Lately I’ve been thinking a lot about the connection between prediction models and the decisions that they influence. There is a lot of theory around this, but communicating how the various pieces all fit together with the folks who will use and be impacted by these decisions can be challenging. One of the important conceptual pieces […]
In this repository hosted at github, the datadolph.in team is sharing all of the R codebase that it developed to analyze large quantities of data.datadolph.in team has benefited tremendously from fellow R bloggers and other open source communities and ...
In this repository hosted at github, the datadolph.in team is sharing all of the R codebase that it developed to analyze large quantities of data.datadolph.in team has benefited tremendously from fellow R bloggers and other open source communities and ...
It’s a folk theorem I sometimes hear from colleagues and clients: that you must balance the class prevalence before training a classifier. Certainly, I believe that classification tends to be easier when the classes are nearly balanced, especially when the class you are actually interested in is the rarer one. But I have always been … Continue reading Does Balancing Classes Improve Classifier Performance? → Related posts: Don’t use correlation…
They sprint, they jump, they lift. Does any of it matter come draft day? Click through to read my take on the matter. Predicting NFL draft picks based on their combine results!
As John mentioned in his last post, we have been quite interested in the recent study by Fernandez-Delgado, et.al., “Do we Need Hundreds of Classifiers to Solve Real World Classification Problems?” (the “DWN study” for short), which evaluated 179 popular implementations of common classification algorithms over 120 or so data sets, mostly from the UCI … Continue reading The Geometry of Classifiers → Related posts: Does Balancing Classes Improve Classifier…
First service percentage? Unforced errors? Points at the net? Grit? Good looks? What really matters in winning the US Open? Click to find out!
![ABC model choice by random forests [guest post]](http://xianblog.files.wordpress.com/2009/08/treerise6.jpg?w=311&h=233)
[Dennis Prangle sent me his comments on our ABC model choice by random forests paper. Here they are! And I appreciate very much contributors commenting on my paper or others, so please feel free to join.] This paper proposes a new approach to likelihood-free model choice based on random forest classifiers. These are fit to […]
(skip to the shiny app) Model building is very often an iterative process that involves multiple steps of choosing an algorithm and hyperparameters, evaluating that model / cross validation, and optimizing the hyperparameters. I find a great aid in this… Continue reading →
After more than a year of collaboration, meetings, simulations, delays, switches, visits, more delays, more simulations, discussions, and a final marathon wrapping day last Friday, Jean-Michel Marin, Pierre Pudlo, and I at last completed our latest collaboration on ABC, with the central arguments that (a) using random forests is a good tool for choosing the […]
