Optimizing pickup locations for transportation requests based on context information

1. A method comprising:

receiving a session indicator and a device-based location associated with a requestor computing device;

identifying, by one or more computer processors, context information associated with the session indicator and the device-based location wherein identifying the context information comprises:

identifying user-specific information by accessing a transportation request history comprising a history of pickup locations associated with a user identifier associated with the session indicator; and

identifying location-specific information by accessing a transportation matching system history comprising previous transportation requests from other users within a threshold distance of the device-based location;

based on the context information associated with the session indicator and the device-based location, generating a confidence score indicating a level of confidence of a potential pickup location corresponding to the session indicator; and

determining a pickup location for the session indicator based on the confidence score associated with the potential pickup location.

2. The method as recited in claim 1 , wherein receiving the device-based location corresponding with the requestor computing device comprises receiving one or more of a GPS location from the requestor computing device or receiving an indication of a user-selected location.

3. The method as recited in claim 1 , further comprising:

identifying one or more correlations between the identified context information and the device-based location; and

for each of the identified one or more correlations:

assigning a value to the correlation,

determining a strength of the identified correlation, and

assigning a weight value based on the strength of the correlation; and

combining each of the one or more weighted values to generate the confidence score.

4. The method as recited in claim 3 , wherein:

the value assigned to the correlation represents how indicative the correlation is that the device-based location is a potential pickup location; and

the weight assigned to the value represents a number of times the correlation is identified for the context information and the device-based location.

5. The method as recited in claim 1 , wherein determining the pickup location associated with the session indicator comprises:

determining that the generated confidence score exceeds a predetermined threshold; and

determining the pickup location based on the generated confidence score exceeding the predetermined threshold.

6. The method of claim 1 , wherein the transportation request history further comprises a history of destination locations associated with the user identifier.

7. The method of claim 1 , wherein the transportation request history further comprises a history of transportation durations associated with the user identifier.

8. The method of claim 1 , wherein the transportation matching system history further comprises a history of destination locations within a threshold distance of the device-based location.

9. A computing device comprising:

at least one processor; and

at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the computing device to:

receive a session indicator and a device-based location associated with a requestor computing device;

identify context information associated with the session indicator and the device-based location wherein identifying the context information comprises:

identifying user-specific information by accessing a transportation request history comprising a history of pickup locations associated with a user identifier associated with the session indicator; and

identifying location-specific information by accessing a transportation matching system history comprising previous transportation requests from other users within a threshold distance of the device-based location;

based on the context information associated with the session indicator and the device-based location, generate a confidence score indicating a level of confidence that a potential pickup location corresponding to the session indicator; and

determine, based on the confidence score, a pickup location associated with the session indicator.

10. The computing device as recited in claim 9 , wherein receiving the device-based location corresponding with the requestor computing device comprises receiving one or more of a GPS location from the requestor computing device or receiving an indication of a user-selected location.

11. The computing device as recited in claim 10 , further storing instructions thereon that, when executed by the at least one processor, cause the computing device to:

identify one or more correlations between the identified context information and the device-based location; and

for each of the identified one or more correlations:

assign a value to the correlation,

determine a strength of the identified correlation, and

assign a weight the value based on the strength of the correlation; and

combine each of the one or more weighted values to generate the confidence score.

12. The computing device as recited in claim 11 , wherein:

the value assigned to the correlation represents how indicative the correlation is that the device-based location is a potential pickup location; and

the weight assigned to the value represents a number of times the correlation is identified for the context information and the device-based location.

13. The computing device as recited in claim 12 , wherein determining the pickup location associated with the session indicator comprises:

determining that the generated confidence score exceeds a predetermined threshold; and

determining the pickup location based on the generated confidence score exceeding the predetermined threshold.

14. The computing device of claim 9 , wherein the transportation request history further comprises a history of destination locations associated with the user identifier.

15. The computing device of claim 9 , wherein the transportation request history further comprises a history of transportation durations associated with the user identifier.

16. The computing device of claim 9 , wherein the transportation matching system history further comprises a history of destination locations within a threshold distance of the device-based location.

17. A non-transitory computer readable medium comprising instructions that, when executed by at least one processor, cause a computer device to:

receive a session indicator and a device-based location associated with a requestor computing device;

identify context information associated with the session indicator and the device-based location wherein identifying the context information comprises:

identifying user-specific information by accessing a transportation request history comprising a history of pickup locations associated with a user identifier associated with the session indicator; and

identifying location-specific information by accessing a transportation matching system history comprising previous transportation requests from other users within a threshold distance of the device-based location;

based on the context information associated with the session indicator and the device-based location, generate a confidence score indicating a level of confidence that a potential pickup location corresponding to the session indicator; and

determine, based on the confidence score, a pickup location associated with the session indicator.

18. The non-transitory computer readable medium as recited in claim 17 , wherein receiving the device-based location corresponding with the requestor computing device comprises receiving one or more of a GPS location from the requestor computing device or receiving an indication of a user-selected location.

19. The non-transitory computer readable medium as recited in claim 18 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:

identify one or more correlations between the identified context information and the device-based location; and

for each of the identified one or more correlations:

assign a value to the correlation,

determine a strength of the identified correlation, and

assign a weight the value based on the strength of the correlation; and

combine each of the one or more weighted values to generate the confidence score.

20. The non-transitory computer readable medium as recited in claim 19 , wherein:

the value assigned to the correlation represents how indicative the correlation is that the device-based location is a potential pickup location; and

the weight assigned to the value represents a number of times the correlation is identified for the context information and the device-based location.