Abstract: This workshop will guide attendees through the entire geospatial machine learning workflow. Attendees will be be exposed to a variety of open source tools used to process, model, and visualize geospatial data including PySAL, GDAL, and QGIS. We will work through a supervised machine learning problem to predict the sale price of single family homes in Pinellas County Florida using a large number of property, structural, and socioeconomic features. This workshop will focus on concepts unique to handling geospatial data such as spatial autocorrelation, coordinate transformations, and edge effects.
Bio: Kevin is a Customer Facing Data Scientist at DataRobot and an Adjunct Professor at Pennsylvania State University where he teaches a graduate level Geographic Information Systems (GIS) course. He has over 16 years of experience using GIS and geospatial analysis to solve real world business problems. His experience with modeling geospatial phenomena include geostatistical, spatial econometric, and point pattern analysis.