Welcome Guest
Log In | Register )
You last visited December 10, 2016, 5:13 pm
All times shown are
Eastern Time (GMT-5:00)

Neural Net Lottery Picker

678 replies. Last post 7 hours ago by lakerben.

Page 45 of 46
511
PrintE-mailLink
lottolot's avatar - Sphere animated2.gif
Tanhauser Gates
Holy See (Vatican City State)
Member #139281
February 18, 2013
173 Posts
Offline
Posted: November 20, 2016, 12:16 pm - IP Logged

I tottaly agree with you, lottolot. It seems people here does not like sharing their methods and only give critics to those who contributes with programs etc. 

Gambler667

Thumbs UpWink

Thanks and regards.

    Avatar

    United States
    Member #98539
    October 9, 2010
    57 Posts
    Offline
    Posted: November 20, 2016, 12:48 pm - IP Logged

    To all:

     

    Moving the slider back and forth on the learning rate setting (alpha) in NNLP.   Which side is faster?  The left side to the lowest value of  1E-05 or the right side to the highest value of 1?

     

    Thanks in advance for your answer to this question.

      Avatar

      United States
      Member #98539
      October 9, 2010
      57 Posts
      Offline
      Posted: November 20, 2016, 3:46 pm - IP Logged

      Back with a new strategy. Based on only playing lines with as low Total Error rates as possible.

      I generate for example 120 lines in a lottery and only pick the lowest 40(33.3%) to 48(40%) lines for playing. It is a risk to take, because it's not impossible there will be winners among the 80 lines which you ignored/didn't play. If I generate 150 lines I would pick the lowest 50 to 60 lines for playing.

      I used this strategy for Saturday lotto(7/34) on October 15th. Generated 120 lines and picked the 40 lines with lowest Total Error.

      I won three 4/7 and one 5/7. Total prize win was NOK 260(about US$31). I spent NOK 200(about US$24). I used the settings for VikingLotto on page 18, which seems to work fine for Saturday lotto as well.

      Dear MillionsWanted,

       

      How long is it taking you to generate 120 lines in the Neural Net Lottery Picker software program?  Exactly what settings are you using that makes a difference to the speed of the software?

       

       

      Sincerely,

       

       

      Kosh

        Gambler667's avatar - shapes swish.jpg

        Australia
        Member #166177
        May 8, 2015
        29 Posts
        Offline
        Posted: November 20, 2016, 5:28 pm - IP Logged

        Hey Guys,

        When running the NNLP using the latest 9  to 30 past draws, having the F parameter between 2 and 12 momentum 0.20 and 0.30 and Learning Rate 0.80 - 0.90 which is the best way to backtesting it? I am running it using Skipping the 3 last games and seeing the Hits with Skipped Training but I am not sure if I am in right path. Any ideas?

        Gambler667

          lottolot's avatar - Sphere animated2.gif
          Tanhauser Gates
          Holy See (Vatican City State)
          Member #139281
          February 18, 2013
          173 Posts
          Offline
          Posted: November 21, 2016, 5:35 pm - IP Logged

          Hey Guys,

          When running the NNLP using the latest 9  to 30 past draws, having the F parameter between 2 and 12 momentum 0.20 and 0.30 and Learning Rate 0.80 - 0.90 which is the best way to backtesting it? I am running it using Skipping the 3 last games and seeing the Hits with Skipped Training but I am not sure if I am in right path. Any ideas?

          Gambler667

          Hi Gambler667:

          My personal experience is spend many MANY hours,with trial and error.

          In the beginning is very frustrating,but finally when you find the right settings(for your game),you can see how the program its works and begin to predict the right numbers!.(at least in my own experience).

          Every game has its own settings...

          I hope this helps.See Ya!

            Gambler667's avatar - shapes swish.jpg

            Australia
            Member #166177
            May 8, 2015
            29 Posts
            Offline
            Posted: November 21, 2016, 5:57 pm - IP Logged

            Hi Lottolot,

            Thanks for your reply and I shall bear in mind it is the trial and error. My doubt is when running the NN Picks which column should I look ? The Total Error or Average Error to pick my out picks? 

