David Humphrey, PhD

Senior Data Scientist at Railinc

North American Railcar Fleet Update

Responsible for modeling complex business problems, discovering business insights and identifying opportunities using appropriate statistical, algorithmic, mining and visualization techniques. Proficient at integrating and preparing large, varied datasets, and communicating results and recommendations to senior levels of organization based on the outcome of modeling and analysis.

• Successful promotion of polynomial regression models to detect anomalous data in critical business processes.
• Creation of new railcar fleet utilization measures through order statistics.
• Gather, interpret, and translate customer needs into business opportunities on which we can capitalize with appropriate analysis techniques.
• Collaborate closely with IT colleagues to deploy models and prototypes appropriately.
• Represent Railinc as speaker at conferences and industry meetings as subject matter expert in content, quality, and practical usefulness of extensive data repository under administration.
• Mentor less experienced colleagues in determination of relevant data and appropriate analysis techniques.
• Lead in-house education on transition of business analysis to Python and away from SAS by creating and delivering content specific to our tools, our data, and our working environment.
• Proficient with Python, Pandas, SQL, SAS, NumPy, SciPy, Matplotlib, Scikit-learn.
• Proficient with Linux and Windows.
• Presently working with Snowflake and AWS RDS.
• Previously worked with Oracle, Hadoop, Greenplum, Teradata, DB2.