Data Scientist

This is a non-merit, employment-at-will contract position. The Data Scientist will leverage data to drive insights and impact the organization's strategic decisions. The position is responsible for developing tools that support the analysis of structured, unstructured, and digital business data research studies and organizational metrics. Essential Functions Applies statistical techniques and tools for data mining and modeling of business applications to gather key organizational data and metrics Performs statistical analysis or operations research analysis of targeted databases for productivity opportunity identification/discovery or specific decision-making Develops and maintains statistical models & methodologies to predict, quantify, and/or forecast various patterns and gaps Deploys, assesses the quality of and revises mathematical models to support the Commission's decision-making process Effectively communicates results of statistical models to a broad audience, including senior leadership Uses quantitative and qualitative data sources to successfully generate results Conducts exploratory data analysis (EDA) to understand data patterns, trends, and potential outliers Identifies and gathers relevant data from various sources, including databases, APIs, and external datasets Cleans and preprocesses data to ensure its quality, consistency, and usability Develops and implements advanced machine learning and statistical models to solve complex business problems Selects appropriate algorithms and techniques for specific tasks such as regression, classification, clustering, and time series forecasting Fine-tunes models to optimize performance and generalization Creates informative data visualizations, dashboards, and reports to communicate findings and insights to stakeholders Translates complex technical results into easily understandable formats for non-technical audiences Implements rigorous validation processes, including cross-validation and hypothesis testing, to assess model performance and reliability Interprets model outputs and assesses their business impact Leads and manages data science projects from inception to deployment, ensuring alignment with organizational goals and timelines Collaborates with cross-functional teams to define project objectives, gather requirements, and prioritize initiatives Stays updated on the latest developments in data science, machine learning, and related technologies Identifies and recommends opportunities for process improvement and innovation Documents methodologies, codes, and model specifications for reproducibility and knowledge sharing Other Functions Assists in Commission data-monitoring activities Develops new and ad-hoc reports on data analysis activities across the Commission Assists with the development of presentations Work Environment And Physical Demands Business casual office environment Required Knowledge, Skills, And Abilities Skill in programming applications using Python, R, SQL, and SAS to extract and transform data from multiple data sources Performing data wrangling and matching leveraging Extract Load Transfer (ETL) techniques Performing feature engineering and selection (transformation, binning, and high-level categorical reduction); model optimization (grid search and Bayesian optimization), and model testing and validation (cross-validation and bootstrapping) Developing and deploying supervised and unsupervised machine-learning models leveraging Random Forest, XGBoost, and GBM tree models, deep learning, and k-means and performing regularization leveraging Ridge, Lasso, and elastic net Sound technical background with experience in the following technologies, or equivalent: databases (SQL Server), cloud (Azure), business intelligence/reporting (PowerBI) Expertise in machine learning and AI techniques Experience implementing predictive algorithms and associated statistical analysis/inference in data science/ML workflow manipulating both structured and unstructured data Experience in using AI tools in Microsoft Azure or AWS environment Advanced knowledge of relational database structure Excellent organizational and communication skills Ability to identify emerging patterns that can be found through the analysis of big data, unstructured data, and data from multiple internal and external sources Ability to manage projects with strong technical and data-driven components Ability to communicate complex concepts to a non-technical audience Minimum Education, Experience Requirements Bachelor's degree 5+ years experience with statistical modeling/data mining (decision tree, logistic regression, cluster analysis, etc.) that includes accessing and analyzing large volumes of data using SQL, SAS, SPSS, etc., including experience in the following areas: Developing an enterprise analytical platform and framework Implementing data science tools such as Python, R, Spark, SQL Data manipulation using libraries such as Pandas and NumPy Experience with machine learning frameworks and libraries (e.g., TensorFlow and Scikit-Learn) Statistical analysis, time series analysis, and predictive modeling OR High school diploma or equivalent 9+ years experience with statistical modeling/data mining (decision tree, logistic regression, cluster analysis, etc.) that includes accessing and analyzing large volumes of data using SQL, SAS, SPSS, etc., including experience in the following areas: Developing an enterprise analytical platform and framework. Implementing data science tools such as Python, R, Spark, SQL. Data manipulation using libraries such as Pandas and NumPy. Experience with machine learning frameworks and libraries (e.g., TensorFlow and Scikit-Learn). Statistical analysis, time series analysis, and predictive modeling