Systems and methods for automated trade-in with limited human interaction

1. A method comprising:

receiving a first indication that a use period of a vehicle associated with a user has started;

receiving, based on the first indication, preliminary data for the vehicle associated with the user;

receiving, from a device associated with the user, a second indication that the use period has ended;

receiving, in response to the second indication and from one or more image sensors, first data comprising:

vehicle-specific identifying information of the vehicle, and

multimedia content showing a first aspect of the vehicle;

creating a feature vector comprising the first data;

inputting the feature vector into a machine learning algorithm corresponding to the vehicle-specific identifying information of the vehicle associated with the user;

determining, using the machine learning algorithm, an instance of damage to the vehicle associated with the user based on the first data and the preliminary data; and

sending, to a mobile device associated with the user, an indication of the instance of damage to the vehicle associated with the user.

2. The method of claim 1 , further comprising:

receiving, from the mobile device associated with the user, a request to begin a determination of the instance of damage to vehicle associated with the user;

receiving, from the mobile device associated with the user, a second data comprising multimedia content showing a second aspect of the vehicle associated with the user; and

determining an initial damage estimate for the vehicle associated with the user.

3. The method of claim 2 , wherein the feature vector further comprises the second data.

4. The method of claim 1 , further comprising:

prior to the inputting the feature vector into the machine learning algorithm, identifying the machine learning algorithm based on the vehicle-specific identifying information of the vehicle associated with the user.

5. The method of claim 1 , further comprising,

prior to the use period, training the machine learning algorithm using reference vehicle-specific identifying information and reference data of one or more aspects of a plurality of reference vehicles that are not associated with the user.

6. The method of claim 5 , wherein the training the machine learning algorithm further comprises:

receiving, for each of the plurality of reference vehicles that are not associated with the user, reference vehicle-specific identifying information and reference data of the first aspect of a given reference vehicle of the plurality of reference vehicles;

receiving, for each of the plurality of reference vehicles, an actual value of the given reference vehicle;

creating, for each of the plurality of reference vehicles, a reference feature vector comprising the reference vehicle-specific identifying information and the reference data;

associating, for each of the plurality of reference vehicles, the reference feature vector to the actual value of the given reference vehicle; and

training the machine learning algorithm using the associated reference feature vectors to predict the actual value of the vehicle associated with the user based on the vehicle-specific identifying information of the vehicle and the first data.

7. The method of claim 6 , further comprising,

determining a predictability for each of the one or more aspects of the reference vehicle for estimating the actual value of the given reference vehicle; and

assigning, based on the determined predictability, a first weight to the first data.

8. The method of claim 1 , wherein the one or more image sensors are calibrated to produce the multimedia content based on a degree of illumination or a time within a diurnal cycle.

9. A computing device, comprising:

one or more processors;

one or more image sensors; and

memory storing instructions that, when executed by the one or more processors, cause the computing device to:

receive a first indication that a use period of a vehicle associated with a user has started;

receive, based on the first indication, preliminary data for the vehicle associated with the user;

receive, from a device associated with the user, a second indication that the use period has ended;

receive, from one or more image sensors, first data comprising:

vehicle-specific identifying information of the vehicle associated with the user, and

multimedia content showing a first aspect of the vehicle associated with the user;

create a feature vector comprising the first data;

input the feature vector into a machine learning algorithm corresponding to the vehicle-specific identifying information of the vehicle associated with the user;

determine, using the machine learning algorithm, an instance of damage to the vehicle associated with the user based on the first data and the preliminary data; and

send, to a mobile device associated with the user, an indication of the instance of damage to the vehicle associated with the user.

10. The computing device of claim 9 , wherein the instructions when executed by the one or more processors, cause the computing device to:

receive, from the mobile device associated with the user, a request to begin a determination of the instance of damage to vehicle associated with the user;

receive, from the mobile device associated with the user, a second data comprising multimedia content showing a second aspect of the vehicle associated with the user; and

determine an initial damage estimate for the vehicle associated with the user.

11. The computing device of claim 10 , wherein the feature vector further comprises the second data.

12. The computing device of claim 9 , wherein the instructions when executed by the one or more processors, cause the computing device to:

prior to the inputting the feature vector into the machine learning algorithm, identifying the machine learning algorithm based on the vehicle-specific identifying information of the vehicle associated with the user.

13. The computing device of claim 9 , wherein the instructions when executed by the one or more processors, cause the computing device to:

prior to the use period, training the machine learning algorithm using reference vehicle-specific identifying information and reference data of one or more aspects of a plurality of reference vehicles that are not associated with the user.

14. The computing device of claim 13 , wherein the instructions when executed by the one or more processors, cause the computing device to train the machine learning algorithm by:

receiving, for each of the plurality of reference vehicles that are not associated with the user, reference vehicle-specific identifying information and reference data of the first aspect of a given reference vehicle of the plurality of reference vehicles;

receiving, for each of the plurality of reference vehicles, an actual value of the given reference vehicle;

creating, for each of the plurality of reference vehicles, a reference feature vector comprising the reference vehicle-specific identifying information and the reference data;

associating, for each of the plurality of reference vehicles, the reference feature vector to the actual value of the given reference vehicle; and

training the machine learning algorithm using the associated reference feature vectors to predict the actual value of the vehicle associated with the user based on the vehicle-specific identifying information of the vehicle and the first data.

15. The computing device of claim 14 , wherein the instructions when executed by the one or more processors, cause the computing device to:

determine a predictability for each of the one or more aspects of the reference vehicle for estimating the actual value of the given reference vehicle; and

assign, based on the determined predictability, a first weight to the first data.

16. The computing device of claim 9 , wherein the instructions when executed by the one or more processors, cause the computing device to train the one or more image sensors by calibrating the one or more image sensors to produce the multimedia content based on a degree of illumination or a time within a diurnal cycle.

17. One or more non-transitory media storing instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:

receiving a first indication that a use period of a vehicle associated with a user has started;

receiving, based on the first indication, preliminary data for the vehicle associated with the user;

receiving, from a device associated with the user, a second indication that the use period has ended;

receiving, from one or more image sensors, first data comprising:

vehicle-specific identifying information of the vehicle associated with the user, and

multimedia content showing a first aspect of the vehicle associated with the user;

creating a feature vector comprising the first data;

inputting the feature vector into a machine learning algorithm corresponding to the vehicle-specific identifying information of the vehicle associated with the user;

determining, using the machine learning algorithm, an instance of damage to the vehicle associated with the user based on the first data and the preliminary data; and

sending, to a mobile device associated with the user, an indication of the instance of damage to the vehicle associated with the user.

18. The one or more non-transitory media storing instructions of claim 17 , wherein the instructions, when executed by one or more processors, cause the one or more processors to perform steps comprising:

receiving, from the mobile device associated with the user, a request to begin a determination of the instance of damage to vehicle associated with the user;

receiving, from the mobile device associated with the user, a second data comprising multimedia content showing a second aspect of the vehicle associated with the user; and

determining an initial damage estimate for the vehicle associated with the user.

19. The one or more non-transitory media storing instructions of claim 18 , wherein the feature vector further comprises the second data.

20. The one or more non-transitory media storing instructions of claim 17 , wherein the instructions, when executed by one or more processors, cause the one or more processors to perform steps prior to the inputting the feature vector into the machine learning algorithm comprising:

identifying the machine learning algorithm based on the vehicle-specific identifying information of the vehicle associated with the user; and

training the machine learning algorithm using reference vehicle-specific identifying information and reference data of one or more aspects of a plurality of reference vehicles that are not associated with the user.