August 2005: A machine learning 3D app to crack into the lotto

Aug. 25th, 2005 15:00 by sdelucaPermalink | TrackBack: http://stephanedeluca.com/trackback/903 — updated on Nov. 18th, 2018 03:51 exists for 13 years & 3 months ago - .

During the summer 2005, I spent a month working on a way to improve my chances to win the French lottery and in August, I came up with SdlLoto.

SdlLoto: a realtime 3D visualisation with WarStation™ / Java

I used the WarStation port to Java I completed in July to develop SdlLoto.

I thought I could find a 3D visualisation that would help me in developing ideas I had.

Failling to find visual patterns

I initially thought I could find visual patterns in series of wining number, but I get to nowhere.

Machine learning: neural network and DNA-programming

Several years ago, I had explored genome programming on my HP4/CV in order to recognise letter glyphs.

For the lotto, I wanted to simulate multiple ways to draw 6 numbers and test it against all the previous actual wining draw I had in database.

I created millions of players, each picking a drawing method, and generated 1024 generations. Because the computing time was long, I made a server version of the sw and ran it on a server during the night. Once the best guess was ready I could run the 3D client version on my computer, get the guess numbers and play then for real.

In order to help tracing the whole process, I visualised the multiple genomes as a rolling bitmap image which I displayed at the bottom of the screen:

My conclusion was I really thrived to work on such a subject and learned tons of stuffs. But I never won the lottery though. No problem.