Predicting the effectiveness of a marketing campaign prior to deployment

Abstract

In some implementations, a computing device may determine, from multiple data sources, multiple event timelines, with each event timeline associated with a customer. Each event in an event timeline represents an interaction between the customer and a vendor of goods and/or services. For N (N>1) marketing campaigns, N augmented timelines may be created for each timeline by augmenting each event timeline with the individual marketing campaigns. Thus, for M (M>1) customers, M×N augmented event timelines may be created. A trained machine learning model may perform an analysis of each augmented event timeline to predict results of executing each marketing campaign. The results may include total predicted revenue and total predicted cost resulting from executing each marketing campaign. A particular marketing campaign from the N marketing campaigns may be selected and execution of one or more marketing events may be initiated.

What is claimed is: 
     
         1 . A method comprising:
 selecting, by one or more processors, a plurality of event timelines, wherein individual event timelines of the plurality of event timelines include events representing interactions between a customer and a vendor;   selecting, by the one or more processors, a plurality of marketing campaigns, wherein individual marketing campaigns of the plurality of marketing campaigns include one or more marketing events representing actions to be performed by or on behalf of the vendor;   creating, by the one or more processors, a set of augmented event timelines, wherein an augmented event timeline of the set of augmented event timelines includes a particular event timeline of the plurality of event timelines and a particular marketing campaign of the plurality of marketing campaigns;   performing, by a trained machine learning model, an analysis of individual augmented event timelines of the set of augmented event timelines;   determining, by the trained machine learning model, a predicted result associated with individual marketing campaigns used in individual augmented event timelines of the set of augmented event timelines;   selecting, by the one or more processors, a particular marketing campaign from the one or more marketing campaigns; and   initiating execution of the one or more marketing events of the particular marketing campaign.   
     
     
         2 . The method of  claim 1 , further comprising:
 selecting a particular customer;   identifying a plurality of augmented event timelines associated with the particular customer;   determining that a particular augmented event timeline of the plurality of augmented event timelines has a highest predicted revenue;   adding the particular customer to a group corresponding to a marketing campaign included in the particular augmented event timeline with the highest predicted revenue.   
     
     
         3 . The method of  claim 2 , further comprising:
 selecting a particular group corresponding to a marketing campaign of the plurality of marketing campaigns;   determining for the particular group:
 a total number of customers in the particular group; 
 a total amount of predicted revenue; and 
 a total cost to execute the marketing campaign to members of the particular group. 
   
     
     
         4 . The method of  claim 3 , further comprising:
 selecting the particular marketing campaign from the one or more marketing campaigns based at least in part on:
 the total number of customers in each group; 
 the total amount of predicted revenue determined for each group; 
 the total cost to execute the marketing campaign to members of the particular group. 
   
     
     
         5 . The method of  claim 1 , further comprising:
 selecting an augmented event timeline of the set of augmented event timelines; and   creating a string of symbols corresponding to the augmented event timeline, wherein each symbol in the string of symbols corresponds to an event in the augmented event timeline.   
     
     
         6 . The method of  claim 5 , wherein determining, by the trained machine learning model, the predicted result associated with individual marketing campaigns used in individual augmented event timelines of the set of augmented event timelines comprises:
 predicting, by the trained machine learning model, one or more next symbols in the string of symbols.   
     
     
         7 . The method of  claim 5 , further comprising:
 determining that a particular event in the augmented event timeline includes a revenue event; and   modifying a symbol corresponding to the particular event to include a revenue indicator, the revenue indicator comprising one of an actual revenue amount, a revenue range, or a revenue magnitude.   
     
     
         8 . A computing device comprising:
 one or more processors; and   one or more non-transitory computer-readable storage media to store instructions executable by the one or more processors to perform operations comprising:
 selecting a plurality of event timelines, wherein individual event timelines of the plurality of event timelines include events representing interactions between a customer and a vendor; 
 selecting a plurality of marketing campaigns, wherein individual marketing campaigns of the plurality of marketing campaigns include one or more marketing events representing actions to be performed by or on behalf of the vendor; 
 creating a set of augmented event timelines, wherein an augmented event timeline of the set of augmented event timelines includes a particular event timeline of the plurality of event timelines and a particular marketing campaign of the plurality of marketing campaigns; 
 performing an analysis of individual augmented event timelines of the set of augmented event timelines; 
 determining a predicted result associated with individual marketing campaigns used in individual augmented event timelines of the set of augmented event timelines; 
 modifying a particular marketing campaign from the one or more marketing campaigns based at least in part on the predicted result to create a modified marketing campaign; and 
 initiating execution of the one or more marketing events of the modified marketing campaign. 
   
