Automatic detection of disruptive orders for a supply chain
Techniques are provided for automatically detecting disruptive orders for a supply chain. One method comprises obtaining a quote for an order; extracting features from the quote; and applying the extracted features to a disruptive quote machine learning engine that generates an anomaly score indicating a likelihood that the quote will cause a disruption, based on one or more predefined disruption criteria. The disruptive quote machine learning engine may employ an isolation forest algorithm and/or a multi-dimensional anomaly detection algorithm. The disruptive quote machine learning engine may be trained using historical order information comprising part-level information from historical orders and/or a manufacturing production plan comprising an inventory forecast.
1. A method, comprising:
obtaining at least one data record associated with a request for at least one product;
extracting one or more features from the at least one data record;
applying the extracted features to a machine learning engine that generates an anomaly score indicating a likelihood that the at least one data record will cause a disruption, based on one or more predefined disruption criteria, wherein the machine learning engine is trained using historical order information to learn to identify at least one data record that will likely cause a disruption, wherein the disruption comprises a delay for one or more of the request and at least one additional request; and
performing one or more automated actions based at least in part on the anomaly score;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
2. The method of claim 1 , further comprising providing a user with one or more predefined factors that contribute to the anomaly score.
3. The method of claim 1 , wherein a plurality of quotes is processed and the quotes within the plurality of quotes are sorted by the anomaly score.
4. The method of claim 1 , wherein the machine learning engine employs one or more of an isolation forest algorithm and a multi-dimensional anomaly detection algorithm.
5. The method of claim 1 , wherein the anomaly score is determined by comparing features of a given at least one data record associated with the request to historical data records associated with historical requests to determine where to rank the at least one data record associated with the request within the historical data records.
6. The method of claim 1 , wherein the historical order information used to train the machine learning engine comprises part-level information of historical orders.
7. The method of claim 1 , wherein training data for the machine learning engine further comprises a manufacturing production plan comprising an inventory forecast.
8. A computer program product, comprising a tangible machine-readable storage medium having encoded therein executable code of one or more software programs, wherein the one or more software programs when executed by at least one processing device perform the following steps:
obtaining at least one data record associated with a request for at least one product;
extracting one or more features from the at least one data record;
applying the extracted features to a machine learning engine that generates an anomaly score indicating a likelihood that the at least one data record will cause a disruption, based on one or more predefined disruption criteria, wherein the machine learning engine is trained using historical order information to learn to identify at least one data record that will likely cause a disruption, wherein the disruption comprises a delay for one or more of the request and at least one additional request; and
performing one or more automated actions based at least in part on the anomaly score.
9. The computer program product of claim 8 , further comprising providing a user with one or more predefined factors that contribute to the anomaly score.
10. The computer program product of claim 8 , wherein a plurality of quotes is processed and the quotes within the plurality of quotes are sorted by the anomaly score.
11. The computer program product of claim 8 , wherein the machine learning engine employs one or more of an isolation forest algorithm and a multi-dimensional anomaly detection algorithm.
12. The computer program product of claim 8 , wherein the anomaly score is determined by comparing features of a given at least one data record associated with the request to historical data records associated with historical requests to determine where to rank the at least one data record associated with the request within the historical data records.
13. The computer program product of claim 8 , wherein the historical order information used to train the machine learning engine comprises part-level information of historical orders, and wherein training data for the machine learning engine further comprises a manufacturing production plan comprising an inventory forecast.
14. An apparatus, comprising:
a memory; and
at least one processing device, coupled to the memory, operative to implement the following steps:
obtaining at least one data record associated with a request for at least one product;
extracting one or more features from the at least one data record;
applying the extracted features to a machine learning engine that generates an anomaly score indicating a likelihood that the at least one data record will cause a disruption, based on one or more predefined disruption criteria, wherein the machine learning engine is trained using historical order information to learn to identify at least one data record that will likely cause a disruption, wherein the disruption comprises a delay for one or more of the request and at least one additional request; and
performing one or more automated actions based at least in part on the anomaly score.
15. The apparatus of claim 14 , further comprising providing a user with one or more predefined factors that contribute to the anomaly score.
16. The apparatus of claim 14 , wherein a plurality of quotes is processed and the quotes within the plurality of quotes are sorted by the anomaly score.
17. The apparatus of claim 14 , wherein the machine learning engine employs an isolation forest algorithm.
18. The apparatus of claim 14 , wherein the anomaly score is determined by comparing features of a given at least one data record associated with the request to historical data records associated with historical requests to determine where to rank the at least one data record associated with the request within the historical data records.
19. The apparatus of claim 14 , wherein the historical order information used to train the machine learning engine comprises part-level information of historical orders.
20. The apparatus of claim 14 , wherein training data for the machine learning engine further comprises a manufacturing production plan comprising an inventory forecast.