We are creating ML models dynamically in the App and using the model within the device for prediction purpose.
ML model is generated by taking the user content in the app. When some new data is entered by user we take the entire user content and generate the model again.
Please let me know creating ML models this way is this right approach?
The best approach would be to use the new CoreML MLUpdateTask APIs for dymaically updating models with new data. These were released for WWDC '19. More information can be found here: https://developer.apple.com/documentation/coreml/mlupdatetask