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).

First, the Log5 Method picks:

0.353 — Victor Martinez batting against Michael Pineda
0.340 — Ian Kinsler batting against Michael Pineda
0.339 — Nick Castellanos batting against Michael Pineda
0.332 — Xander Bogaerts batting against Ubaldo Jimenez
0.330 — Miguel Cabrera batting against Michael Pineda
0.327 — Eduardo Nunez batting against Matthew Moore
0.327 — DJ LeMahieu batting against Alfredo Simon
0.323 — Carlos Gonzalez batting against Alfredo Simon
0.322 — Josh Harrison batting against Wei-Yin Chen
0.319 — Charles Blackmon batting against Alfredo Simon
0.319 — Cameron Maybin batting against Michael Pineda

It looks like a good night to be a Tigers hitter. On the other hand, you never know when Pineda is going to find his stuff.

These are the top picks for the NN:

0.322, 0.746 — Josh Harrison batting against Wei-Yin Chen.
0.330, 0.745 — Miguel Cabrera batting against Michael Pineda.
0.313, 0.744 — Jose Altuve batting against Zack Greinke.
0.327, 0.743 — Eduardo Nunez batting against Matthew Moore.
0.340, 0.738 — Ian Kinsler batting against Michael Pineda.
0.332, 0.736 — Xander Bogaerts batting against Ubaldo Jimenez.
0.307, 0.735 — Odubel Herrera batting against Chase Anderson.
0.276, 0.733 — Brandon Phillips batting against Eddie Butler.
0.353, 0.729 — Victor Martinez batting against Michael Pineda.
0.314, 0.727 — Starling Marte batting against Wei-Yin Chen.
0.302, 0.727 — Martin Prado batting against Juan Nicasio.

The NN doesn’t like Michael Pineda, either, and it’s not crazy about Wei-Yin Chen, either. Miguel Cabrera and Ian Kinsler seems to be the consensus picks. As always, the probability of any of these hitters ending the streak is pretty good, so choose wisely.

from baseballmusings.com http://ift.tt/25Cq6NW