0

Dataset contains the features such as description, goal , category etc to predict the probability in decimal such as 0.1,0.8 etc,

Now in the next step need to find out the text words associated with high probability using RNN +LTSM or any other neural network

Please guide with the key steps or the reference sample

Regards, Swati

jaiswati_b
  • 21
  • 3
  • so you want to assess the importance of features (words/text). I think in LSTM text analysis this is not so easy. Please provide a clear description of your data and model. Otherwise it is hard to say what a solution can be. See here for som background: https://datascience.stackexchange.com/q/44644/71442 – Peter May 31 '19 at 11:26
  • Thank You Peter, for the quick response !! Need to extract features in the Description text using RNN/using unsupervised learning and to identify features correlated (may be with feature importance) to success/failure (That indicates the success and failure values in the target variable).. – jaiswati_b May 31 '19 at 11:49

0 Answers0