Сonsider an example of football game predicting.

As factors affecting the outcome of the game, we will use:

  • home or away game;

  • number of yellow cards received in the previous game;

  • number of main players who will miss the next game

  • interval in days between the upcoming and the previous game;

  • current place in the standings;

  • place of opposing team in the standings;

  • the bad weather on match day

Let's create an Excel file with historical data, on which the neural network will be trained and make a prediction for the next game.

Add column names:

Fill in the first line with data which are known before the game:

  • home game = Yes;

  • the number of yellow cards received in the previous game = 0;

  • the number of main players who will miss the next game = 0

  • the interval in days between the upcoming and the previous game = 3;

  • current place in the standings = 7;

  • place of opposing team in the standings = 16;

  • the bad weather on match day = Yes.

Then the value in the Result column will contain the outcome of the game for which the above factors were described.

Let's fill in similarly the rest lines of the file:

The lines, from the first to the penultimate one, are the traning data for the neural network.

The last line of the file contains the known factors before the future game, for which the neural network will make a prediction:

The Result field is empty. We don’t know its value and this is exactly the value that the neural network will predict.

Now save the file in csv format:

A similar file can be created in a simple text editor:

Now, when the data file is ready, let's load it into the forecasting service:

Expecting the result of processing:

The training of the neural network was completed and we have received a prediction for the next game:

  • Prediction - the predicted result of the next match (draw, win or lose);

  • Estimated accuracy of prediction - the percentage of correct predictions of the next matches on the test data.