Beat the Streak Picks

Here are the top picks my programs produced for use in Beat the Streak. This post mostly explains the ideas behind the calculations. In addition, this post shows tests on the Neural Network (NN). This post discusses an NN that includes the ballpark. I recently update the models, and the results of those tests are here.

For 2017, I am just going to publish the Log5 hit averages and the NN probabilities with parks factored in. I am keeping track of the results here.

First, the Log5 Method picks:

0.293 — Daniel Murphy batting against Jeremy Hellickson
0.280 — Corey Seager batting against Tyler Anderson
0.280 — Yunel Escobar batting against Hisashi Iwakuma
0.276 — Yadier Molina batting against Scott Feldman
0.275 — Francisco Lindor batting against Patrick Corbin
0.275 — Aledmys Diaz batting against Scott Feldman
0.274 — Eduardo Nunez batting against Clayton Richard
0.274 — Brandon Phillips batting against Gerrit Cole
0.273 — J.T. Realmuto batting against Noah Syndergaard
0.273 — Justin Turner batting against Tyler Anderson

Murphy’s strong start combined with his excellent 2016 season pushed him way to the top of this list. It’s also nice to see some middle infielders make it.

The NN with Park produces this list:

0.293, 0.733 — Daniel Murphy batting against Jeremy Hellickson.
0.280, 0.709 — Yunel Escobar batting against Hisashi Iwakuma.
0.280, 0.707 — Corey Seager batting against Tyler Anderson.
0.273, 0.699 — J.T. Realmuto batting against Noah Syndergaard.
0.271, 0.698 — Jean Segura batting against Matthew Shoemaker.
0.274, 0.695 — Eduardo Nunez batting against Clayton Richard.
0.275, 0.695 — Francisco Lindor batting against Patrick Corbin.
0.274, 0.694 — Brandon Phillips batting against Gerrit Cole.
0.262, 0.693 — Mookie Betts batting against Daniel Norris.
0.263, 0.692 — Dustin Pedroia batting against Daniel Norris.
0.276, 0.690 — Yadier Molina batting against Scott Feldman.

The NN agrees that Murphy is head and shoulders above the rest of the pack in his probability of getting a hit today. Remember that for the best players there will still be a 25% chance of them not getting a hit in the game.

Also, with the season somewhat underway, the Day by Day Database is reporting current hit streaks.

from baseballmusings.com http://ift.tt/2olPgjc