US20140143012A1

US20140143012A1 - Method and system for predictive marketing campigns based on users online behavior and profile

Info

Publication number: US20140143012A1
Application number: US14/086,238
Authority: US
Inventors: Mickey ALON; Mike TELEM
Original assignee: Insightera Ltd; Marketo Inc
Current assignee: Marketo Inc
Priority date: 2012-11-21
Filing date: 2013-11-21
Publication date: 2014-05-22
Also published as: US9569785B2; US20170109330A1; US20140143655A1; US10366146B2; US20190332650A1

Abstract

The present invention discloses a method for providing prediction of content usage in a website. The method comprising the steps of: real time monitoring traffic of visitors in a website, tracking visitors that are visiting the monitored website to identify one or more parameters relating to user profile, navigation path or content usage, applying at least one statistical algorithm on identified parameters, said algorithm is at least one of: clustering algorithm, nearest neighbor algorithm or probability algorithm and defining content replacement and recommendation for visitors when visiting the monitored website according analysis results of the at least one statistical algorithm.

Description

TECHNICAL FIELD

The present invention relates to the field of marketing prediction, and more particularly, to predicting content usage based on statistically analyzing online visitor's behavior patterns.

BACKGROUND ART

Current solutions for predicting content usage are based on likelihood of a user to consume a content item based on statistical usage the similar content items by other visitors ignoring the knowledge which can be collected of user identification and navigation behavior when browsing a particular website.
Known in the art predictive analytics utilizes machine learning algorithms over big data, using common practices of scoring, next best item and optimized email campaigns. The Big data systems which can work with batch and asynchronous processing, raise a challenge for providing predictive analytics data response that would be ready for real-time interactions.

SUMMARY OF INVENTION

The present invention discloses a method for providing prediction of content usage in a website. The method comprising the steps of: capturing and monitoring real time behavior of visitors in a website, tracking visitors that are visiting the monitored website to identify one or more parameters relating to visitor profile attributes, such as Geo location, navigation path or content usage, applying at least one statistical algorithm on identified parameters, said algorithm is at least one of: clustering algorithm, nearest neighbor algorithm or probability algorithm and defining content replacement and recommendation for visitors when visiting the monitored website according to the analysis results of the at least one statistical algorithm.
According to some embodiments of the present invention the clustering algorithm enables classifying visitors into groups by analyzing the profile and navigation activities parameters of the user.
According to some embodiments of the present invention the probability algorithm enable analyzing the monitored user behavior and identifying correlation/association between visitors profile parameters, navigation path and/or content usage for creating probability tree.
According to some embodiments of the present invention the nearest neighbor algorithm enable classifying visitors into groups by analyzing content usage parameters of the user.
According to some embodiments of the present invention the method further comprises the step of scoring the content items according to a probability tree created by the probability algorithm.
According to some embodiments of the present invention the method further comprises the step of scoring the content items according to Neighborhoods created by the nearest neighbor algorithm
According to some embodiments of the present invention the method further comprises the step of analyzing an organizations behavior by Identifying function of each user in the organization and classifying his behavior for generating marketing scenarios based on analyzed organizational behavior.
According to some embodiments of the present invention the method further comprises the step of checking user profiles and classified pattern behavior for identifying correlation with existing clients in CRM (Customer Relationship Management) database.
According to some embodiments of the present invention the method further comprises the step of characterizing a user's marketing state based on comparing analysis results to predefined marketing templates.
According to some embodiments of the present invention the method further comprises the step of scoring incoming leads based on CRM accounts similarity.
According to some embodiments of the present invention the method further comprises the step of providing recommendation for further communication/actions to be taken based on neighborhood and/or clustering groups or probability algorithm.
The present invention discloses a system for providing prediction of content usage in a website. The system is comprised of: a tracking module for monitoring traffic of visitors in a website and identifying one or more parameters relating to user profile, navigation path or content usage, statistical algorithm for analyzing identified parameters, said algorithm is at least one of: clustering algorithm, nearest neighbor algorithm or probability algorithm and prediction module for defining content replacement and recommendation for visitors when visiting the monitored website according to analysis results of the at least one statistical algorithm.
These, additional, and/or other aspects and/or advantages of the present invention are: set forth in the detailed description which follows; possibly inferable from the detailed description; and/or learnable by practice of the present invention.

