{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/101067"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/101067","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"DeepBall: Modeling expectation and uncertainty in baseball with recurrent neural networks","abstract":"Making reliable preseason batter projections for baseball players is an issue of utmost importance to both teams and fans who seek to infer a player's underlying talent or predict future performance. However, this has proven to be a difficult task due to the high-variance nature of baseball and the lack of abundant, clean data. For this reason, current leading models rely mostly upon expert knowledge. We propose DeepBall, which combines a recurrent neural network with novel regularization and ensemble aggregation. We compare this to Marcel, the industry-standard open-source baseline, and other traditional machine learning techniques, and DeepBall outperforms all. DeepBall is also easily extended to predict multiple years in the future. In addition to predicting expected performances, we apply standard machine learning techniques to extend DeepBall to model uncertainty in these predictions by estimating the maximum-likelihood distribution over potential outcomes for each player. Due to the positive results, we believe that in the future, DeepBall can be beneficial to both teams and fans in modeling expectation and uncertainty. Finally, we discuss potential extensions to the model and directions of future research.","abstract_html":"Making reliable preseason batter projections for baseball players is an issue of utmost importance to both teams and fans who seek to infer a player's underlying talent or predict future performance. However, this has proven to be a difficult task due to the high-variance nature of baseball and the lack of abundant, clean data. For this reason, current leading models rely mostly upon expert knowledge. We propose DeepBall, which combines a recurrent neural network with novel regularization and ensemble aggregation. We compare this to Marcel, the industry-standard open-source baseline, and other traditional machine learning techniques, and DeepBall outperforms all. DeepBall is also easily extended to predict multiple years in the future. In addition to predicting expected performances, we apply standard machine learning techniques to extend DeepBall to model uncertainty in these predictions by estimating the maximum-likelihood distribution over potential outcomes for each player. Due to the positive results, we believe that in the future, DeepBall can be beneficial to both teams and fans in modeling expectation and uncertainty. Finally, we discuss potential extensions to the model and directions of future research.","abstract_has_math":false,"creators":["Calzada, Daniel"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Koyejo, Oluwasanmi O."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-09-04T20:31:55Z","date_published":"2018-09-04T20:31:55Z","updated_at":"2026-07-22T22:24:38Z","subjects":["baseball","MLB","prediction","projection","season","player","batter","pitcher","time","series","time-series","recurrent","neural","network","deep","learning","Gaussian","mixture","maximum","likelihood","distribution","marcel","strikeout","walk","average","slugging","percentage","WAR","oWAR"],"languages":["en"],"rights":["Copyright 2018 by Daniel Calzada. All rights reserved."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/101067","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Koyejo, Oluwasanmi O."]},{"key":"dc:creator","label":"Author","values":["Calzada, Daniel"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-09-04T20:31:55Z","2018-04-25","2018-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["baseball","MLB","prediction","projection","season","player","batter","pitcher","time","series","time-series","recurrent","neural","network","deep","learning","Gaussian","mixture","maximum","likelihood","distribution","marcel","strikeout","walk","average","slugging","percentage","WAR","oWAR"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2018 by Daniel Calzada. All rights reserved."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/101067"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Making reliable preseason batter projections for baseball players is an issue of utmost importance to both teams and fans who seek to infer a player's underlying talent or predict future performance. However, this has proven to be a difficult task due to the high-variance nature of baseball and the lack of abundant, clean data. For this reason, current leading models rely mostly upon expert knowledge. We propose DeepBall, which combines a recurrent neural network with novel regularization and ensemble aggregation. We compare this to Marcel, the industry-standard open-source baseline, and other traditional machine learning techniques, and DeepBall outperforms all. DeepBall is also easily extended to predict multiple years in the future. In addition to predicting expected performances, we apply standard machine learning techniques to extend DeepBall to model uncertainty in these predictions by estimating the maximum-likelihood distribution over potential outcomes for each player. Due to the positive results, we believe that in the future, DeepBall can be beneficial to both teams and fans in modeling expectation and uncertainty. Finally, we discuss potential extensions to the model and directions of future research.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-08-31 without embargo terms","The student, Daniel Calzada, accepted the attached license on 2018-04-24 at 23:22.","The student, Daniel Calzada, submitted this Thesis for approval on 2018-04-24 at 23:42.","This Thesis was approved for publication on 2018-04-25 at 08:47.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12468 on 2018-08-31 at 17:14:37","Made available in DSpace on 2018-09-04T20:31:55Z (GMT). No. of bitstreams: 3 CALZADA-THESIS-2018.pdf: 1211146 bytes, checksum: 7e4c3d89cd8c000e30e6a8ac9859ec36 (MD5) Daniel Calzada MS Thesis - LaTeX Source.zip: 1130768 bytes, checksum: 0d9350a4023ec614f4d02648deb175e5 (MD5) LICENSE.txt: 4211 bytes, checksum: 7e61f7e5ed3a75d0381bcc90951005e9 (MD5) Previous issue date: 2018-04-25"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["DeepBall: Modeling expectation and uncertainty in baseball with recurrent neural networks"]}]}],"canonical_facts":{"dc:contributor":["Koyejo, Oluwasanmi O."],"dc:creator":["Calzada, Daniel"],"dc:date":["2018-09-04T20:31:55Z","2018-04-25","2018-05"],"dc:description":["Making reliable preseason batter projections for baseball players is an issue of utmost importance to both teams and fans who seek to infer a player's underlying talent or predict future performance. However, this has proven to be a difficult task due to the high-variance nature of baseball and the lack of abundant, clean data. For this reason, current leading models rely mostly upon expert knowledge. We propose DeepBall, which combines a recurrent neural network with novel regularization and ensemble aggregation. We compare this to Marcel, the industry-standard open-source baseline, and other traditional machine learning techniques, and DeepBall outperforms all. DeepBall is also easily extended to predict multiple years in the future. In addition to predicting expected performances, we apply standard machine learning techniques to extend DeepBall to model uncertainty in these predictions by estimating the maximum-likelihood distribution over potential outcomes for each player. Due to the positive results, we believe that in the future, DeepBall can be beneficial to both teams and fans in modeling expectation and uncertainty. Finally, we discuss potential extensions to the model and directions of future research.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-08-31 without embargo terms","The student, Daniel Calzada, accepted the attached license on 2018-04-24 at 23:22.","The student, Daniel Calzada, submitted this Thesis for approval on 2018-04-24 at 23:42.","This Thesis was approved for publication on 2018-04-25 at 08:47.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12468 on 2018-08-31 at 17:14:37","Made available in DSpace on 2018-09-04T20:31:55Z (GMT). No. of bitstreams: 3 CALZADA-THESIS-2018.pdf: 1211146 bytes, checksum: 7e4c3d89cd8c000e30e6a8ac9859ec36 (MD5) Daniel Calzada MS Thesis - LaTeX Source.zip: 1130768 bytes, checksum: 0d9350a4023ec614f4d02648deb175e5 (MD5) LICENSE.txt: 4211 bytes, checksum: 7e61f7e5ed3a75d0381bcc90951005e9 (MD5) Previous issue date: 2018-04-25"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/101067"],"dc:language":["en"],"dc:rights":["Copyright 2018 by Daniel Calzada. All rights reserved."],"dc:subject":["baseball","MLB","prediction","projection","season","player","batter","pitcher","time","series","time-series","recurrent","neural","network","deep","learning","Gaussian","mixture","maximum","likelihood","distribution","marcel","strikeout","walk","average","slugging","percentage","WAR","oWAR"],"dc:title":["DeepBall: Modeling expectation and uncertainty in baseball with recurrent neural networks"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:38Z"}