Supply risk detection

Abstract

Systems and methods for supply risk detection are disclosed. In some embodiments, a method includes identifying fulfillment-related features corresponding to an item to be stored in inventory. The method also includes selecting a subset of the fulfillment-related features that is correlated with a supply constraint associated with the item. For example, in some cases the correlation is based on historical supply constraint data. The method further includes building a supply risk early detection model based, at least in part, upon the subset fulfillment-related features and evaluating the model to determine a probability that a third-party vendor will suffer a shortage of the item, as well as an expected duration of the shortage. Upon evaluation of the model, the method may include creating a purchasing plan for the item that takes into account the probability of the shortage and the expected duration of the shortage.

1 . A method, comprising:
 performing, by one or more computers:
 identifying fulfillment-related features corresponding to an item to be stored in inventory, wherein the item is supplied by a third-party vendor; 
 selecting a subset of the fulfillment-related features that is correlated with a supply constraint associated with the item, wherein the correlation is based on historical supply constraint data; 
 building a supply risk early detection model based, at least in part, upon the subset of fulfillment-related features; 
 evaluating the supply risk early detection model to determine a probability that the third-party vendor will suffer a shortage of the item and an expected duration of the shortage; and 
 creating a purchasing plan for the item that takes into account:
 the probability of the shortage, 
 the expected duration of the shortage, 
 an associated cost of buying additional units of the item, and 
 an associated cost of not having sufficient supply of the item to serve an expected demand for the item. 
 
   
     
     
         2 . The method of  claim 1 , wherein the fulfillment-related features include a vendor identity. 
     
     
         3 . The method of  claim 1 , wherein the fulfillment-related features include at least one of an item identity or a release date of the item. 
     
     
         4 . The method of  claim 1 , wherein the fulfillment-related features include a quantity of the item to be purchased. 
     
     
         5 . The method of  claim 1 , wherein the fulfillment-related features include a velocity with which the item is sold to customers. 
     
     
         6 . The method of  claim 1 , wherein the fulfillment-related features include a user-defined replenishment code associated with the item. 
     
     
         7 . The method of  claim 1 , wherein the fulfillment-related features include a prior supply constraint. 
     
     
         8 . The method of  claim 1 , wherein the supply constraint includes at least one of a purchase order rejection, a purchase order cancellation, a purchase order backorder, or a partial receipt. 
     
     
         9 . The method of  claim 1 , wherein selecting the subset of fulfillment-related features includes calculating a correlation coefficient for each feature of the subset of fulfillment-related features. 
     
     
         10 . The method of  claim 1 , wherein the supply risk early detection model includes a logistical regression model, and wherein an exponent of the logistical regression model includes a linear combination of two or more features of the subset of fulfillment-related features. 
     
     
         11 . The method of  claim 1 , wherein creating the purchasing plan includes modifying an existing purchasing plan. 
     
     
         12 . A system, comprising:
 at least one processor; and   a memory coupled to the at least one processor, wherein the memory stores program instructions, and wherein the program instructions are executable by the at least one processor to cause the system to:
 identify fulfillment-related features corresponding to an item to be purchased from a third-party vendor by a merchant; 
 select a subset of the fulfillment-related features that is correlated with a supply constraint associated with the item, wherein the correlation is based on historical supply constraint data, and wherein the supply constraint includes at least one of a purchase order rejection, a purchase order cancellation, a purchase order backorder, or a partial receipt; and 
 build a model configured to calculate a probability of the third-party vendor stocking out of the item and an expected duration of the stockout based, at least in part, upon the subset of fulfillment-related features. 
   
     
     
         13 . The system of  claim 12 , wherein the fulfillment-related features include a vendor identity and an item identity. 
     
     
         14 . The system of  claim 12 , wherein the fulfillment-related features include at least one of a quantity of the item to be purchased by the merchant, a velocity with which the item is sold to the merchant's customers, or a user-defined replenishment code associated with the item. 
     
     
         15 . The system of  claim 12 , wherein the model includes a logistical regression model, and wherein an exponent of the logistical regression includes a linear combination of two or more features of the subset of fulfillment-related features. 
     
     
         16 . The system of  claim 12 , wherein the program instructions are further executable by the at least one processor to cause the system to create a purchasing plan for the item that takes into account:
 the probability of the stockout,   the expected duration of the stockout,   an associated cost of buying additional units of the item, and   an associated cost of not having sufficient supply of the item to serve an expected demand for the item.   
     
     
         17 . A non-transitory computer-readable storage medium having program instructions stored thereon that, upon execution by a computer system, cause the computer system to:
 evaluate a model configured to calculate a probability of a third-party vendor stocking out of an item and an expected duration of the stockout based, at least in part, upon a set of fulfillment-related features corresponding to the item, wherein each feature of the set of fulfillment-related features is correlated with a supply constraint based on historical supply constraint data, and wherein the supply constraint includes at least one of a purchase order rejection, a purchase order cancellation, a purchase order backorder, or a partial receipt; and   creating a purchasing plan for the item that takes into account:
 the probability of the stockout, 
 the expected duration of the stockout, 
 an associated cost of buying additional units of the item, and 
 an associated cost of not having sufficient supply of the item to serve an expected demand for the item. 
   
     
     
         18 . The non-transitory computer-readable storage medium of  claim 17 , wherein the set of fulfillment-related features includes a vendor identity, an item identity, a quantity of the item to be purchased by the merchant, a velocity with which the item is sold to the merchant's customers, or a user-defined replenishment code associated with the item. 
     
     
         19 . The non-transitory computer-readable storage medium of  claim 17 , wherein the model includes a logistical regression model, and wherein an exponent of the logistical regression includes a linear combination of two or more features of the set of fulfillment-related features. 
     
     
         20 . The non-transitory computer-readable storage medium of  claim 17 , wherein creating the purchasing plan includes modifying an existing purchasing plan.