Data Scientist

Responsible for modeling complex business problems and discovering business insights through the use of data mining techniques, statistical analysis, designing tools / applications, automation and building high quality prediction systems and incorporating them into business processes. The individual will collaborate with the leadership and SMEs from business units, key external-related business partners across COMPANY, and the IT organization to develop technology tools / applications, support digital plans & strategies, identify, and develop proof of concepts. Ultimately responsible for developing data analytics and visualization products that provide insights across the agency to COMPANY external risks and opportunities with stakeholders, including LPC’s, Industrial Customers, Local, State, and Federal Officials, Community Involvement, and Economic Development current and potential customers.

PRINCIPAL ACCOUNTABILITIES :

• Participates and at times leads efforts for identifying business insights through data structure, data mining, predictive models, and implementing innovative techniques for analysis and gathering business intelligence.
• In addition to enabling and informing key decision-making, the data and models produced will be used in all manners of financial planning, business cases, economic development lead generation, customer and stakeholder analysis, reporting to regulators, and performing studies to optimize interactions in community involvement, and local and federal policy.
• Research and implement cutting-edge techniques and tools in machine learning / deep learning / artificial intelligence to make data analysis more efficient, selecting features, building and optimizing classifiers using machine learning techniques.
• Strong ability to communicate complex data and modeling in a simple, actionable way
• Ability to visualize data in the most effective way possible for a given project or study
• Determine requirements that will be used to train and evolve deep learning models and algorithms.
• Data mining using state-of-the-art methods to identify trends and patterns and generate insights that will optimize operational decisions and inform executive decision making.
• Extending company's data with third party sources of information when needed.
• Enhancing data collection procedures to include information that is relevant for building analytic systems.
• Processing, cleansing, and verifying the integrity of data used for analysis.
• Doing ad-hoc analysis and presenting results in a clear manner using data visualization tools.
• Creating automated anomaly detection systems and constant tracking of its performance.
• Design, test and produce key data reporting to generate insights and drive operational decision making
• Experiment to identify hidden relationships between variables in large data sets.
• Leverage both structured and unstructured data sources from across the agency.
• Use big data analysis tools and techniques.
• Supports and at times play a key role in training, coaching, and upskilling current management & specialist team members, and advising management on how to maximize data science capabilities for optimal decision-making.

MINIMUM REQUIREMENTS :

Education and Experience —

• Degree in mathematics, statistics, computer science, economics, engineering, operations research, decision science, or a related quantitative field, plus professional experience performing analytics, including statistical analysis, mathematical modeling, and computer programming. Master’s degree and / or PhD degree is highly preferred.

At least years of experience with advanced analytics, including predictive analytics, machine learning, deep learning, mathematical optimization, and risk simulation, in either an academic or professional setting. or more years of experience is highly preferred.

Knowledge / Skills / Abilities —

Excellent quantitative reasoning, mathematical modeling, and problem solving abilities. Knowledge and experience in statistical and machine learning techniques : Regression Modeling, Random Forest, Boosting, Trees, SVM, K-Nearest Neighbors, PCA, Bayesian, Ensembles etc. Experience in developing deep-learning algorithms using large datasets. Strong programming skills using data science tools such as R, Python, or Matlab. Familiar with big data infrastructure and tools ( Hadoop, Spark, NoSQL, Lucene / Solr / Elastic, AWS, etc.). Experienced at leveraging both structured and unstructured data sources. Knowledge of SQL for extracting and transforming data from databases. Effective oral and written communication skills, especially concerning technical concepts and results. Ability to obtain and maintain a security clearance based on position / access requirements and essential job functions.

EEO : -