Neural Networks and the applicability to lotteries has been discussed many times here on Lottery Post.

Here some comments on NN here on Lottery Post of the past years: 

"You are quite correct in your comments that neural networks will not predict the winning numbers everytime. They are however very powerful prediction tools that when used with other ai toolsets can reduce your odds and give you more winnings than other methods."

"If the lottery is not random enough they might be able to find a pattern if not, it's just like guessing"

"Most of the work of neural networks is going into pattern recognition and simulations. Neural networks are trained rather than programmed, and potentially will have the most adaptability of any expert system, but like humans they can make mistakes."

"Neural networks are particularly adept at solving problems that cannot be expressed as a series of steps. Neural networks are particularly useful for recognizing patterns, classification into groups, series prediction and data mining."

"There is no such thing as AI or NI when it comes to lotteries, anyone saying something different I challenge them to prove it"

"AI and NN along with many other methods of prediction can be applied to lotteries, just don't expect
them to work. I have written at least a dozen of each and the lottery is just too random. Trying to
predict the lottery is a waste of time IMHO but that does not mean that we can't play smarter. Study
the data and then make your best guess. Forget the odds, don't apply to much math and trust your
gut instincts. AI and NN can be used to make forecast for some events like sales, stocks, profits etc...
but these events are not based on random. Math can be used to test the randomness of a game but
it will never be able to predict random"

The last couple of months I did a research on this subject and wrote a simple program (freeware) using a neural network generating lottery picks (predictions?) using the history draw results of a lottery game (via import feature in the tool).

So now you have the opportunity testing a Neural Network algorithm for your lottery game(s) 

Information and instructions can be found in the tool.

You can download tool here: http://intelbet.somee.com/tools/nnlp.rar (zipped file)  or  http:/intelbet.somee.com/tools/nnlp.exe (exe file)

Some screen shots (From Windows 10):

Generate Picks

Generate Picks 2

Neural Network Settings

Note: I'm not asserting you can predict the/some winning numbers for you lottery game with this tool.

About the tool:

- Obusfacted with Confuserex

- No installation required, just put the executable somewhere

- No changes are made to your registry

Good luck!

Error Message

ANN_LOT stopped

Thanks

tokecap, 

What does the error message say?

System Requirements for the tool 

• Windows XP, Vista, Windows 7, Windows 10
• .NET Framework 4 or higher

With the following command line you can check which .NET Framework versions are installed on your computer:

 dir %WINDIR%\Microsoft.Net\Framework\v*

Link does not work.

Hi CARBOB,

I'm not able to create a valid downloadlink here to the tool; http://lotterypost.com is automatically put in front of my download link when creating one...

Copy one of these links in your browser's address bar:

http:/intelbet.somee.com/Tools/NNLP.rar

http:/intelbet.somee.com/Tools/NNLP.exe

Got it, thanks. Nice job.

Update .NET Framework 4 or higher

Got it, thanks

Tokecap

Hi,

Both Bitdefender and Mcafee detect that these programs contain a virus.

Spot9

I have Windows Defender and it never identified a virus.

I have McAfee too and it says it contains virus and won't even let me override it. Whatever it is, don't download it unless you want Your laptop to crash! Stoopendaal you can do better than this! Thanks!

The application has been obuscated (its content is scrambled and compressed) with the obfuscator tool 'ConfuserEx'.

It's a known issue some virus scanners can give some false positives for applications obfuscated with this tool:

https://github.com/yck1509/ConfuserEx/issues/17

https://github.com/yck1509/ConfuserEx/issues/180

I'll try to fix this.

I created a new version (1.1) of the application (also obfuscated now without the compressing packer option).

http:/intelbet.somee.com/Tools/NNLP.rar

http:/intelbet.somee.com/Tools/NNLP.exe

I tested this version of the application with different virus scanners and one virus scanner (of the 57 virus scanners) (Qihoo-360) found a 'virus'.

McAfee, Symantect etc didn't detect a ' virus'  in the application.

You can do the online virus scan here: https://www.virustotal.com

Thanks. I'll check it out.

Any specially recommended settings for pick 5, 6 and 7 and keno?

Getting a caution from Windows 10 about running the executable. May drop back to Win7 and see what happens. Don't want to put it in a new installation of Windows 10 until I see what it is and what it does.

