It has become our tradition to hold R Week in April with both a Meetup & the R Conference (rstats.nyc) in the same week. For this mega dose of R, we have Andy Liaw, the author of the randomForest package.
Members of the meetup get a 20% discount with code nyhackr.
Thank you to eBay NYC (friends.ebaynyc.com) for hosting us.
About the Talk:
Random Forests have been a very popular machine learning method for nearly two decades since its introduction by Leo Breiman. This classification & regression algorithm has proven itself very effective in many applications, & is robust as well as easy to use. In this talk we will briefly explain what the algorithm is. We discuss on an intuitive level what is needed for ensemble methods to work, & how random forests achieve that. Comparison will be made with other tree ensemble methods such as boosting. Based on the intuition, we will discuss possibilities for tuning random forests for better performance. We will also touch on how the variable importance idea that Breiman introduced in random forests can be applied to other Machine Learning methods.
Andy Liaw is a Senior Principal Scientist in Biometrics Research, Merck & Co., where he applies statistics & machine learning to complex chemical & biological data to address problems in drug discovery. He is the author of the randomForest package for R. He holds a Ph.D. & M.S. in Statistics from Texas A&M University.
Pizza (nyhackr.org/pizzapoll.html) begins at 6:30, the talk starts at 7, then after we head to the local bar.