Detecting attribute change from trip data
Systems and methods for detecting and verifying closed places (e.g., claims no longer in business) from trip data are provided. A networked system accesses trip data associated with the POI. The networked system processes the trip data to generate at least two time buckets based on timestamps from the trip data associated with the POI, and calculates trip counts associated with the POI for each of the time buckets. Using a machine learning algorithm and based on the at least two time buckets, the networked system determines that the trip counts show a decline over time that indicates that the POI is likely closed. In response to the determining, the networked system updates a database to indicate the POI is closed.
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:
triggering an analysis engine to perform a time series analysis on trip data stored at a network system, the analysis engine performing operations comprising:
accessing the trip data associated with a point of interest (POI), the trip data comprising information pertaining to past trips between a pick-up location and a drop-off location;
processing, by a time module of the analysis engine, the trip data to generate two or more time buckets of trips based on timestamps from the trip data associated with the POI, the timestamps indicating a start time or an end time of each trip of the trip data, each of the two or more time buckets of trips being a same duration of time;
calculating, by the time module of the analysis engine, a trip count for each of the two or more time buckets that indicates a number of trips associated with the POI;
based on the trip counts for each of the two or more time buckets, using a machine learning algorithm to determine a trend that predicts when the trip counts are estimated to reach a zero or almost zero threshold indicating that the POI is likely closed; and
in response to a determination that the threshold indicating that the POI is likely closed is met or transgressed, updating, by the network system, data structures of a data storage to indicate the POI is closed.
2. The system of claim 1 , wherein the operations further comprise, in response to the determining, triggering a verification process to verify the POI is closed.
3. The system of claim 2 , 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 whether the POI is closed;
receiving a response to the query via the user interface from the user device; and
using the response to verify whether the POI is closed.
4. The system of claim 1 , wherein the POI is the pick-up location or the drop-off location of each trip of the trip data.
5. The system of claim 1 ; wherein the updating the database to indicate the POI is closed comprises indicating the POT is a seasonal location that closes part of the year.
6. The system of claim 1 , wherein the threshold value comprises a percentage threshold associated with a percentage drop over a period of time.
7. The system of claim 1 , wherein the trend indicates that the POI is only active for a particular period of time of the year.
8. A method comprising:
triggering an analysis engine to perform a time series analysis on trip data stored at a network system, the analysis engine performing operations comprising:
accessing trip data associated with a point of interest (POI), the trip data comprising information pertaining to past trips between a pick-up location and a drop-off location;
processing, using one or more hardware processors, the trip data to generate two or more time buckets of trips based on timestamps from the trip data associated with the POI, the timestamps indicating a start time or an end time of each trip of the trip data each of the two or more time buckets of trips being a same duration of time;
calculating, by a time module of the analysis engine, a trip count for each of the two or more time buckets that indicates a number of trips associated with the POI;
based on the trip counts for each of the two or more time buckets, using a machine learning algorithm to determine a trend that predicts when the trip counts are estimated to reach a zero or almost zero threshold value indicating that the POI is likely closed; and
in response to a determination that the threshold value indicating that the POI is likely closed is met or transgressed, updating, by the network system, data structures of a data storage to indicate the POI is closed.
9. The method of claim 8 , wherein the operations further comprise, in response to the determining, triggering a verification process to verify the POI is closed.
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 whether the POI is closed;
receiving a response to the query via the user interface from the user device; and
using the response to verify whether the POI is closed.
11. The method of claim 8 , wherein the machine learning algorithm is the Markoff chain algorithm.
12. The method of claim 8 , wherein the updating the database to indicate the POI is closed comprises indicating the POI is a seasonal location that closes part of the year.
13. The method of claim 8 , wherein the threshold value comprises a percentage threshold associated with a percentage drop over a period of time.
14. The method of claim 8 , wherein the trend indicates that the POI is only active for a particular period of time of the year.
15. 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:
triggering an analysis engine to perform a time series analysis on trip data stored at a network system, the analysis engine performing operations comprising:
accessing the trip data associated with a point of interest (POI), the trip data comprising information pertaining to past trips between a pick-up location and a drop-off location;
processing, by a time module of the analysis engine, the trip data to generate two or more time buckets of trips based on timestamps from the trip data associated with the POI, the timestamps indicating a start time or an end time of each trip of the trip data, each of the two or more time buckets of trips being a same duration of time;
calculating, by a time module of the analysis engine, a trip count for each of the two or more time buckets that indicate a number of trips associated with the POI;
based on the trip counts for each of the two or more time buckets, using a machine learning algorithm to determine a trend that predicts when the trip counts are estimated to reach a zero or almost zero threshold value indicating that the POI is likely closed; and
in response to a determination that the threshold value indicating that the POI is likely closed is met or transgressed, updating, by the network system, data structures of a data storage to indicate the POI is closed.
16. The machine-storage medium of claim 15 , wherein the threshold value comprises a percentage threshold associated with a percentage drop over a period of time.
17. The machine-storage medium of claim 15 , wherein the trend indicates that the POI is only active for a particular period of time of the year.