-**User:** A person seeking family-friendly action movies for a weekend watch party.
...
...
@@ -6,7 +6,7 @@
---
## Workflow
## Workflow Case
### Step 1: Greeting
-**User:** Hello!
...
...
@@ -40,3 +40,49 @@
2.**Filters and recommends movies** based on genre and suitability.
3.**Provides additional insights** like popularity when prompted.
4.**Ends with a polite and open-ended conclusion.**
----
----
# Use Case 2: Model Evaluation Metrics
## Actors:
-**User:** A person interested in understanding the evaluation metrics of a genre prediction model.
-**Chatbot:** Netflix Dataset Chatbot that provides insights into machine learning models and their performance.
---
## Workflow
### Step 1: Greeting
-**User:** Hello.
-**Chatbot:** Hi there! I can explain our data preprocessing steps, show you model metrics, or help with any other data-related insights you might need. What are you interested in today?
---
### Step 2: User Requests Model Evaluation Information
-**User:** Can you tell me about how you evaluate your genre prediction model?
-**Chatbot:** Absolutely! We use several metrics:
1.**Accuracy:** Gives the percentage of correctly predicted genres.
2.**F1-Score:** Balances precision and recall, especially useful if some genres have fewer movies.
3.**ROC-AUC:** Measures how well the model distinguishes between genres.
---
### Step 3: User Asks for Specific Metric Details
-**User:** Can you share the latest accuracy figure?
-**Chatbot:** Our current genre classification model is at about **85% accuracy** across 5 major genres.
---
### Step 4: Conclusion
-**User:** That’s impressive. Thank you!
-**Chatbot:** You’re welcome! Let me know if you need additional model details.
---
## Summary
1.**Chatbot identifies the user's intent** to understand model evaluation metrics.
2.**Explains key evaluation metrics**: Accuracy, F1-Score, and ROC-AUC.
3.**Shares specific metric values** like the latest accuracy figure when prompted.
4.**Ends with a polite and open-ended conclusion**, encouraging further queries.
