Roger Cheng at the Hardball Times takes Carl Wivvag’s pitcher injury predictors a step further by combining them.
It seems like everybody in the baseball analytics community is trying to invent or discover the “next big thing” in sabermetrics. Some ideas, like Voros McCracken’s theory of BABIP, come out of nowhere and make a huge impact. However, I believe that we can also make improvements to existing ideas by combining things that we already know, and the above analysis of pitcher injury prediction outlines one specific example of that. This process can be extended to predictions of any kind, and perhaps there are other domains in sabermetrics that could also benefit from using multiple classifiers in tandem.
Early this century I was working at the Center for Intelligent Information Retrieval at UMass Amherst. They found a very similar result with search engines, that combining the results of multiple search engines produced a better result than any single search engine.
from baseballmusings.com https://ift.tt/2Pf9h9U
No comments:
Post a Comment