Detecting attribute change from trip data
Systems and methods for improving attribute data for a point of interest (POI) are provided. A networked system accesses trip data associated with the POI. The networked system generates, using a processor-implemented clustering algorithm, a first spatial cluster and a second spatial cluster using coordinates corresponding to the POI indicated in the trip data. A centroid for the first spatial cluster and a centroid for the second spatial cluster are identified by the networked system. The networked system determines that a difference in distance between the centroid for the first spatial cluster and the centroid for the second spatial cluster meets or transgresses a centroid distance threshold. In response to the determining, a database is updated to indicate a new attribute for the POI, the new attribute corresponds to an attribute associated with either the first spatial cluster or the second spatial cluster.
1. A system comprising:
one or more hardware processors; and
a memory storing instructions that, when executed by the one or more hardware processors, causes the one or more hardware processors to perform operations comprising:
detecting, by a network system, a potential change in an attribute of a point of interest (POI) that represents a pick-up location or a drop-off location;
based on the detecting, triggering an analysis engine of the network system to perform an analysis on trip data stored at the network system, the analysis engine performing operations comprising:
accessing the trip data associated with the POI, the POI representing the pick-up location or the drop-off location of each trip of the trip data;
based on the accessed trip data, generating, by a clustering module of the analysis engine using a processor-implemented clustering algorithm, a first spatial cluster and a second spatial cluster using coordinates corresponding to the POI indicated in the trip data;
identifying, by the clustering module, a centroid for the first spatial cluster and a centroid for the second spatial cluster; and
determining, by a threshold module of the analysis engine, that a difference in distance between the centroid for the first spatial cluster and the centroid for the second spatial cluster meets or transgresses a centroid distance threshold; and
in response to the determining that the difference meets or transgresses the centroid distance threshold, updating, by the network system, data structures of a data storage to indicate a change in the attribute of the POI, the changed attribute corresponding to an attribute associated with either the first spatial cluster or the second spatial cluster.
2. The system of claim 1 , wherein the operations further comprise, in response to the determining, triggering a verification process to verify the new attribute is accurate.
3. The system of claim 2 , wherein the verification process comprises:
generating a user interface that presents a query regarding verifying the new attribute;
causing the user interface to be presented on a user device of a user that has an association with the POI;
receiving a response to the query via the user interface from the user device; and
using the response to verify the new attribute.
4. The system of claim 1 , further comprising:
based on timestamps from the trip data, determining a time metric for the first spatial cluster and a time metric for the second spatial cluster; and
determining that a difference between the time metric for the first spatial cluster and the time metric for the second spatial cluster meets or transgresses a time threshold,
wherein the updating the database occurs further in response to the difference between the time metric for the first spatial cluster and the time metric for the second spatial cluster meeting or transgressing the time threshold.
5. The system of claim 1 , wherein the generating the first spatial cluster and the second spatial cluster comprises generating the first spatial cluster based on a first time period and the second spatial cluster based on a second time period.
6. The system of claim 1 , wherein the clustering algorithm comprises K means clustering algorithm.
7. The system of claim 1 , wherein:
the coordinates comprise a latitude and a longitude for the POI and the centroid for the first spatial cluster is an average point of the latitude and longitude for the POI in the first spatial cluster and the centroid for the second spatial cluster is an average point of the latitude and longitude for the POI in the second spatial cluster; and
the determining that the difference in distance between the centroid for the first spatial cluster and the centroid for the second spatial cluster meets or transgresses the centroid distance threshold comprising determining that a difference in distance between the average point of the latitude and longitude for the POI in the first spatial cluster and the average point of the latitude and longitude for the POI in the second spatial cluster meets or transgresses the centroid distance threshold.
8. A method comprising:
detecting, by a network system, a potential change in an attribute of a point of interest (POI) that represents a pick-up location or a drop-off location;
based on the detecting, triggering an analysis engine of the network system to perform an analysis on trip data stored at the network system, the analysis engine performing operations comprising:
accessing the trip data associated with the POI, the POI representing the pick-up location or the drop-off location of each trip of the trip data;
based on the accessed trip data, generating, by a processor and using a processor-implemented clustering algorithm, a first spatial cluster and a second spatial cluster using coordinates corresponding to the POI indicated in the trip data;
identifying, by a clustering module of the analysis engine, a centroid for the first spatial cluster and a centroid for the second spatial cluster; and
determining, by a threshold module of the analysis engine, that a difference in distance between the centroid for the first spatial cluster and the centroid for the second spatial cluster meets or transgresses a centroid distance threshold; and
in response to the determining that the difference meets or transgresses the centroid distance threshold, updating, by the network system, data structures of a data storage to indicate a change in the attribute of the POI, the changed attribute corresponding to an attribute associated with either the first spatial cluster or the second spatial cluster.
