) Discover patterns in past data to predict the outcome of future events including statistical modeling, classification and analysis, clustering, optimization and simulation, and customer segmentation• (U) Text Mining-Provide information stored in text documents and databases including document classification, natural language processing, information extraction and search• (U) Data Infrastructure- Prepare, clean and integrate disparate data sources and building Extract, Transform, Load (ETL) and data pipelines optimized for advanced analytics• (U) Data Visualization-Create advanced algorithms easily accessible through 2-D and 3-D, statistical and spatial visualization• Develop a dashboard capability for CE/CV Investigators that will allow triggers (resulting from the above) to be efficiently prioritized and worked• (U) Applying the Risk Management Framework to provide a process to integrate security and risk management activities in to the CE/CV development life cycle. Applying the risk based approach to security control selection and specification consideration effectiveness, efficiency, and constraints due to applicable laws, directives, executive orders, policies, standards, or regulations• (U) Design, develop, test and communicate date sources from documented and repeatable methods based in sound data engineering principles and applicable standards• (U) Document, analyze, and enhance all data conditioning processes and procedures that translate raw data inputs into decision-quality data products appropriate for the SISPV leadership• (U) Ability to identify systems enhancements and new capabilities, concept demonstrators, capability business case• (U) Ability to interact and work in a teaming environment• (U) Develop performance metrics to reflect business analytic maturity levelSkills and ExperienceRequired:• (U) Bachelor of Science degree or higher in statistics, mathematics, image science, physical science or related technical or scientific field or similar course of study at an accredited school (or substitution experience and experience).• (U) Minimum 7-10 years experience• (U) Familiar with data mining, ability to develop and manipulate, and maintain databases• (U) Demonstrated experience using software packages used for advanced statistical analysis of operational data and tools for data visualization.• (U) Clear and concise writing skills.• (U) Positive, engaging communication skills.• (U) Excellent organizational skills to achieve required timelines.• (U) Demonstrated experience using COTS statistical software (SPSS, SAS, MatLab, etc.) for advanced statistical analysis of operational tools and data visualization.