H2o Model Classification - Confusion Matrix Vs AUC

I am new to H2o and I am having trouble with AUC and Confusion Matrix/Accuracy

I have a classification model using H2o in Python for which the AUC = 71%

But the accuracy based on confusion Matrix is only 61%. I Understand that confusion matrix is based on threshold = Max F1.
Also when I try to get the predicted values for test data the accuracy is only 61%

How do I determine for which threshold the accuracy will be 71%

© Copyright 2013-2019 Analytics Vidhya