Sales prediction systems and methods

Abstract

Computer implemented sales prediction system collects data relating to events of visitors showing an interest in a client company from plural data sources, an organization module which organizes collected data into different event types and separates collected event counts in each event type between non-recent and recent events occurring within a predetermined time period, a first processing module which periodically calculates weighting for each event type based on recent and non-recent events for the event type compared to totals for other selected event types, a second processing module which periodically calculates sales prediction scores for each visitor and companies with which visitors are associated based on accumulated event data and weighting, and a reporting and data extract module which is configured to detect variation in sales prediction scores over time to identify spikes which can predict upcoming sales and to provide predicted sales information and leads to the client company.

What is claimed is: 
     
         1 . A method comprising using at least one hardware processor to:
 periodically,
 collect activity data representing activity of a visitor at a website comprising one or more webpages, wherein the activity data comprises an Internet Protocol (IP) address, domain, or cookie of the visitor, wherein the activity comprises a plurality of events, and wherein the plurality of events comprises one or more visits to the one or more webpages, 
 map the IP address, domain, or cookie of the visitor to a known entity using a lookup, and 
 calculate a prediction score for the known entity, based on the plurality of events represented in the activity data, by, at least in part,
 for each visited webpage, calculating a Q-score based on a number of visits to that webpage, and 
 aggregating each calculated Q-score into the prediction score; and, 
 
   when the prediction score for the known entity in a period represents a spike relative to one or more prior prediction scores calculated for the known entity in one or more prior periods, providing data, which enables one or more marketing or sales activities to the known entity, to at least one recipient.   
     
     
         2 . The method of  claim 1 , wherein the Q-score for each visited webpage is based on the number of visits to that webpage and a weight associated with that webpage. 
     
     
         3 . The method of  claim 2 , wherein, for each visited webpage, calculating a Q-score based on a number of visits to that webpage and a weight associated with that webpage comprises increasing the weight associated with webpages that have been visited within a certain time period preceding the calculation of the Q-score. 
     
     
         4 . The method of  claim 2 , wherein the weights associated with each visited webpage represent a relationship between the visited webpage and a product marketed through the website, such that the prediction score represents a likelihood that the known entity will purchase the product. 
     
     
         5 . The method of  claim 1 , wherein the plurality of events comprise one or more searches performed on the website, and wherein calculating the prediction score further comprises calculating a Q-score for each of the one or more searches. 
     
     
         6 . The method of  claim 1 , wherein the plurality of events comprise one or more click events, and wherein calculating the prediction score further comprises calculating a Q-score for each of the one or more click events. 
     
     
         7 . The method of  claim 6 , wherein at least one of the one or more click events comprises selecting an online advertisement. 
     
     
         8 . The method of  claim 1 , wherein the plurality of events comprise filling out one or more online forms, and wherein calculating the prediction score further comprises calculating a Q-score for each of the one or more online forms. 
     
     
         9 . The method of  claim 1 , wherein the plurality of events comprise one or more online chats, and wherein calculating the prediction score further comprises calculating a Q-score for each of the one or more online chats. 
     
     
         10 . The method of  claim 1 , further comprising collecting additional activity data representing attendance of the known entity at one or more trade shows or seminars, and wherein calculating the prediction score further comprises calculating a Q-score for each attendance of the known entity at the one or more trade shows or seminars. 
     
     
         11 . The method of  claim 1 , wherein the plurality of events comprise one or more price requests, and wherein calculating the prediction score further comprises calculating a Q-score for each of the one or more price requests. 
     
     
         12 . The method of  claim 1 , wherein the plurality of events comprise one or more subscriptions to a web feed, and wherein calculating the prediction score further comprises calculating a Q-score for each of the one or more subscriptions to a web feed. 
     
     
         13 . The method of  claim 1 , wherein the plurality of events comprise watching one or more videos, and wherein calculating the prediction score further comprises calculating a Q-score for each of the watched one or more videos. 
     
     
         14 . The method of  claim 1 , wherein the plurality of events comprise one or more downloads of an electronic document, and wherein calculating the prediction score further comprises calculating a Q-score for each of the one or more downloads of an electronic document. 
     