     
     
         9 . The computing device of  claim 8 , the operations further comprising:
 selecting a particular customer;   identifying a plurality of augmented event timelines associated with the particular customer;   determining that a particular augmented event timeline of the plurality of augmented event timelines has a highest predicted revenue;   adding the particular customer to a group corresponding to a marketing campaign included in the particular augmented event timeline with the highest predicted revenue; and   determining a total predicted revenue for the plurality of campaigns for the particular customer.   
     
     
         10 . The computing device of  claim 9 , the operations further comprising:
 selecting a particular group corresponding to the marketing campaign;   determining for the particular group:
 a total number of customers in the particular group; 
 a total amount of predicted revenue; and 
 a total cost to execute the marketing campaign to members of the particular group. 
   
     
     
         11 . The computing device of  claim 10 , the operations further comprising:
 modifying the particular marketing campaign from the one or more marketing campaigns based at least in part on:
 the total number of customers in each group; 
 the total amount of predicted revenue determined for each group; 
 the total cost to execute the marketing campaign to members of the particular group; and 
 the total predicted revenue for the plurality of campaigns for the particular customer. 
   
     
     
         12 . The computing device of  claim 8 , the operations further comprising:
 selecting an augmented event timeline of the set of augmented event timelines; and   creating a string of symbols corresponding to the augmented event timeline, wherein each symbol in the string of symbols corresponds to an event in the augmented event timeline.   
     
     
         13 . The computing device of  claim 12 , wherein determining, by the trained machine learning model, the predicted result associated with individual marketing campaigns used in individual augmented event timelines of the set of augmented event timelines comprises:
 predicting, by the trained machine learning model, one or more next symbols in the string of symbols.   
     
     
         14 . The computing device of  claim 12 , the operations further comprising:
 determining that a particular event in the augmented event timeline includes a revenue event; and   modifying a symbol corresponding to the particular event to include a revenue indicator, the revenue indicator comprising one of an actual revenue amount, a revenue range, or a revenue magnitude.   
     
     
         15 . One or more non-transitory computer-readable storage media storing instructions executable by one or more processors to perform operations comprising:
 selecting a plurality of event timelines, wherein individual event timelines of the plurality of event timelines include events representing interactions between a customer and a vendor;   selecting a plurality of marketing campaigns, wherein individual marketing campaigns of the plurality of marketing campaigns include one or more marketing events representing actions to be performed by or on behalf of the vendor;   creating a set of augmented event timelines, wherein an augmented event timeline of the set of augmented event timelines includes a particular event timeline of the plurality of event timelines and a particular marketing campaign of the plurality of marketing campaigns;   performing, by a trained machine learning model, an analysis of individual augmented event timelines of the set of augmented event timelines;   determining, by the trained machine learning model, a predicted result associated with individual marketing campaigns used in individual augmented event timelines of the set of augmented event timelines;   selecting a particular marketing campaign from the one or more marketing campaigns; and   initiating execution of the one or more marketing events of the particular marketing campaign.   
     
     
         16 . The one or more non-transitory computer-readable storage media of  claim 15 , the operations further comprising:
 selecting a particular customer;   identifying a plurality of augmented event timelines associated with the particular customer;   determining that a particular augmented event timeline of the plurality of augmented event timelines has a highest predicted revenue;   adding the particular customer to a group corresponding to the particular marketing campaign included in the particular augmented event timeline with the highest predicted revenue.   
     
     
         17 . The one or more non-transitory computer-readable storage media of  claim 16 , the operations further comprising:
 selecting a particular group corresponding to a marketing campaign of the plurality of marketing campaigns;   determining for the particular group:
 a total number of customers in the particular group; 
 a total amount of predicted revenue; and 
 a total cost to execute the marketing campaign to members of the particular group; and 
   selecting the particular marketing campaign from the one or more marketing campaigns based at least in part on:
 the total number of customers in each group; 
 the total amount of predicted revenue determined for each group; and 
 the total cost to execute the marketing campaign to members of the particular group. 
   
     
     
         18 . The one or more non-transitory computer-readable storage media of  claim 15 , the operations further comprising:
 selecting an augmented event timeline of the set of augmented event timelines; and   creating a string of symbols corresponding to the augmented event timeline, wherein each symbol in the string of symbols corresponds to an event in the augmented event timeline.   
     
     
         19 . The one or more non-transitory computer-readable storage media of  claim 18 , wherein determining, by the trained machine learning model, the predicted result associated with individual marketing campaigns used in individual augmented event timelines of the set of augmented event timelines comprises:
 predicting, by the trained machine learning model, one or more next symbols in the string of symbols.   
     
     
         20 . The one or more non-transitory computer-readable storage media of  claim 18 , the operations further comprising:
 determining that a particular event in the augmented event timeline includes a revenue event; and   modifying a symbol corresponding to the particular event to include a revenue indicator, the revenue indicator comprising one of an actual revenue amount, a revenue range, or a revenue magnitude.