OK, now it is working! Thanks stoopendaal! I read the intro and it is confusing, so here is a couple of questions for you:

1- Can this software be saved on the desktop? If so where is the "save as" button?

2- How can we use this software to win the BIG MM and PB jackpots? And more importantly, how long do I have to wait before I win the huge jackpots?

3- When you "start the training" it goes on a loop forever unless you stop it? What are the total error, average error, etc... and how can I use this information to win the afore mentioned jackpots?

That is all the questions I have for now, so thanks for your understanding and answering the questions in advance!

Got it, thank you so much!!!

For your game of Viking Lotto, you used 148 in history.

For your game of Keno, you used 32 in history.

One question: Based on your experiences, do you think how many history data should be good

for Keno when you're using NNRP 3.0? Thanks.

Is anyone aware of intelbet's commercial programms ? On its site it states there's both , though only freeware can be found.

  Me too because we should find the Menus from the commercial one.

Another small win. This time 2x4/7 on Saturday Lotto. I played 20 lines/bets generated by NN_PRED 3.0, which cost 100 NOK(Norwegian kroner), while i won 2x45 NOK. I won back 90% of my bet.

I used jlg99's settings for lotto.

first small win using the same setting as jlg99's posted by millionswanted. 1 line 6/8 and another 1 7/10 (ON keno) 

I played the same numbers for 4 draws. will run NN_PRED again and will probably play the numbers for 10 draws. 

cheers!

Hi

thanks for your tests

That make me feel to challenge myself(lol)

So I took back NNpred 30, and I filled it with 30 keno Lines, With these settings:

HNeur / 1225

Max it /100

Train res /12 or 24

inp siz/ 1 or 2

rprop 0,0008

PRED:10

rPROP max  80

then when finshed copy / past the 10 results in RNG MP

with the settings size from 4 to ....

Check latest :9

result to generate I use 3 for testing

Match from 3 (if size=4/5/6) 4 (if size over 6)

result Meet cond =6

I was surprised by the results .. try and let me know

Good night

I see a problem, the match results it's based on is not the real history of the game, just some predictions from NN_PRED.

I don't see any problems. The forecast from the forecast sometimes gives a good result.

will try this out! thanks!

anyone having luck with markov chain generator lately?

I am trying to get the hang of RNG_MP 1.0 and my experience so far is it's better with fewer Draw Results than many. Fewer means less than 11 and sometimes as low as 6.

I hope to see a version 2 of RNG_MP which is capable of using multiple CPU cores, rather than one, perhaps in 64 bit.

No Luck with RNG_MP here. at best I might get 3-6 Match_combinations if I'm lucky, that's with using 11 latest draw results

It's very hard to find correct settings. It's  not possible to get as good results as Match Results shows, most of the time.

The basic rules and settings for working with RNG_MP are described briefly by me in previous posts. There are some changes. I used drop-down databases:
79 65 18 46 50 45 24 17 21 36 10 38 26 72 28 4 67 74 7 23
6 44 79 55 38 2 75 45 32 3 69 19 17 53 54 18 42 35 65 27
44 80 7 2 49 76 33 6 70 74 56 34 8 1 15 13 36 21 60 65
but the program converts this database as it grows:
4 7 10 17 18 21 23 24 26 28 36 38 45 46 50 65 67 72 74 79
2 3 6 17 18 19 27 32 35 38 42 44 45 53 54 55 65 69 75 79
1 2 6 7 8 13 15 21 33 34 36 44 49 56 60 65 70 74 76 80
as a result, the forecast is the same for different databases.
I noticed a possible error. The last draw from the top, with the same settings, leaving the last draw from the top, change the base, then the forecast does not change...
I agree with the observation of MillionsWanted, 6 Draw very often give a good forecast. It is difficult to choose the exact settings, and even more difficult to determine the winning numbers, because I play from 5 to 10 combinations of 5-6 numbers.
2.05.20. 2 by 3\5 1- 4 out of 5 Forecast from forecast 2- 3 out of 5 and 2- 4 out of 5
5.05.20. 3 - 3\5 2 - 4\5
6.05.20. 2 - 3\5 2 - 4\5 1 - 5\5
7.05.20. 1 - 3\5
8.05.20. 3 - 3\5