Listen in as Anders Larson, FSA, MAAA, interviews Shea Parkes, FSA, MAAA about Support Vector Machines (SVMs). SVMs are a family of predictive models with a lot of unique quirks. For example, they can focus on getting to a yes/no answer above all else. Also don’t miss the heroic attempt to verbally explain the “kernel trick” that can really kick SVMs’ performance into overdrive.

Direct download: SOA17_37_PAF_09_Support_Vector_Machines.mp3
Category:Predictive Analytics and Futurism -- posted at: 9:21am CST