Vehicle gateway device and interactive cohort graphical user interfaces associated therewith
A system receives vehicle metric data from a gateway device connected to a vehicle. The vehicle gateway device gathers data related to operation of the vehicle and/or location data. The system receives data from multiple vehicles and multiple fleets. The system uses machine learning to identify cohorts for fleets. The system calculates metrics for fleets and benchmarks for the cohorts. The system presents the metrics and benchmarks in a graphical user interface.
1. A system comprising:
a computer readable storage medium having program instructions embodied therewith; and
one or more processors configured to execute the program instructions to cause the one or more processors to:
receive vehicle metric data associated with a plurality of vehicles for a first fleet;
determine a plurality of segmentation attribute values for the first fleet from the vehicle metric data, the plurality of segmentation attribute values comprising:
a first attribute value indicating a distance driven per vehicle,
a second attribute value indicating a trip length, wherein the trip length indicates a distance, and
a third attribute value indicating a vehicle type composition of the first fleet;
determine a first cohort for the first fleet based at least in part on a combination of the determined plurality of segmentation attribute values; and
present, in a graphical user interface, a visualization that indicates a metric for the first fleet relative to a benchmark for the first cohort.
2. The system of claim 1 , wherein the metric is associated with at least one of harsh acceleration events, harsh braking events, or speeding.
3. The system of claim 1 , the visualization comprises at least a graph and each of the metric and the benchmark are visually represented on the graph.
4. The system of claim 1 , wherein determining the plurality of segmentation attribute values further comprises:
calculating a value representing the vehicle type composition of the first fleet based at least in part on vehicle gateway devices with respective connections to the plurality of vehicles from the first fleet; and
assigning the value to the third attribute.
5. The system of claim 1 , wherein the one or more processors are configured to execute further program instructions to cause the one or more processors to:
receive, from a tree-based machine learning model, a ranking of an initial set of segmentation attribute values; and
select, from the initial set of segmentation attribute values, the plurality of segmentation attribute values based at least in part on the ranking.
6. The system of claim 5 , wherein selecting the plurality of segmentation attribute values further comprises:
clustering the initial set of segmentation attribute values for a plurality of fleets that results in a cluster, wherein boundary values for the cluster define the first cohort.
7. A method comprising:
receiving vehicle metric data associated with a plurality of vehicles for a first fleet;
determining a plurality of segmentation attribute values for the first fleet from the vehicle metric data the plurality of segmentation attribute values comprising:
a first attribute value indicating a distance driven per vehicle,
a second attribute value indicating a trip length, wherein the trip length indicates a distance, and
a third attribute value indicating a vehicle type composition of the first fleet;
determining a first cohort for the first fleet based at least in part on a combination of the determined plurality of segmentation attribute values; and
presenting, in a graphical user interface, a visualization that indicates a metric for the first fleet relative to a benchmark for the first cohort.
8. The method of claim 7 , wherein the metric is associated with at least one of harsh acceleration events, harsh braking events, or speeding.
9. The method of claim 7 , the visualization comprises at least a graph and each of the metric and the benchmark are visually represented on the graph.
10. The method of claim 7 , wherein determining the plurality of segmentation attribute values further comprises:
calculating a value representing the vehicle type composition of the first fleet based at least in part on vehicle gateway devices with respective connections to the plurality of vehicles from the first fleet; and
assigning the value to the third attribute.
11. The method of claim 7 , further comprising:
receiving, from a tree-based machine learning model, a ranking of an initial set of segmentation attribute values; and
selecting, from the initial set of segmentation attribute values, the plurality of segmentation attribute values based at least in part on the ranking.
12. The method of claim 11 , wherein selecting the plurality of segmentation attribute values further comprises:
clustering the initial set of segmentation attribute values for a plurality of fleets that results in a cluster, wherein boundary values for the cluster define the first cohort.
13. A system comprising:
a computer readable storage medium having program instructions embodied therewith; and
one or more processors configured to execute the program instructions to cause the one or more processors to:
receive vehicle metric data associated with a plurality of vehicles for a first fleet;
determine a plurality of segmentation attribute values for the first fleet from the vehicle metric data, the plurality of segmentation attribute values comprising:
a first attribute value indicating a trip length, wherein the trip length indicates a distance,
a second attribute value indicating a vehicle type composition of the first fleet, and
a third attribute value indicating a type of geography;
determine a first cohort for the first fleet based at least in part on a combination of the determined plurality of segmentation attributes; and
present, in a graphical user interface, a visualization that indicates a metric for the first fleet relative to a benchmark for the first cohort.
14. The system of claim 13 , wherein the metric is associated with at least one of harsh acceleration events, harsh braking events, or speeding.
15. The system of claim 13 , the visualization comprises at least a graph and each of the metric and the benchmark are visually represented on the graph.
16. The system of claim 13 , wherein determining the plurality of segmentation attribute values further comprises:
calculating a value representing the vehicle type composition of the first fleet based at least in part on vehicle gateway devices with respective connections to the plurality of vehicles from the first fleet; and
assigning the value to the second attribute.
17. The system of claim 13 , wherein determining the plurality of segmentation attribute values further comprises:
calculating a value representing the type of geography based at least in part on the plurality of vehicles from the first fleet that started or ended a trip in a city from a plurality of predetermined cities; and
assigning the value to the third attribute.
18. The system of claim 13 , wherein the one or more processors are configured to execute further program instructions to cause the one or more processors to:
receive, from a tree-based machine learning model, a ranking of an initial set of segmentation attribute values; and
select, from the initial set of segmentation attribute values, the plurality of segmentation attribute values based at least in part on the ranking.
19. The system of claim 18 , wherein selecting the plurality of segmentation attribute values further comprises:
clustering the initial set of segmentation attribute values for a plurality of fleets that results in a cluster, wherein boundary values for the cluster define the first cohort.