A carregar...
Publicação
Beat the Streak
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.82 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
As the world of sports expands to never seen levels, so does the necessity for tools that provided material advantages for organizations and stakeholders. The objective of this project is to develop a predictive model capable of predicting the odds a baseball player has to achieve a base hit on a given day. After that, using this information to both have a fair shot at winning the game Beat the Streak and providing valuable insights to the coaching staff. This project builds upon the work developed previously in Alceo and Henriques (2019), adding a full season of data, emphasizing new strategies, and displaying more data visualization content. The results achieved on the new season are aligned with the previous work where the best model, a Multi-layer Perceptron, developed in Python achieved an 81% correct pick ratio.
Descrição
Alceo, P., & Henriques, R. (2020). Beat the Streak: Prediction of MLB Base Hits Using Machine Learning. In A. Fred, A. Fred, A. Salgado, D. Aveiro, J. Dietz, J. Bernardino, & J. Filipe (Eds.), Knowledge Discovery, Knowledge Engineering and Knowledge Management: 11th International Joint Conference, IC3K 2019, Revised Selected Papers (pp. 108-133). (Communications in Computer and Information Science; Vol. 1297). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-66196-0_6
Palavras-chave
Baseball Classification model Data mining Machine learning MLB Predictive analysis General Computer Science General Mathematics
Contexto Educativo
Citação
Editora
Springer Science and Business Media Deutschland GmbH