-2

I am getting good accuracy metrics around 80 with precision =66, recall =37, F1 =47. How can I improve precision, and recall metrics in anomaly detection scenarios.. any suggestions?

user12
  • 171
  • 8
  • If your F1 is 47 and your accuracy is 80, then you have considerable class imbalance, and should not be using the accuracy score at all - it is too much influenced by the size of the majority class. – Jon Nordby Feb 02 '23 at 22:12

1 Answers1

0

I think this ways will help you :

  1. Feature engineering
  2. Use ensemble methods
  3. Adjusting thresholds
  4. Collect more data
  5. Use data augmentation and oversampling
  6. Use a different algorithm, such as autoencoders or one-class SVM
  7. Tune the hyperparameters
Nick NaSvlishvili
  • 1
  • Your answer could be improved with additional supporting information. Please [edit] to add further details, such as citations or documentation, so that others can confirm that your answer is correct. You can find more information on how to write good answers [in the help center](/help/how-to-answer). – Community Jan 22 '23 at 19:43