Data Scientists will be expected to:
Perform hands-on analysis and modeling involving the creation of intervention hypotheses and experiments, assessment of data needs and available sources, determination of optimal analytical approaches, performance of exploratory data analysis, and feature generation (e.g., identification, derivation, aggregation).
Collaborate with mission stakeholders to define, frame, and scope mission challenges where big data interventions may offer important mitigations and develop robust project plans with key milestones, detailed deliverables, robust work tracking protocols, and risk mitigation strategies.
Demonstrate proficiency in extracting, cleaning, and transforming CBP transactional and mission data associated within an identified problem space to build predictive models as well as develop appropriate supporting documentation.
Leverage expert knowledge of a variety of statistical and machine learning techniques and methods to define and develop programming algorithms; train, evaluate, and deploy predictive analytics models that directly inform mission decisions.
Execute projects including those intended to identify patterns and/or anomalies in large datasets; perform automated text/data classification and categorization as well as entity recognition, resolution and extraction; and named entity matching.
Brief project management, technical design, and outcomes to both technical and non-technical audiences including senior government stakeholders throughout the model development/ project lifecycle through written as well as in-person reporting.
Proficiency with statistical software packages: R
Experience with programming languages: R, SQL
Experience constructing and executing queries to extract data for exploratory data analysis and model development
Experience performing training set construction, analysis, and data mining
Experience with unsupervised machine learning techniques and methods
Significant experience in developing machine learning models and applying advanced analytics solutions to solve complex business problems
Proficiency with SQL programming
Experience with unsupervised and supervised machine learning techniques and methods
Experience working with large-scale (e.g., terabyte and petabyte) unstructured and structured data sets and databases
Experience performing data mining, analysis, and training set construction.
Experience with programming languages including: Python, Scala, Java
Experience constructing and executing queries to extract data in support of EDA and model development
Proficiency with statistical software packages including: SAS, SPSS Modeler, R, WEKA, or equivalent
Proficiency with Unsupervised Machine Learning methods including Cluster Analysis (e.g., K-means, K-nearest Neighbor, Hierarchical, Deep Belief Networks, Principal Component Analysis), Segmentation, etc.
Experience with Natural Language Processing (NLP), computational linguistics, Entity extraction, named entity recognition (NER), name matching, disambiguation, Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA).
Proficiency with Supervised Machine Learning methods including Decision Trees, Support Vector Machines, Logistic Regression, Random/Rotation Forests, Categorization/Classification, Neural Nets, Bayesian Networks, etc.
Experience with pattern recognition and extraction, automated classification, and categorization
Experience with entity resolution (e.g., record linking, named-entity matching, deduplication/ disambiguation)
Experience with visualization tools and techniques (e.g., Periscope, Business Objects, D3, ggplot, Tableau, SAS Visual Analytics, PowerBI)
Experience with big data technologies (e.g., Hadoop, HIVE, HDFS, HBase, MapReduce, Spark, Kafka, Sqoop)
Master’s Degree in mathematics, statistics, computer science/engineering, or other related technical fields with equivalent practical experience