     
         15 . The method of  claim 1 , wherein the plurality of events comprise one or more interactions with an email offer, and wherein calculating the prediction score further comprises calculating a Q-score for each of the one or more interactions with an email offer. 
     
     
         16 . The method of  claim 15 , wherein the one or more interactions comprise one or more of opening an email offer and responding to an email offer. 
     
     
         17 . The method of  claim 1 , wherein calculating a prediction score for the known entity based on the plurality of events represented in the activity data comprises weighting each of the plurality of events according to a predictive model. 
     
     
         18 . The method of  claim 17 , wherein the predictive model defines weightings for one or more of the plurality of events based on a likelihood of the one or more events to precede a purchase. 
     
     
         19 . The method of  claim 1 , wherein the spike represents an increase in the prediction score for the known entity, relative to one or more prior prediction scores for the known entity, that exceeds a threshold. 
     
     
         20 . The method of  claim 1 , wherein the one or more marketing or sales activities comprise personalizing a website experience for the known entity. 
     
     
         21 . The method of  claim 1 , wherein the one or more marketing or sales activities comprise sending a targeted message to the known entity. 
     
     
         22 . The method of  claim 1 , wherein providing data, which enables one or more marketing or sales activities to the known entity, comprises generating an alert to the at least one recipient. 
     
     
         23 . The method of  claim 1 , wherein providing data, which enables one or more marketing or sales activities to the known entity, to at least one recipient comprises providing a lead, identifying the known entity, to one or both of a customer relationship management system and a marketing automation system. 
     
     
         24 . The method of  claim 1 , wherein providing data, which enables one or more marketing or sales activities to the known entity, comprises adding contact information for the known entity to at least one telemarketing list. 
     
     
         25 . The method of  claim 1 , wherein providing data, which enables one or more marketing or sales activities to the known entity, comprises retrieving contact information associated with the known entity. 
     
     
         26 . The method of  claim 1 , wherein the known entity is a company, and wherein the prediction score for the company is calculated based on a plurality of events represented in activity data from a plurality of visitors associated with the company. 
     
     
         27 . The method of  claim 1 , wherein the known entity is a contact. 
     
     
         28 . The method of  claim 1 , wherein the prediction score represents one or both of a relative degree of interest in a product or a relative intent to purchase the product. 
     
     
         29 . A system comprising:
 at least one hardware processor; and   one or more software modules configured to, when executed by the at least one hardware processor,
 periodically,
 collect activity data representing activity of a visitor at a website comprising one or more webpages, wherein the activity data comprises an Internet Protocol (IP) address, domain, or cookie of the visitor, wherein the activity comprises a plurality of events, and wherein the plurality of events comprises one or more visits to the one or more webpages, 
 map the IP address, domain, or cookie of the visitor to a known entity using a lookup, and 
 calculate a prediction score for the known entity, based on the plurality of events represented in the activity data, by, at least in part,
 for each visited webpage, calculating a Q-score based on a number of visits to that webpage, and 
 aggregating each calculated Q-score into the prediction score, and, 
 
 
 when the prediction score for the known entity in a period represents a spike relative to one or more prior prediction scores calculated for the known entity in prior periods, provide data, which enables one or more marketing or sales activities to the known entity, to at least one recipient. 
   
     
     
         30 . A non-transitory computer-readable medium having instructions stored thereon, wherein the instructions, when executed by a processor, cause the processor to:
 periodically,
 collect activity data representing activity of a visitor at a website comprising one or more webpages, wherein the activity data comprises an Internet Protocol (IP) address, domain, or cookie of the visitor, wherein the activity comprises a plurality of events, and wherein the plurality of events comprises one or more visits to the one or more webpages, 
 map the IP address, domain, or cookie of the visitor to a known entity using a lookup, and 
 calculate a prediction score for the known entity, based on the plurality of events represented in the activity data, by, at least in part,
 for each visited webpage, calculating a Q-score based on a number of visits to that webpage, and 
 aggregating each calculated Q-score into the prediction score; and, 
 
   when the prediction score for the known entity in a period represents a spike relative to one or more prior prediction scores calculated for the known entity in one or more prior periods, provide data, which enables one or more marketing or sales activities to the known entity, to at least one recipient.