Corporate Vice President, Geospatial Analytics and Data Science Lead

Job Requisition ID: 90868

Location Designation: Fully Onsite 

Location: New York, NY

Offered salary: $176,800.00

Duties: Leads and contributes to geospatial data analysis, modeling, and productionalization projects. Attends business review meetings with internal and external clients to determine requirements and deliverables, reception, and data processing. Builds predictive and prescriptive spatial data science models and prepares reports and presentations, communicates results, and implements support. Demonstrates to internal and external stakeholders how geospatial analytics can be implemented and adopted to maximize business benefits throughs projects and geospatial evangelism at conferences and workshops. Provides technical support, including strategic consulting, needs assessments, project scoping, and presentation of analytical proposals. Creates high-performing predictive models leveraging advanced geospatial, machine-learning, and deep-learning techniques. Performs creative analyses to address business objectives and client needs. Tests new geospatial analysis methods, software, and data sources for continual improvement of quantitative solutions. Communicates with internal stakeholders concerning product design, data specification, and model implementations; with partners concerning the collaboration ideas and specifics; and, with clients and account teams concerning project and test results, opportunities, and questions. Contributes to problem resolution and removes obstacles with timely and high-quality project completion. Creates project milestone plans to ensure projects are completed on time and within budget. Provides high-quality customer support, answers questions, resolves issues, and builds solutions. Validates ongoing spatial data science projects, including coding scripts, summarizing results for data manipulation, cleaning, and modeling, and challenging existing methods and recommending alternatives. Provides feedback to improve deliverables and teach spatial data science concepts and tools to a general internal audience. Accounts for and adheres to insurance industry trends and data and analytics processes and businesses. Functions as the spatial geospatial expert in meetings with internal stakeholders and external vendors and participates in proof-of-concept tests for new data, software, and technologies and shares knowledge within the Analytics group. Ensures compliance with regulatory and privacy requirements during design and implementation of modeling and analysis projects.

Requirements: Master's degree in Statistics, Computer Science, Mathematics, Economics or related quantitative field (willing to accept foreign education equivalent) plus four years of experience performing geospatial predictive analytics using large and complex spatially-enabled datasets in software services or insurance industry

or,

alternatively, a Doctor of Philosophy in Statistics, Computer Science, Mathematics, Economics or related quantitative field (willing to accept foreign education equivalent) and one year of experience performing geospatial predictive analytics using large and complex spatially-enabled datasets in software services or insurance industry. 

Experience must include 1 year in each of the following skills: Performing geoanalytics data visualization and spatial data modeling leveraging geographic information system (GIS) technologies (including ArcGIS Enterprise, ArcGIS Pro, GDAL, GeoPandas, Shapely, and Spark) to interpret data and gain analytical insights (including opportunity discovery, trade area analysis, and footprint optimization analysis) leveraging all of the following spatial data science techniques: geographically-weighted regression, spatial autocorrelation, network analysis, spatially-constrained multivariate clustering (based on DBSCAN), spacetime hotspot analysis, spatiotemporal forecasting, and Empirical Bayesian kriging (EBK); Building tunable and descriptive geospacial models to understand sales transactions and competitor presence and provide prescriptive insights, including demographic trend analysis to support site selection, leasing decisions, and emerging and fading hotspots for location-based investment opportunities leveraging customized end-to-end statistical modeling, machine-learning, and deep-learning techniques including: generalized linear modeling (GLM), tree modeling (leveraging Random Forests and gradient boosting machine (GBM) models), time series modeling (leveraging ARIMA, exponential smoothing, and Long Short-Term Memory), generative modeling (leveraging Transformers) and tuning with Optuna; Productionalizing geospatial data science models and data pipelines to enable production-readiness and support large-scale data ingestion leveraging all of the following languages: R, Python