Quantitative Pickup Quality Metric for Uber

Uber
Name
Institution
Due Date
Uber
Create a quantitative pickup quality metric using attributes derived from the passive, active and third-party signals available to Uber. Discuss why your selected attributes represent a robust pickup quality metric. What weights would you assign to the features you chose for your pickup model?
Pickup Satisfaction = Minimize [(Fluctuations between ETA and ATA) + (Driver loops around rendezvous)] + Enhance [(Real-time pruning for parking restrictions, construction, closures, and congestion)] + Reduce [(Customer Complaints)]
A robust pickup metric has to factor in the customers or riders and the drivers. Therefore, there is a need to find common ground between the needs of drivers and riders. The attributes selected for the developed quantitative quality pickup metric entails several attributes, including fluctuations between ETA and ATA, drivers looping around rendezvous, real-time pruning, and the reduction of customer complaints.
The fluctuations between the estimated time of arrival and the actual time of arrival can be quite annoying because of the false sense of hope. Every rider wants to get their ride as fast as possible. However, when placing an order, an expectation is created upon seeing the ETA. However, the chances are high when this keeps fluctuating, and ATA proves to be longer than ETA. The pickup experience would have already been ruined by the time the driver arrived. Additionally, the driver looping around the rendezvous point can also ruin the entire pickup experience. Having already aroused the customer’s expectations, when a driver appears to be circling the rendezvous point without making any headway, it is highly likely that the rider will become frustrated. The app could be showing that the driver is close but never making it to the pickup spot. This attribute is quite crucial as it helps to reveal the weakness in the app’s ability to pinpoint the exact pickup location. The data gathered and collected from this point can be quite crucial in helping to enhance Uber’s pickup experience.
Real-time pruning is another attribute that represents a robust pickup quality metric. This attribute is crucial to both drivers and riders as it helps determine the best and fastest routes, as well as areas with restricted parking spaces. With such information available, it would be easier and quicker for drivers to do pickups and deliver riders to their destinations. Furthermore, the app would direct riders to apt pickup spots where drivers are not limited by parking and residential restrictions.
Finally, a reduction in customer complaints is also crucial. This metric helps to paint a clearer picture of whether customers are satisfied or dissatisfied with an experience. However, it may not have as much weight as the other three attributes because it often implies the other attributes. But, a reduction in customer complaints is an indication of growth and improvement on all other attributes. Therefore, this attribute’s role is twofold and hence its inclusion in the pickup quality metric.
The weights of the pickup model would total 100. Fluctuations between ETA and ATA should be 35%, drivers looping around the rendezvous point 20%, real-time p...