Using R, SQL Server Advanced Analytics, and Baseball to Hit a Home Run
Advanced Analysis Techniques
The last two releases of SQL Server provided the capability to use SQL Server as the hub in a hub and spoke model for big data and data science. Our hub will use R In-database advanced analytics and Power BI. The technology is impressive, but data needs to be interesting. We are using data provided by RetroSheets.org to create a data set of play by play data and box scores for Major League Baseball games from 1922 to 2015. We set out to discover the answer to questions every baseball fan wants to know! Do you have a better chance to see your team win by going to a Double Header or regular game? Is there 'a the best day of the week' to see your favorite team win? How do winning and losing seasons impact this or home and away games? Come for the baseball, stay for the science!
No material found.