Systems and methods for ai-based detection of delays in a shipping network

A computer program product comprising a non-transitory, computer-readable medium storing thereon a set of computer-executable instructions, the set of computer-executable instructions comprising instructions for:

• tracking shipment information for an in-progress shipment that has shipped, the shipment information comprising status information and an associated estimated delivery date for the in-progress shipment;
• transforming the shipment information for the in-progress shipment into a set of predictive features, the set of predictive features representing a current status of the in-progress shipment and a time to the associated estimated delivery date for the in-progress shipment;
• executing a machine learning model on the set of predictive features to receive an inference indicating whether the in-progress shipment will meet the associated estimated delivery date, the machine learning model trained on a training set of in-flight snapshots of a plurality of historical shipments, the training set of in-flight snapshots including a plurality of in-flight snapshots from different snapshot times for a respective historical shipment, wherein each in-flight snapshot in the training set of in-flight snapshots represents a respective historical shipment from the plurality of historical shipments at a respective snapshot time while the respective historical shipment was in-flight and before the respective historical shipment was delivered, wherein each in-flight snapshot in the training set of in-flight snapshots has an associated time remaining to estimated delivery date based on the respective snapshot time and a historical shipment estimated delivery date of the respective historical shipment, wherein the machine learning model represents a set of shipment statuses that occur between shipping and delivery, a set of timings of the shipment statuses from the set of shipment statuses relative to estimated delivery dates, and a set of shipment outcomes of the plurality of historical shipments and wherein the machine learning model is adapted to output the inference, the inference comprising a delay risk score;
• and
• based on a determination that the delay risk score exceeds a threshold, marking the in-progress shipment as being at risk of missing the associated estimated delivery date for the in-progress shipment.

A computer-implemented method comprising:

• collecting a set of records representing a plurality of historical shipments, each historical shipment in the plurality of historical shipments having a historical shipment estimated delivery date and a historical shipment actual delivery date;
• creating a training set of in-flight snapshots for the plurality of historical shipments, the training set of in-flight snapshots including a plurality of in-flight snapshots from different snapshot times for a respective historical shipment, wherein each in-flight snapshot in the training set of in-flight snapshots represents a respective historical shipment from the plurality of historical shipments at a respective snapshot time while the respective historical shipment was in-flight and before the respective historical shipments was delivered, and wherein each in-flight snapshot in the training set of in-flight snapshots has an associated time remaining to estimated delivery date based on the respective snapshot time and the historical shipment estimated delivery date of the respective historical shipment;
• training a machine learning model using the training set of in-flight snapshots to infer, based on a set of predictive features, whether shipments having associated estimated delivery dates will meet the associated estimated delivery dates, wherein the machine learning model adapted to output delay risk scores for inferences, and wherein the machine learning model represents a set of shipment statuses that occur between shipment and delivery, a set of timings of the shipment statuses from the set of in-flight shipment statuses relative estimated delivery dates, and a set of shipment outcomes of the plurality of historical shipments;
• and
• deploying the machine learning model in a shipping management system.