            My lotto is a 6/45 with 2 bonus numbers and yesterday I made my data files using the tips from the forum having 9 past draws without bonus and 30 with bonus numbers. After the draw took place last night I could check my games produced from the program and it really works to predict 4 correct numbers! The hard part is how many games to produce or which portion from the Total Error column to look at?

            My settings were:

            LR - 9E-05

            Momentum: 0.008539

            Noise - 0.23

            Threshold - 0.1493

            HLN - 225

            STD - 0

            Gambler667

              MillionsWanted's avatar - 24Qa6LT

              Norway
              Member #9517
              December 10, 2004
              1272 Posts
              Online
              Posted: November 21, 2016, 9:26 pm - IP Logged

              Dear MillionsWanted,

               

              How long is it taking you to generate 120 lines in the Neural Net Lottery Picker software program?  Exactly what settings are you using that makes a difference to the speed of the software?

               

               

              Sincerely,

               

               

              Kosh

              It may take 4-5 days. I put it on Restart training after 14400 seconds(4 hours) and let it run until it reaches my set limit.

              You may set Process Priority to Above Normal.

                lottolot's avatar - Sphere animated2.gif
                Tanhauser Gates
                Holy See (Vatican City State)
                Member #139281
                February 18, 2013
                173 Posts
                Offline
                Posted: November 22, 2016, 4:37 pm - IP Logged

                Hi Lottolot,

                Thanks for your reply and I shall bear in mind it is the trial and error. My doubt is when running the NN Picks which column should I look ? The Total Error or Average Error to pick my out picks? 

                My lotto is a 6/45 with 2 bonus numbers and yesterday I made my data files using the tips from the forum having 9 past draws without bonus and 30 with bonus numbers. After the draw took place last night I could check my games produced from the program and it really works to predict 4 correct numbers! The hard part is how many games to produce or which portion from the Total Error column to look at?

                My settings were:

                LR - 9E-05

                Momentum: 0.008539

                Noise - 0.23

                Threshold - 0.1493

                HLN - 225

                STD - 0

                Gambler667

                Hello Gambler 667: 

                I do not consider anything, of any particular column.

                I simply use all the bets, but then try to apply some type of filter, (such as the "Total Sum" filter).

                Recently I hit a prize, which had the highest error rate,of all bets.(Total error column).

                If I had used only the bets with the lowest error rate, I would have lost that prize.

                Other users will think differently, but it is my personal experience.
                Thanks and regards.Thumbs UpSee Ya!
                  Gambler667's avatar - shapes swish.jpg

                  Australia
                  Member #166177
                  May 8, 2015
                  29 Posts
                  Offline
                  Posted: November 22, 2016, 4:52 pm - IP Logged

                  Hi Lottolot,

                   

                  How many lines have you produced ? Did you play them all ?

                  I was trying to look at Stoopendaals` settings images for his 6/45 lottery here at the forum and I was unable to see them.

                  If anyone can see them could you please let me know?

                  Thanks again!!!

                  Banana Gambler667

                    Gambler667's avatar - shapes swish.jpg

                    Australia
                    Member #166177
                    May 8, 2015
                    29 Posts
                    Offline
                    Posted: November 22, 2016, 5:17 pm - IP Logged

                    Hi Lottolot,

                    Forgot to add this - the images with the settings from the NNL tool. We know every lottery is different but for those using the same type of lottery could be advantageous.

                    Cheers,

                    Gambler667 HyperDance

                      lottolot's avatar - Sphere animated2.gif
                      Tanhauser Gates
                      Holy See (Vatican City State)
                      Member #139281
                      February 18, 2013
                      173 Posts
                      Offline
                      Posted: November 23, 2016, 6:13 pm - IP Logged

                      Hi Lottolot,

                       

                      How many lines have you produced ? Did you play them all ?

                      I was trying to look at Stoopendaals` settings images for his 6/45 lottery here at the forum and I was unable to see them.

