Deep Learning has proven its ability to solve many different problems as handwriting and speech or computer vision. The algorithms are a reproduction of the human brain, which is the most powerful engine. The network may capture the latent structure in any dataset better as a human being possibly could. However, the results seem somehow magical for someone who is not familiar with this class of algorithms. Randomness adds to the dimensionality of a model. This software uses a new model to predict lottery numbers using the history of past draws as a training set. Lotto is very popular and widespread game based on guessing numbers. The lottery principle is simple: people buy tickets that contains a list combinations that bet over a finite set of numbers. A draw happens eventually at a fixed date and time. The gains depend upon how well the ticket combination matches the winning numbers. The jackpot is when the ticket has the winning combination.
Deep Learning
Deep Learning has proven its ability to solve many different problems as handwriting and speech or computer vision. The algorithms are a reproduction of the human brain, which is the most powerful engine. The network may capture the latent structure in any dataset better than a human being possibly could. However, the results seem somehow magical for someone who is not familiar with this class of algorithms. Randomness adds to the dimensionality of a model. This software uses a new model to predict lottery numbers using the history of past draws as a training set. Lotto is a very popular and widespread game based on guessing numbers. The lottery principle is simple: people buy tickets that contain a list of combinations that bet over a finite set of numbers. A draw happens eventually at a fixed date and time. The gains depend upon how well the ticket combination matches the winning numbers. The jackpot is when the ticket has the winning combination.
Model we use
The features retained are, at each draw time, the day, the month, and the year. We use the actual winning numbers in each drawing too. To all, we add the count of times each number emerged during all past draws and the cross presence matrix defined as the number of times every pair of numbers appeared together. The result of that network is the probability of a number appearing in a winning combination in the next draw.
In addition to this network, the software includes another neural network. Based on a history of past draws, this network can tell us how well any combination of numbers relates to previous winning combinations.
