Automated generation of delivery dates using machine learning
An apparatus in one embodiment comprises at least one processing platform including a plurality of processing devices. The processing platform is configured to receive a request to execute one or more predictive models for generating a delivery date, to initiate execution of the one or more predictive models responsive to the request, and to invoke a plurality of machine learning algorithms using data from a plurality of data sources when executing the one or more predictive models. The processing platform is further configured to capture the data from the plurality of data sources and organize the data into a sparse matrix, to automatically generate the delivery date, and to automatically transmit the delivery date to one or more user devices.
1. An apparatus comprising:
at least one processing platform comprising a plurality of processing devices;
said at least one processing platform being configured:
to receive a request to execute one or more predictive models for generating a delivery date;
to initiate execution of the one or more predictive models responsive to the request;
to invoke a plurality of machine learning algorithms using data from a plurality of data sources when executing the one or more predictive models;
to capture the data from the plurality of data sources and organize the data into a sparse matrix;
to automatically generate the delivery date; and
to automatically transmit the delivery date to one or more user devices.
2. The apparatus of claim 1 wherein the one or more predictive models use one or more decision trees.
3. The apparatus of claim 2 wherein the one or more decision trees use different variables from each other to determine an outcome.
4. The apparatus of claim 2 wherein the one or more predictive models use a neural network to optimally combine results from the one or more decision trees.
5. The apparatus of claim 1 wherein the captured data includes real-time changes to one or more order conditions, and wherein the automatically generated delivery date is based on the real-time changes to the one or more order conditions.
6. The apparatus of claim 1 wherein said at least one processing platform is further configured to reduce a size of the sparse matrix.
7. The apparatus of claim 6 wherein said at least one processing platform is further configured to use one or more heuristics to reduce the size of the sparse matrix.
8. The apparatus of claim 7 wherein the one or more heuristics remove data corresponding to at least one of a timestamp and a stock keeping unit (SKU) code having a frequency determined to be less than a given threshold.
9. The apparatus of claim 1 wherein the one or more predictive models run on a data science platform.
10. The apparatus of claim 9 wherein the data science platform is configured to provide an interactive workspace for a plurality of data scientists electronically accessing the data science platform.
11. The apparatus of claim 9 wherein the data science platform is configured to at least one of manage versioning of the one or more predictive models, measure performance of the one or more predictive models, and execute experiments on the one or more predictive models.
12. The apparatus of claim 1 wherein said at least one processing platform is further configured to train the one or more predictive models based on historical data comprising actual delivery dates.
13. The apparatus of claim 12 wherein the one or more predictive models use one or more decision trees, and wherein the training comprises training the one or more decision trees on different outcomes.
14. The apparatus of claim 1 wherein the data comprises at least one of supply chain data, order data, lead time data, delivery data and fulfillment data.
15. A method comprising:
receiving a request to execute one or more predictive models for generating a delivery date;
initiating execution of the one or more predictive models responsive to the request;
invoking a plurality of machine learning algorithms using data from a plurality of data sources when executing the one or more predictive models;
capturing the data from the plurality of data sources and organizing the data into a sparse matrix;
automatically generating the delivery date; and
automatically transmitting the delivery date to one or more user devices;
wherein the method is performed by at one processing platform comprising at least one processing device comprising a processor coupled to a memory.
16. The method of claim 15 further comprising training the one or more predictive models based on historical data comprising actual delivery dates.
17. The method of claim 16 wherein the one or more predictive models use one or more decision trees, and wherein the training comprises training the one or more decision trees on different outcomes.
18. A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing platform causes said at least one processing platform:
to receive a request to execute one or more predictive models for generating a delivery date;
to initiate execution of the one or more predictive models responsive to the request;
to invoke a plurality of machine learning algorithms using data from a plurality of data sources when executing the one or more predictive models;
to capture the data from the plurality of data sources and organize the data into a sparse matrix;
to automatically generate the delivery date; and
to automatically transmit the delivery date to one or more user devices.
19. The computer program product of claim 18 wherein the program code when executed by said at least one processing platform further causes said at least one processing platform to train the one or more predictive models based on historical data comprising actual delivery dates.
20. The computer program product of claim 19 wherein the one or more predictive models use one or more decision trees, and wherein the training comprises training the one or more decision trees on different outcomes.