Method and system for generating delivery estimates
Embodiments of a method and system for determining delivery estimates for shipping a parcel include: retrieving historical delivery data from a plurality of shipping carriers; generating cross-carrier delivery features based on normalizing the historical delivery data; generating a cross-carrier delivery prediction model based on the cross-carrier delivery features; retrieving parcel data for the parcel based on a tracking number S 140 ; generating parcel features based on normalizing the parcel data S 150 ; determining a delivery estimate for the parcel based on processing the parcel features with the cross-carrier delivery prediction model S 160 ; and responding to the delivery estimate S 170.
1. A method, comprising:
receiving first parcel data for a first parcel from a first carrier at a first webhook endpoint;
identifying a second parcel associated with the first parcel;
at a resource associated with the first webhook endpoint, sending an API request to a second carrier for second parcel data for the second parcel, in response to receiving the first parcel data for the first parcel; and
sending a single message to a user endpoint, wherein the single message is determined based on the first and second parcel data for the first and second parcels, respectively.
2. The method of claim 1 , wherein the single message comprises a predicted delivery estimate for the second parcel, wherein the predicted delivery estimate is generated from a carrier-specific model, specific to the second carrier, that is trained on historical carrier data.
3. The method of claim 2 , wherein the carrier-specific model is selected based on a destination address for the second parcel.
4. The method of claim 2 , wherein the single message further comprises a confidence metric associated with the predicted delivery estimate.
5. The method of claim 2 , wherein the carrier-specific model is stored in a database, wherein the carrier-specific model is updated based on a comparison between the predicted delivery estimate and an actual delivery time.
6. The method of claim 1 , wherein the single message comprises a carrier-provided delivery estimate for the second parcel and a predicted delivery estimate for the second parcel.
7. The method of claim 1 , further comprising:
detecting a trigger event during a delivery of the second parcel; and
updating the second parcel data based on the trigger event, wherein the updated second parcel data is provided to the user endpoint.
8. The method of claim 7 , wherein the trigger event comprises at least one of a delivery disruption or a user query.
9. The method of claim 1 , further comprising executing a delivery of the second parcel, comprising controlling an autonomous system to deliver the second parcel based on a selected service level and a set of control instructions.
10. The method of claim 9 , wherein the autonomous system comprises a drone.
11. The system of claim 1 , wherein the first and second carrier are determined based on a respective first and second tracking number provided by a user.
12. A system, comprising:
a non-transitory machine-readable storage medium storing executable instructions that, when executed by a processing system, cause the processing system to perform operations comprising:
receiving a shipment request identifying a first and second parcel;
receiving a selection of a first and second carrier for the first and second parcel, respectively;
establishing a first and second webhook endpoint for the first and second carrier, respectively;
receiving first parcel data for the first parcel from the first carrier at the first webhook endpoint;
receiving second parcel data for the second parcel from the second carrier; and
sending a single message to a user endpoint, wherein the single message is determined based on the first and second parcel data for the first and second parcels, respectively.
13. The system of claim 12 , wherein the single message comprises a predicted delivery estimate for the second parcel, wherein the predicted delivery estimate is generated from a model trained on historical carrier data.
14. The system of claim 13 , wherein the model comprises a machine learning model.
15. The system of claim 13 , wherein the model is specific to the second carrier, wherein the model is trained by:
determining historical delivery data for a set of parcels from the second carrier;
determining delivery features based on the historical delivery data;
predicting a delivery estimate for each parcel of the set based on the delivery features using the model;
determining an actual delivery time for each parcel of the set; and
updating the model based on a comparison between the delivery estimates and the actual delivery times.
16. The system of claim 12 , wherein the single message comprises a carrier-provided delivery estimate for the second parcel and a predicted delivery estimate for the second parcel.
17. The system of claim 12 , wherein receiving the second parcel data for the second parcel from the second carrier comprises:
querying the second carrier for the second parcel data based on a default query schedule;
receiving unexpected parcel data; and
updating the query schedule based on the unexpected parcel data.
18. The system of claim 12 , wherein the first and second parcel are associated with different recipients.
19. The system of claim 12 , wherein the single message comprises a delivery estimate notification.
20. The system of claim 12 , wherein the second parcel data is requested from the second carrier responsive to receipt of the first parcel data.