Hong KongLogistics and transport2025 – ongoingGoGoX
Real-time prediction for driver order assignment
GoGoX cut driver subsidies by 42% after its order assignment algorithm began predicting driver earnings and order demand
Problem
GoGoX guarantees a minimum income to some drivers and pays subsidies when their earnings fall short. The company wanted those drivers to complete more of its own business orders while still earning the guaranteed amount.
Approach
GoGoX built machine-learning models that predict expected earnings for drivers in its order assignment project and the demand for GoGoX business orders. It feeds them with a real-time data pipeline on Google Cloud, so the models train on current data. The company tracks the subsidies paid, the business orders drivers complete and the order incentives it spends.
Results
Takeaway
GoGoX judged the new algorithm on three business measures: subsidies, orders served and incentives. The company did not say how long it measured them or against which baseline.
Categories
- Industry
- Logistics and transport
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and MLOptimization
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Vendor case study
Sources
Source summaries
Google Cloud's customer story describes how the Hong Kong logistics company GoGoX built a real-time data pipeline to train models that predict driver earnings and order demand. It reports a 42% drop in driver subsidy, a 96% rise in business orders served by assignment drivers and a 30% drop in total business-order incentive. The page carries no date; the Internet Archive first saved it on July 17, 2025.
Full details are in the original sources.
