Metrics for presenting RNN/LSTM result


I am working on a two different architecture based on LSTM model to predict the users next action based on the previous actions. I am wondering, what is the best way to present the result? Is it okay to present only the prediction accuracy? Or Should I use other metrics? I found a paper using top_K_accuracy where on a different paper I found AUC of ROC. Overall, I want to know what is the state of art of presenting prediction accuracy based on LSTM model.

Bloodstone Programmer

Posted 2019-01-20T10:04:19.120

Reputation: 180



There really is nothing special about LSTMs when it comes to classification and metrics. So your question should be what metrics are good for multi-class classification. Both accuracy and auc works. Another metric that is good here is Matthew's Correlation Coefficient (MCC) which is similar to F1 score for a binary problem.

Simon Larsson

Posted 2019-01-20T10:04:19.120

Reputation: 3 498