Hi, I'm currently looking into this project and it would be very nice to be able to play around with it. However, this isn't going so well since I don't know which versions of the libraries were used during the project. Could you provide me with this information?

how can i use it to predict a new game? i do not know the new game data.

There is something i do not quite understand. When you append last standings, you actually assign to "playing_statistics_4" and all others below "playing_statistics_3".
Shouldnt it be 3 to 3, 4 to 4, etc. ?

playing_statistics_1 = get_last(playing_statistics_1, Standings, 0)

playing_statistics_2 = get_last(playing_statistics_2, Standings, "15")
playing_statistics_3 = get_last(playing_statistics_3, Standings, "14")
playing_statistics_4 = get_last(playing_statistics_3, Standings, "13")
playing_statistics_5 = get_last(playing_statistics_3, Standings, "12")
playing_statistics_6 = get_last(playing_statistics_3, Standings, "11")
playing_statistics_7 = get_last(playing_statistics_3, Standings, "10")
playing_statistics_8 = get_last(playing_statistics_3, Standings, "9")

When creating training and test datasets you have used the following code

x_train, y_train = dataTrain.iloc[:,:28].values,dataTrain.iloc[:,28:].values
x_train=np.reshape(x_train,(1860,28,1))
x_test, y_test = dataTest.iloc[:,:28].values,dataTest.iloc[:,28:].values
x_test=np.reshape(x_test,(800,28,1))

dataTrain.iloc[:,:28] this is completely wrong. You are still passing the original FTR column(Which is actually the current match result), which is the 0th column.

It should've been dataTrain.iloc[:,1:28] instead

The correct version would've been as described below

x_train, y_train = dataTrain.iloc[:,1:28].values,dataTrain.iloc[:,28:].values
x_train=np.reshape(x_train,(1860,27,1))
x_test, y_test = dataTest.iloc[:,1:28].values,dataTest.iloc[:,28:].values
x_test=np.reshape(x_test,(800,27,1))

When modified correctly it only gives 54% accuracy.

Hence the results produced are completely misleading.

I have tried running through dataCleaning.ipynb and I am not getting quite the same end csv file as you did. And with my new csv there also isn't good prediction percentage in LSTM.ipynb. I also tried fixing what I thought was wrong with dataCleaning file, but no luck. Is there any chance you can share the original code you used for cleaning up the data, so you got such good end results?