9. The method of claim 8 , further comprising, in response to the determining, triggering a verification process to verify the new attribute is accurate.
10. The method of claim 9 , wherein the verification process comprises:
causing a user interface to be presented on a user device of a user that has an association with the POI, the user interface presenting a query regarding verifying the new attribute;
receiving a response to the query via the user interface from the user device; and
using the response to verify the new attribute.
11. The method of claim 9 , wherein the verification process comprises transmitting the new attribute to an operator system, an operator of the operator system to verify the new attribute using public domain data.
12. The method of claim 8 , further comprising:
based on timestamps from the trip data, determining a time metric for the first spatial cluster and a time metric for the second spatial cluster; and
determining that a difference between the time metric for the first spatial cluster and the time metric for the second spatial cluster meets or transgresses a time threshold,
wherein the updating the database occurs further in response to the difference between the time metric for the first spatial cluster and the time metric for the second spatial cluster meeting or transgressing the time threshold.
13. The method of claim 8 , wherein the generating the first spatial cluster and the second spatial cluster comprises generating the first spatial cluster based on a first time period and the second spatial cluster based on a second time period.
14. The method of claim 8 , wherein the clustering algorithm comprises K means clustering algorithm.
15. The method of claim 8 , wherein:
the coordinates comprise a latitude and a longitude for the POI and the centroid for the first spatial cluster is an average point of the latitude and longitude for the POI in the first spatial cluster and the centroid for the second spatial cluster is an average point of the latitude and longitude for the POI in the second spatial cluster; and
the determining that the difference in distance between the centroid for the first spatial cluster and the centroid for the second spatial cluster meets or transgresses the centroid distance threshold comprising determining that a difference in distance between the average point of the latitude and longitude for the POI in the first spatial cluster and the average point of the latitude and longitude for the POI in the second spatial cluster meets or transgresses the centroid distance threshold.
16. The method of claim 8 , further comprising:
receiving, by a device interface of the network system, the trip data, the trip data comprising information pertaining to a service provided between the pick-up location and the drop-off location for each trip; and
storing the trip data for later analysis by the network system.
17. The method of claim 8 , wherein the changed attribute comprises a new address of the POI that has moved, a new name of the POI, or a new status for the POI.
18. A machine-storage medium storing instructions that, when executed by one or more processors of a machine, cause the one or more processors to perform operations comprising:
detecting, by a network system, a potential change in an attribute of a point of interest (POI) that represents a pick-up location or a drop-off location;
based on the detecting, triggering an analysis engine of the network system to perform an analysis on trip logs stored at the network system, the analysis engine performing operations comprising:
accessing a plurality of trip logs associated with the POI, the POI representing the pick-up location or the drop-off location of each trip of the plurality of trip logs;
based on the accessed plurality of trip logs, generating, by a clustering module of the analysis engine using a processor-implemented clustering algorithm, a first spatial cluster and a second spatial cluster using coordinates corresponding to the POI indicated in the trip logs;
identifying, by the clustering module, a centroid for the first spatial cluster and a centroid for the second spatial cluster; and
determining, by a threshold module of the analysis engine, that a difference in distance between the centroid for the first spatial cluster and the centroid for the second spatial cluster meets or transgresses a centroid distance threshold; and
in response to the determining that the difference meets or transgresses the centroid distance threshold, updating, by the network system, data structures of a data storage to indicate a new address for the POI, the new address corresponding to a location associated with either the first spatial cluster or the second spatial cluster.
19. The machine-storage medium of claim 18 , wherein the operations further comprise, in response to the determining, triggering a verification process to verify the new address is accurate, the verification process comprising:
causing a user interface to be presented on a user device of a user that has an association with the POI, the user interface presenting a query regarding verifying the new address;
receiving a response to the query via the user interface from the user device; and
using the response to verify the new address.
20. The machine-storage medium of claim 18 , wherein the operations further comprise:
based on timestamps from the trip logs, determining a time metric for the first spatial cluster and a time metric for the second spatial cluster; and
determining that a difference between the time metric for the first spatial cluster and the time metric for the second spatial cluster meets or transgresses a time threshold,
wherein the updating the database occurs further in response to the difference between the time metric for the first spatial cluster and the time metric for the second spatial cluster meeting or transgressing the time threshold.