Blackbox modeling (Video)

Collapse
X
 
  • Time
  • Show
Clear All
new posts
  • fiveteamer
    SBR Posting Legend
    • 04-14-08
    • 10805

    #71
    Justin probably makes a living betting WNBA, he must have beards all over the country.

    Anything else, he is like everybody else, a coin toss.
    Comment
    • durito
      SBR Posting Legend
      • 07-03-06
      • 13173

      #72
      You can make a better living betting the WNBA than playing in it, that's for sure.
      Comment
      • TJMAXX
        SBR Rookie
        • 05-22-09
        • 19

        #73
        Originally posted by Justin7
        I don't think there are any good books explaining how to make a model in sports betting. I've actually started writing one, though I doubt more than 20 people would pay for it.
        A few of us would probably pay 20x the price of the book to keep the good shit quiet for a few more years...
        Comment
        • Dave Head
          SBR Hustler
          • 07-22-09
          • 73

          #74
          Good video, but I would hate to see someone invest $2,000 or $3,000 to hire a programmer to get 5 years worth of stats. If you don't have the skills to go data mining yourself, are you going to have the skills to do your own regression analysis, much less any modeling? Yes, you could use a spreadsheet, but that is still for practical purposes a manual process, which would have to be repeated each week for 5 years. That's a full-time job. Don't get me wrong. I have respect for handicappers that don't just fly by the seat of their pants, but I think your time would be better spent actually watching the games.
          Comment
          • Justin7
            SBR Hall of Famer
            • 07-31-06
            • 8577

            #75
            Originally posted by Dave Head
            Good video, but I would hate to see someone invest $2,000 or $3,000 to hire a programmer to get 5 years worth of stats. If you don't have the skills to go data mining yourself, are you going to have the skills to do your own regression analysis, much less any modeling? Yes, you could use a spreadsheet, but that is still for practical purposes a manual process, which would have to be repeated each week for 5 years. That's a full-time job. Don't get me wrong. I have respect for handicappers that don't just fly by the seat of their pants, but I think your time would be better spent actually watching the games.
            I have done data scraping before. This is a waste of my time though - it's better spent in other pursuits.
            Comment
            • Sforz
              SBR MVP
              • 08-07-08
              • 2221

              #76
              good stuff justin7.

              thank you.
              Comment
              • rdgarza
                SBR Rookie
                • 09-30-09
                • 9

                #77
                Justin7:

                Thank you for the video, it's very good.

                I have a question for all of you:

                What do you use for run your models?, Excel or you program your own code or maybe something like Matlab.
                Comment
                • Justin7
                  SBR Hall of Famer
                  • 07-31-06
                  • 8577

                  #78
                  Originally posted by rdgarza
                  Justin7:

                  Thank you for the video, it's very good.

                  I have a question for all of you:

                  What do you use for run your models?, Excel or you program your own code or maybe something like Matlab.
                  I use Virtual Pascal integrated environment. It makes debugging much, much easier.
                  Comment
                  • Indecent
                    SBR Wise Guy
                    • 09-08-09
                    • 758

                    #79
                    Rather than using the most recent year as the validation data set, consider randomizing the order of games and using 2/3 of the games for training your model and 1/3 for validation set. This will hopefully prevent overtraining problems.

                    Edit: Thanks for the video! The action points concept was new to me, and the rest of it is great for any beginner looking to get started.
                    Comment
                    • goldseeker
                      SBR Wise Guy
                      • 09-11-05
                      • 604

                      #80
                      Good info Justin. For modeling, SAS is the better tool.
                      Comment
                      Search
                      Collapse
                      SBR Contests
                      Collapse
                      Top-Rated US Sportsbooks
                      Collapse
                      Working...