                      If anyone can see them could you please let me know?

                      Thanks again!!!

                      Banana Gambler667

                      Hi:

                      With the settings below,I played 8 bets.

                      I generated a lot of bets,and after I filtering them, until only 8

                       

                      Settings for NNLP:

                      My personal6/49 settings:

                      Learning:0,174848

                      Noise:0,176

                      Threshold:0,053731

                      Neurons:77

                      Training data:27

                      The rest of settings: Not used.

                      I hope this helps!!!Cheers

                      Best regards

                      Regards.See Ya!

                        lottolot's avatar - Sphere animated2.gif
                        Tanhauser Gates
                        Holy See (Vatican City State)
                        Member #139281
                        February 18, 2013
                        173 Posts
                        Offline
                        Posted: November 23, 2016, 6:17 pm - IP Logged

                        I REMEMBER SOME USERS WHO SUGGESTED THAT THE STOOPENDAL PROGRAMS HAD SOME TYPES OF VIRUSES. 

                        HE EXPLAINS IT, IN  REFERENCE TO A PICK 3 PROGRAM :

                         

                        "The code of the tool is obfuscated to prevent reverse engeneering (or to make it difficult).

                        Some anti-virus software like Symantec detects obfuscated code as a threat based on certain attributes (They're not telling which ones).

                        http://www.symantec.com/security_response/writeup.jsp?docid=2013-110421-4535-99

                        Some information about obfuscating code: http://en.wikipedia.org/wiki/Obfuscation_%28software%29

                        Disadvantages of obfuscation

                        At best, obfuscation merely makes it time-consuming, but not impossible, to reverse engineer a program.[14] In Java it also limits the use of the Reflection application programming interface on the obfuscated code.[15] Some anti-virus software, such as AVG, will also alert their users when they land on a site with code obfuscated, as one of the purposes of obfuscation can be to hide malicious code. However, some developers may employ code obfuscation for the purpose of reducing file size or increasing security. The average user may not expect their antivirus software to provide alerts about an otherwise harmless piece of code, especially from trusted corporations, so such a feature may actually serve as a deterrent.

                        Obfuscating software

                        A variety of tools exists to perform or assist with code obfuscation. These include experimental research tools created by academics, hobbyist tools, commercial products written by professionals, and open-source software. ABCME is an obfuscation tool that assimilates assembly code to benign software codes.[16] There also exist deobfuscation tools that attempt to perform the reverse transformation.

                        Although the majority of commercial obfuscation solutions work by transforming either program source code,[17][18] or platform-independent bytecode as used by Java[19] and .NET,[20] there are also some that work with C and C++ - languages that are typically compiled to native code, or work directly on compiled binaries."

                         

                        REGARDSSee Ya!

                          Gambler667's avatar - shapes swish.jpg

                          Australia
                          Member #166177
                          May 8, 2015
                          29 Posts
                          Offline
                          Posted: November 24, 2016, 6:42 pm - IP Logged

                          Hi Lottolot,

                          Thanks for sharing your settings. I shall try it, too.

                          Cheers,

                          Gambler667

                          See Ya!Sun Smiley

                            Avatar
                            bgonçalves
                            Brasil
                            Member #92564
                            June 9, 2010
                            2126 Posts
                            Offline
                            Posted: November 25, 2016, 1:30 pm - IP Logged

                            http://articles.adsabs.harvard.edu//full/1990fnmd.book.....C/0000134.000.html

                              lottolot's avatar - Sphere animated2.gif
                              Tanhauser Gates
                              Holy See (Vatican City State)
                              Member #139281
                              February 18, 2013
                              173 Posts
                              Offline
                              Posted: November 25, 2016, 2:52 pm - IP Logged

                              http://articles.adsabs.harvard.edu//full/1990fnmd.book.....C/0000134.000.html

                              FrownBang HeadCrazyROFL

                              Because you have undestood that page,perhaps you can explain it to us... (I can´t).

                              Regards

                                 
                                Page 45 of 46