Rider Attribute Matching for Trustworthy Shared Mobility Pooling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Shared mobility platforms face challenges in creating comfortable and trustworthy experiences for riders in pooling situations, as strangers are often paired without considering their compatibility.
Innovation Solution
The development of a computing platform that profiles riders based on their attributes and preferences, allowing the platform to match riders who share similar interests, preferences, or behaviors, thereby enhancing the in-vehicle experience and building trust.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If pooling services are introduced to pick up multiple individuals in similar directions, then efficiency on the road is improved, but rider comfort and trust deteriorate due to incompatible riders being paired together
Solution Approach 1:
The system changes the parameter of rider matching from random or location-based to attribute-based compatibility scoring. By introducing propensity scores that quantify compatibility between riders based on their attributes (music preferences, temperature preferences, lifestyle characteristics), the system transforms the matching process to simultaneously optimize for both efficiency (pooling) and trust (compatibility).
Solution Approach 2:
The system implements feedback mechanisms where rider attributes, preferences, and compatibility scores are continuously collected and used to improve future matching decisions. The propensity score model learns from past rider interactions and feedback to refine compatibility assessments, ensuring that pooling services maintain both efficiency and rider trust over time.
2Productivity
If pooling services are introduced to pick up multiple individuals in similar directions, then efficiency on the road is improved, but rider comfort deteriorates due to incompatible riders being paired together
Solution Approach 1:
The system changes the parameter of rider matching from random or location-based to attribute-based compatibility scoring. By introducing propensity scores that quantify compatibility between riders based on their attributes (music preferences, temperature preferences, lifestyle characteristics), the system transforms the matching process to simultaneously optimize for both efficiency (pooling) and comfort (compatibility).
Solution Approach 2:
The system performs preliminary actions by collecting rider attributes, preferences, and compatibility information before the actual pooling assignment. By pre-calculating propensity scores and identifying compatible rider pairs in advance, the system ensures that efficiency improvements from pooling do not compromise rider comfort during the actual shared ride experience.
3Reliability
If rider profiling and matching based on attributes is implemented, then rider trust and compatibility are improved, but platform complexity increases
Solution Approach 1:
The system segments the complex rider matching problem into manageable components: attribute collection, propensity score calculation, compatibility assessment, and assignment optimization. By dividing the platform functionality into these distinct modules, the system can improve trust through detailed profiling while managing complexity through structured, separable processing steps.
Solution Approach 2:
The system introduces propensity scores as an intermediary metric that mediates between raw rider attributes and final pooling assignments. This intermediary layer simplifies the complexity by providing a single compatibility score that encapsulates multiple attribute comparisons, making the matching process more manageable while still capturing nuanced rider compatibility.
4Reliability
If rider profiling and matching based on attributes is implemented, then rider compatibility is improved, but data collection requirements increase
Solution Approach 1:
The system implements multi-functional data collection where the same data infrastructure serves multiple purposes: basic ride matching, compatibility assessment, propensity score calculation, and continuous model improvement. By making the data collection system universal and multi-functional, the platform can gather comprehensive rider attributes without proportionally increasing data management complexity.
Solution Approach 2:
The system merges the collection of rider attributes, preferences, and behavioral data into a unified profiling framework. By combining these previously separate data collection efforts into a single integrated system, the platform improves rider compatibility assessment while avoiding the multiplicative increase in data management complexity that would result from separate collection systems.
Data Source
AI summary
Systems and method are described for receiving, by a computing platform, information about a first user of a shared mobility service, generating, based on the information about the first user, a first user profile comprising one or more first user attributes, comparing the one or more first user attributes to one or more second user attributes of a second user profile associated with a second user of the shared mobility service, and based on the comparison, causing a vehicle carrying the second user to pick up the first user.


