Predicting aggregate value of objects representing potential transactions based on potential transactions expected to be created

Abstract

An online system stores objects representing potential transactions of an enterprise. The online system uses predictor models to determine an aggregate score based on values of the objects associated with a time interval, for example, a month. Each object is configured to take one of a plurality of states. The online system stores historical data describing activities associated with potential transaction objects and uses the stored data for generating the predictor models. The online system categorizes the objects into bins based on states of the objects. The online system may generate different predictions for each category. The online system may use machine learning based models as predictor models. The online system extracts features describing potential transaction objects and provides these as input to the predictor model.

What is claimed is: 
     
         1 . A method comprising:
 for a tenant of a multi-tenant online system, storing a plurality of objects, wherein an object represents a potential transaction and is associated with a value of the potential transaction, the object having one of a plurality of object categories, the object configured to perform category transitions responsive to changes in data associated with the object;   extracting features of a set of objects that were previously processed and interacted with by one or more users;   training a plurality of models for a set of object categories based on the extracted features, each of the plurality of models associated with one of the object categories in the set of categories, wherein training each of the plurality of models comprises using a training dataset including extracted features associated with one of the object categories in the set of categories;   identifying a set of objects from the plurality of stored objects, the identified set of objects representing potential transactions that are yet to close;   executing a subset of trained models from the plurality of trained models to determine total expected values of the identified set of objects for the one or more object categories;   determining an aggregated value for an end of a time interval by aggregating the expected values across the plurality of object categories based on the identified set of objects; and   sending the aggregated value for display by a user interface.   
     
     
         2 . The method of  claim 1 , wherein at least one of the trained models is associated with a sub-interval of the time interval. 
     
     
         3 . The method of  claim 1 , wherein the time interval includes a sequence of sub-intervals and the subset of trained models includes a trained model for each of the sub-intervals. 
     
     
         4 . The method of  claim 3 , wherein each of the trained models in the subset of trained models includes is associated with (1) an object category of the set of object categories and (2) a sub-interval in the sequence of sub-intervals. 
     
     
         5 . The method of  claim 1 , wherein historical data associated with the stored plurality objects is stored in a database table, the method further comprising:
 detecting a change in a value associated with an object representing a potential transaction; and   adding a row to the database table responsive to detecting the change in the value.   
     
     
         6 . The method of  claim 1 , wherein the set of objects that were previously processed includes objects representing previous potential transactions. 
     
     
         7 . The method of  claim 1 , where the extracted features include at least one of:
 a rate of user interactions associated with the object within a past time interval;   a rate of updates to the object; or   total number of updates to the object since the potential transaction object was created.   
     
     
         8 . A non-transitory computer-readable storage medium comprising stored instructions that, when executed by a computing device, cause the computing device to perform operations including:
 for a tenant of a multi-tenant online system, storing a plurality of objects, wherein an object represents a potential transaction and is associated with a value of the potential transaction, the object having one of a plurality of object categories, the object configured to perform category transitions responsive to changes in data associated with the object;   extracting features of a set of objects that were previously processed and interacted with by one or more users;   training a plurality of models for a set of object categories based on the extracted features, each of the plurality of models associated with one of the object categories in the set of categories, wherein training each of the plurality of models comprises using a training dataset including extracted features associated with one of the object categories in the set of categories;   identifying a set of objects from the plurality of stored objects, the identified set of objects representing potential transactions that are yet to close;   executing a subset of trained models from the plurality of trained models to determine total expected values of the identified set of objects for the one or more object categories;   determining an aggregated value for an end of a time interval by aggregating the expected values across the plurality of object categories based on the identified set of objects; and   sending the aggregated value for display by a user interface.   
     
     
         9 . The non-transitory computer-readable storage medium of  claim 8 , wherein at least one of the trained models is associated with a sub-interval of the time interval. 
     
     
         10 . The non-transitory computer-readable storage medium of  claim 8 , wherein the time interval includes a sequence of sub-intervals and the subset of trained models includes a trained model for each of the sub-intervals. 
     
     
         11 . The non-transitory computer-readable storage medium of  claim 10 , wherein each of the trained models in the subset of trained models includes is associated with (1) an object category of the set of object categories and (2) a sub-interval in the sequence of sub-intervals. 
     
     
         12 . The non-transitory computer-readable storage medium of  claim 8 , wherein historical data associated with the stored plurality objects is stored in a database table, the operations further comprising:
 detecting a change in a value associated with an object representing a potential transaction; and   adding a row to the database table responsive to detecting the change in the value.   
     
     
         13 . The non-transitory computer-readable storage medium of  claim 8 , wherein the set of objects that were previously processed includes objects representing previous potential transactions. 
     
     
         14 . The non-transitory computer-readable storage medium of  claim 8 , where the extracted features include at least one of:
 a rate of user interactions associated with the object within a past time interval;   a rate of updates to the object; or   total number of updates to the object since the potential transaction object was created.   
     
     
         15 . A system comprising:
 computing device; and   a computer-readable storage medium comprising stored instructions that, when executed by the computing device, cause the computing device to perform operations including:
 for a tenant of a multi-tenant online system, storing a plurality of objects, wherein an object represents a potential transaction and is associated with a value of the potential transaction, the object having one of a plurality of object categories, the object configured to perform category transitions responsive to changes in data associated with the object; 
 extracting features of a set of objects that were previously processed and interacted with by one or more users; 
 training a plurality of models for a set of object categories based on the extracted features, each of the plurality of models associated with one of the object categories in the set of categories, wherein training each of the plurality of models comprises using a training dataset including extracted features associated with one of the object categories in the set of categories; 
 identifying a set of objects from the plurality of stored objects, the identified set of objects representing potential transactions that are yet to close; 
 executing a subset of trained models from the plurality of trained models to determine total expected values of the identified set of objects for the one or more object categories; 
 determining an aggregated value for an end of a time interval by aggregating the expected values across the plurality of object categories based on the identified set of objects; and 
 sending the aggregated value for display by a user interface. 
   
     
     
         16 . The system of  claim 15 , wherein at least one of the trained models is associated with a sub-interval of the time interval. 
     
     
         17 . The system of  claim 15 , wherein the time interval includes a sequence of sub-intervals and the subset of trained models includes a trained model for each of the sub-intervals. 
     
     
         18 . The system of  claim 10 , wherein each of the trained models in the subset of trained models includes is associated with (1) an object category of the set of object categories and (2) a sub-interval in the sequence of sub-intervals. 
     
     
         19 . The system of  claim 15 , wherein historical data associated with the stored plurality objects is stored in a database table, the method further comprising:
 detecting a change in a value associated with an object representing a potential transaction; and   adding a row to the database table responsive to detecting the change in the value.   
     
     
         20 . The system of  claim 15 , wherein the set of objects that were previously processed includes objects representing previous potential transactions.