Markov Software


Would anyone be interested in a small utility that I wrote
that uses Markov chains theory to analyse and generate
lotto combinations?

It still in alpha design phase, but it works... kind of :dizzy:

If anyone is interested I might consider sending it to LT so that
he can post/host it here!

The only thing I ask in exchange of using the program is feedback on the results and usage!

Feel free to ask questions...


Hi thornc,

I'm not familiar with Markov, can you shed light on his theory/approach or is there a good link to an explanation?




Man, I had a huge 2000 characters post explaning everything!

But when I pressed "Submit Reply" I got an error/maintenance
message and I lost the post!! :(

I don't have time to write it all again... so in short.

The program takes an input file with the history draws of a lottery and it generates new combinations based on the numbers that are drawed together in the input file (a bit more complicated than this).
The theory behind Markov Chains says that a current event is only based on past occourences. Or something like that, the other explanation was better! :(


Too bad about your post ... had the same problem bfr, what I do now with a 'long' post sometimes is to copy it to Notepad bfr submitting ... saves aggravation.

Am interested to know more when you have time.


Should anyone reading this be current in numbers theory, i would appreciate contact. i am 20 years out of date on the literature yet poring over some of the publications lately, especially the eastern european and russian universities - their marhkov chain stuff is even way beyond now - it seems do-able to come up with the seed. bclc have provided the time their fred machine programme started running and i do have unfettered cpu access to one of the large machines, able to run such a programme, hopefully in some reasonable length of before the end of the century.........cheers.

Last edited by daleks on 11-01-2002 at 12:53 PM outline.xls
Last edited:


I see Ion Saliu is a new member here. I'm certain that he could shed light on this :agree:

It's been a long time since I looked at that math.:sick:



I see Ion Saliu is a new member here. I'm certain that he could shed light on this

Well those of you that know Ion's site, can get my markov program there....
I didn't want to post any link, or contact since it is against this forum rules.



I tried to get markov.exe from Saliu's download site with no luck ... got a 'dead' page ... is that the only source?


reply to Brad!

I tried to get markov.exe from Saliu's download site with no luck ... got a 'dead' page ... is that the only source?

At the moment I'm afraid that the answer is yes! Weird, it seems that Saliu's ftp site is down... maybe it is out of traffic for the month?!

Anyway since direct contacts are forbidden you'll just have to wait a while longer before getting the program :notme:!?



I also downloaded your CoolRevGUI program about a month ago. It's soooo fast. Great utility to have. Thanks.


re: Geenie...

I also downloaded your CoolRevGUI program about a month ago. It's soooo fast. Great utility to have. Thanks. [/B]

:blush: .... No need to thank... Glad to hear people like me software! So you had no problems with it? Some people are reporting that nothing is displayed in the edit field!

Brad, Saliu's ftp site seems to be working now! You and others can give my markov program a try.... but please do report your results!

Ion Saliu

As per thornc, I make MARKOV.EXE available as a free download from my web site. The author is, however, solely in charge. He is the one to ask for technical support, improvements, updates, etc.

• Program name: MARKOV.EXE
Markov chains analysis applied to lotto-6 games
Author: Cristiano Lopes, Portugal

The program takes a lotto-6 data file, performs Markov chains correlating, and outputs a new data file. The output file tries to offer the highest-probability combinations in future lotto-6 drawings. Cristiano asked me to test the program. I did so with a really tough lotto-6 game: Pennsylvania lottery 6/69 game. I tried a few ranges of past draws to input to the application. One of the ranges yielded a result way above random expectation. I created an input file with 35 combinations. They represented draw #3 through draw #37. The program generated an output file of 20 combinations. The last line had only 4 numbers, so I deleted it. The 19-combination output file yielded 2 3-hit combinations within the next two draws. Those were line #1 and line #2 in the data file. They acted as 'future drawings'. That's a total of 38 combinations played. The probability of '3 of 6' in a 6/69 game is '1 in 151'. A total of 302 combinations are needed to get 2 '3 of 6' hits. The tiny Markov program was 7.95 times (302 / 38 = 795%) better than random expectation! That's a huge improvement by any standards. (You may note that '35' is approximately equal to N/2 in a 69-number game. Search for 'wonder grid' and 'CheckGrid632' for similarities in my software. )

•• Running the program

markov < drawings file > output file

Keep one blank spoace between the parameters; do not miss the < and the > signs!
You must create first an input file (named, for example, INPUT6). It must have exactly 6 lotto numbers per line, seaparated by blank spaces (mandatory spaces, not commas, or anything else!).

The program is available as freeware from this FTP site:

Ion Saliu

Topic: Markov.exe need input from users! (from ezboard!)
Author: thornc (Cristiano Lopes)

Hello markov users I'm planning in extendind the current markov program, I have a few ideas but I want input from you the users....

Also I have a question, what do you prefer?
1) GUI based markov program
2) or a console based markov.

The console based version would accept parameter from an input file like Ion's ST files, and the GUI would accept parameters inputed through its window....
No display of the generated is just has to look at the output file with a text editor...

I'm trying to extend the type of games one can use markov on, but for now I'm thinking on only aiming at lotto and perhaps keno, Powerball is to complicated for me since I don't understand the rules....

Comments are welcome and expected!

C. Lopes


Q for tornc:


have my in/out files ready however am unable to start your prog. It's most likely cuz I'm a GUI type guy, has been some time since I used the DOS commands ... never really was proficient with those.

Can you give me a quick example on how to start? (I'll probably kick myself when I see it :dang: ).

TIA :)


Re: Brad


Suppose you created a folder called C:\markov, and you copied the markov.exe and you data file named data into data directory.

What you do is:
*Start a dos command prompt.
*in the command prompt type:
cd c:\markov
* You should be in c:\markov afterwards, then you type:
markov < data > output
* The program should work, and it displays a debug message that you shouldn't worry about. It creates the output file.

Things to note, the input file must be in the form
1 2 3 4 5 6
7 8 9 10 11 12
Most recent draw on the top and each number separated by spaces!
The output can contain duplicate combinations, and usually the
last line has less then 6 numbers and should be deleted!

That's about it! Have fun... and do realize that it's an alpha implementation... meaning it can have bugs and it's not perfect!



thanks for the needed 'refresher', although it smarted a bit I did survive the kick in the pants :D .

Have generated my first output, using 1149 hist. draws yielded ~1000 lines. At first glance most were not ordered (low to high) but that's not a problem, I have a prog that will fix that, am in the process of sorting and analysing them. Even the last line gave 6 numbers. Will keep you posted, let's see if we can get some winners.

Cheers :agree2: