A last mile delivery company that is patnered with motorbike owners and drivers to deliver parcels accross a city has completed more than a million deliveries in less than year, with a fleet of over 1200 riders. The major issue the company has faced as it expands its service, is the suboptimal placement of drivers and clients. This has led to a high number of unfulfilled delivery requests. Using some of it's data, and causal inference we try to understand the primary causes of unfulfilled requests as well as come up with solutions that recommend drivers locations that increase the fraction of complete orders. Since drivers are paid based on the number of requests they accept, the solution will help the business grow both in terms of client satisfaction and increased business.
Causal Inference with Machine learning
When humans rationalize the world, we often think in terms of cause and effect — if we understand why something happened, we can change our behavior to improve future outcomes. Causal inference is a statistical tool that enables our AI and machine learning algorithms to reason in similar ways.