Automated supply chain demand forecasting

Abstract

In an embodiment, a method includes receiving training data representing historic consumer demand for products, detecting changepoints in that data that may be associated with disruptive events, identifying relevant data for modeling, performing clustering, processing configuration information, training one or more machine learning models that are capable of evaluating other received data more accurately, and outputting results to a user display device.

What is claimed is: 
     
         1 . A computer-implemented method of forecasting supply chain demand of products of goods or services, executed by a computing system associated with a supply chain network, the method comprising:
 retrieving a training data set comprising product demand data that has been acquired by data acquisition logic of the computing system, the product demand data indicating consumer demand for millions of products at a plurality of time points;   clustering the training data set into a plurality of time series clusters;   calculating one or more break points in one or more of the time series clusters of the training data set, each of the break points corresponding to a disruptive event, by executing a supervised multi class machine learning classifier;   retrieving a baseline forecast for one or more of the products and calculating one or more of mean demand level, median demand level, or standard deviation of demand level for selected periods of the training data set that are before and after one or more of the break points;   identifying a deviation between the baseline forecast and a particular time series cluster among the plurality of the time series clusters, the deviation exceeding 1.5*Inter Quartile Range (IQR), above and below the 75th and 25th percentiles of the baseline forecast and, in response thereto, flagging the particular time series cluster as impacted by a disruptive event;   creating one or more machine learning models to predict future product demand data based on the training data set;   processing configuration information that specifies third-party data for training the one or more machine learning models and, in response thereto, accessing one or more of mobility tracking data specifying a percent change in visits to stores within a geographic area, a social distance index, school closures data, case count data, unemployment claims data, consumer sentiment data, hospital utilization data, as additional data source for which the one or more machine learning models may be trained;   programmatically activating a training function of the one or more machine learning models with a reference to or identification of the training dataset and the third-party data.   
     
     
         2 . The computer-implemented method of  claim 1 , at least a portion of the product demand data comprising upstream consumption data that corresponds to one or more other computing systems that are upstream from the computing system associated with the supply chain network; the method further comprising updating the product demand data for the one or more products by imputing sales values based on the upstream consumption data. 
     
     
         3 . The computer-implemented method of  claim 1 , further comprising clustering the training data set into a plurality of time series clusters based on moving average convergence/divergence (MACD) indicators that are associated with the product demand data. 
     
     
         4 . A computer-implemented method of forecasting supply chain demand of products of goods or services, executed by a computing system associated with a supply chain network, the method comprising:
 retrieving product demand data that has been acquired by data acquisition logic of the computing system, the product demand data indicating consumer demand for one or more products at a plurality of time points;   determining that at least a portion of the product demand data comprises upstream consumption data that corresponds to one or more other computing systems that are upstream from the computing system associated with the supply chain network;   updating the product demand data for the one or more products by imputing sales values based on the upstream consumption data;   determining a plurality of changepoints for the one or more products represented in the updated product demand data based on evaluation of the product demand data using a trained machine learning model, each changepoint corresponding to a time point of the plurality of time points;   clustering the plurality of changepoints into groups and identifying demand patterns associated with the one or more products;   determining, based on the demand patterns, a baseline model of expected consumer demand for each of the one or more products;   determining, for a particular product of the one or more products, a probability that the particular product will experience a disruptive event based on a deviation from the baseline model of the expected consumer demand.   
     
     
         5 . The computer-implemented method of  claim 4 , the product demand data further comprising downstream consumption data obtained from Point of Sale (POS) computer systems. 
     
     
         6 . The computer-implemented method of  claim 4 , further comprising clustering the plurality of changepoints into the groups based on moving average convergence/divergence (MACD) indicators that are associated with the updated product demand data. 
     
     
         7 . The computer-implemented method of  claim 4 , further comprising updating the product demand data for the one or more products by transforming the product demand data by one or more of: formatting the product demand data, deduplicating the product demand data, or correcting errors associated with the product demand data. 
     
     
         8 . The computer-implemented method of  claim 4 , further comprising determining the baseline model of the expected consumer demand for each of the one or more products based on one or more of: GPS location tracking, social-related data, school closures data, unemployment claims data, consumer sentiment data, hospital utilization data, school closure data, unemployment data, or consumer sentiment data. 
     
