Feedback Flow
The feedback flow allows supervisors to correct any wrong predictions made by the model. This corrected data will be pulled by the feedback job running in the OCI Data Science. This job uses this delta with the current training data and trains a new model. This ensures continuous learning and improvement of the model.
You can provide the feedback using the following editing capabilities of B2C Reports.
Inline Edit
You can update a single row inline using the “Wrapped Chat Sentiments Report”.
Multi Edit
You can select multiple rows and open them for editing in the “ChatAIPredictionInfo” workspace. To use this feature, you must enable multi edit for “ChatAIPredictionInfo” in the user profile.