This repository contains the code for a conference paper "Predicting the football match winner using LSTM model of Recurrent Neural Networks" that we wrote
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
When creating training and test datasets you have used the following code
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]
insteadThe correct version would've been as described below
When modified correctly it only gives 54% accuracy.
Hence the results produced are completely misleading.