     
         9 . A computer system comprising:
 one or more processors; and   one or more computer-readable non-transitory storage media in communication with the one or more processors, the one or more computer-readable non-transitory storage media storing one or more sequences of instructions that when executed by the one or more processors, cause the one or more processors to:   retrieve product demand data that has been acquired by data acquisition logic of the computing system, the product demand data indicating consumer demand for one or more products at a plurality of time points;   determine that at least a portion of the product demand data comprises upstream consumption data that corresponds to one or more other computing systems that are upstream from the computing system associated with the supply chain network;   update the product demand data for the one or more products by imputing sales values based on the upstream consumption data;   determine a plurality of changepoints for the one or more products represented in the updated product demand data based on evaluation of the product demand data using a trained machine learning model, each changepoint corresponding to a time point of the plurality of time points;   cluster the plurality of changepoints into groups and identifying demand patterns associated with the one or more products;   determine, based on the demand patterns, a baseline model of expected consumer demand for each of the one or more products;   determine, for a particular product of the one or more products, a probability that the particular product will experience a disruptive event based on a deviation from the baseline model of the expected consumer demand.   
     
     
         10 . The system of  claim 9 , the product demand data further comprising downstream consumption data obtained from Point of Sale (POS) computer systems. 
     
     
         11 . The system of  claim 9 , the one or more sequences of instructions when executed by the one or more processors further cause the one or more processors to:
 cluster the plurality of changepoints into the groups based on moving average convergence/divergence (MACD) indicators that are associated with the updated product demand data.   
     
     
         12 . The system of  claim 9 , the one or more sequences of instructions when executed by the one or more processors further cause the one or more processors to:
 update the product demand data for the one or more products by transforming the product demand data by one or more of: formatting the product demand data, deduplicating the product demand data, or correcting errors associated with the product demand data.   
     
     
         13 . The system of  claim 9 , the one or more sequences of instructions when executed by the one or more processors further cause the one or more processors to:
 determine the baseline model of the expected consumer demand for each of the one or more products based on one or more of: GPS location tracking, social-related data, school closures data, unemployment claims data, consumer sentiment data, hospital utilization data, school closure data, unemployment data, or consumer sentiment data.   
     
     
         14 . One or more computer-readable non-transitory storage media including instructions that, when executed by one or more processors, are configured to cause the one or more processors to:
 retrieve product demand data that has been acquired by data acquisition logic of the computing system, the product demand data indicating consumer demand for one or more products at a plurality of time points;   determine that at least a portion of the product demand data comprises upstream consumption data that corresponds to one or more other computing systems that are upstream from the computing system associated with the supply chain network;   update the product demand data for the one or more products by imputing sales values based on the upstream consumption data;   determine a plurality of changepoints for the one or more products represented in the updated product demand data based on evaluation of the product demand data using a trained machine learning model, each changepoint corresponding to a time point of the plurality of time points;   cluster the plurality of changepoints into groups and identifying demand patterns associated with the one or more products;   determine, based on the demand patterns, a baseline model of expected consumer demand for each of the one or more products;   determine, for a particular product of the one or more products, a probability that the particular product will experience a disruptive event based on a deviation from the baseline model of the expected consumer demand.   
     
     
         15 . The one or more computer-readable non-transitory storage media of  claim 15 , the product demand data further comprising downstream consumption data obtained from Point of Sale (POS) computer systems. 
     
     
         16 . The one or more computer-readable non-transitory storage media of  claim 15 , the instructions being configured to further cause the one or more processors to:
 cluster the plurality of changepoints into the groups based on moving average convergence/divergence (MACD) indicators that are associated with the updated product demand data.   
     
     
         17 . The one or more computer-readable non-transitory storage media of  claim 15 , the instructions being configured to further cause the one or more processors to:
 update the product demand data for the one or more products by transforming the product demand data by one or more of: formatting the product demand data, deduplicating the product demand data, or correcting errors associated with the product demand data.   
     
     
         18 . The one or more computer-readable non-transitory storage media of  claim 15 , the instructions being configured to further cause the one or more processors to:
 determine the baseline model of the expected consumer demand for each of the one or more products based on one or more of: GPS location tracking, social-related data, school closures data, unemployment claims data, consumer sentiment data, hospital utilization data, school closure data, unemployment data, or consumer sentiment data.