Arrival Time for Seattle Rides

Requirements Clarification & Assessment

1. Objective Understanding:

   • Clearly define the primary objective: Develop a model to predict the Estimated Time of Arrival (ETA) for ride requests in Seattle.
   • Understand the business implications of accurate ETA predictions, such as improving customer satisfaction and operational efficiency.

2. Dataset Evaluation:

   • Size & Volume: Assess if 1 million ride journeys are representative of the different traffic patterns and conditions in Seattle.
   • Feature Relevance: Identify key features like time of day, day of the week, weather conditions, and traffic data that might influence ETA.
   • Data Quality: Check for consistency, missing values, and anomalies. Determine how much of the data is usable after cleaning.

3. Performance Metrics:

   • Define what constitutes "reliable accuracy" for the model. Is there a specific RMSE or MAE that the business considers acceptable?
   • Determine the acceptable level of prediction error from a business perspective. How much deviation in ETA is tolerable?

4. Business Context:

   • Understand the business goals and constraints. Are there budgetary or time constraints for model development?
   • Consider the impact of model predictions on user experience and operational decisions.

5. External Factors:

   • Consider external factors like city infrastructure changes or seasonal events that might affect traffic patterns and, consequently, ETAs.