BRIEF DESCRIPTION OF DRAWINGS

FIG. 1 is a block diagram of a system for adjusting content of webpages, according to some embodiments of the invention;

FIG. 2 is a flowchart illustrating a method of tracking visitors, according to some embodiments of the invention;

FIG. 3 is a flowchart illustrating a method of generating anonymous profile of a user, according to some embodiments of the invention;

FIG. 4 is a flowchart illustrating a method of clustering algorithm, according to some embodiments of the invention;

FIG. 5 is a flowchart illustrating a method of assigning visitors to clustered groups , according to some embodiments of the invention;

FIG. 6 is a flowchart illustrating a method of analyzing organization behavior, according to some embodiments of the invention;

FIG. 7A is a flowchart illustrating a method of near by neighbor algorithm, according to some embodiments of the invention;

FIG. 7B is a flowchart illustrating a method of CRM Association module, according to some embodiments of the invention;

FIG. 8A is a flowchart illustrating a method of probability algorithm, according to some embodiments of the invention;

FIG. 8B is a flowchart illustrating a method of scoring according to some embodiments of the invention; and

FIG. 9 is a flowchart illustrating a method of prediction module, according to some embodiments of the invention;

MODES FOR CARRYING OUT THE INVENTION

In the following detailed description of various embodiments, reference is made to the accompanying drawings that form a part thereof, and in which are shown by way of illustration specific embodiments in which the invention may be practiced. It is understood that other embodiments may be utilized and structural changes may be made without departing from the scope of the present invention.
The term “big data” as used herein in this application, is defined as a collection of data sets that is so large and complex that it is not possible to handle with database management tools. As per Gartner, “Big Data are high-volume, high-velocity, and/or high-variety information assets that require new forms of processing to enable enhanced decision making, insight discovery and process optimization.”
The term “anonymous profile” as used herein in this application, is defined as a visitor of a website that didn't identify by login process to the website.
The term “proprietary heuristics” as used herein in this application, is defined as experienced techniques that were developed by the applicant and are used when an exhaustive search or computation is impractical.
The present invention aims for statistical analysis of anonymous visitors behavior that navigate in an Internet website including at least one of: clicks, visits, navigation pattern, Geo location, role within the organization, association to an organization, social network or industry. It is suggested, according to the present invention, to enable evaluation process for analyzing marketing status and predicting content usage, providing content and recommendations based on the statistical analysis, marketing scenarios and strategies, as identified throughout the user navigation and content usage (i.e. behavior pattern in the internet website and content consumption).
The prediction process provides a marketing strategy which known as “prospect nurturing”. This marketing strategy enables serving personalized content to visitors and it is used today mostly by email communication, and only for identified prospects (i.e. visitors). The present invention allows real-time prospect nurturing for anonymous visitors throughout their navigation in the website. It may provide anonymous potential clients with marketing information to bring them into or advance them in the sales' cycle.
In other words, the present invention allows a real-time auto-prediction and marketing evaluation process based on detection of behavioral pattern, marketing scenarios and classification of anonymous visitors (i.e. potential clients). Anonymous visitors are normally at pre-lead state and nurturing them is called ‘seed nurturing’.
In ‘seed nurturing’ the classification of visitors is performed by heuristics to find conversion patterns behavior (i.e. conversion from an anonymous user to a business lead) that are common between anonymous visitors. Conversion patterns are the pattern behavior of anonymous visitors that are becoming business leads after being exposed to specific marketing material. For example, on his second visit to a web site an anonymous user sees a link to a white paper, the user clicks on it and reads it, and fills out a form requesting more details thus becomes a business lead. Identification of such conversion patterns may be used for verifying or updating the predefined rules in the engagement rules of the web content adjustments.
FIG. 1 is a block diagram of a system for predicting content usage and/or marketing status, according to some embodiments of the invention.
According to some embodiments of the present invention, anonymous application 100 aims to improve content consumption prediction and providing recommendation of content or further marketing activities for visitors that are coming via user communication devices 105. Optionally improving the marketing evaluation and prediction performed by identifying marketing status and scenario, according to the viewer's behavior (i.e. navigation path), activities associations and other parameters.
According to some embodiments of the present invention, the anonymous application 100 may activate a tracking module 110 to generate a profile of an anonymous user (i.e. viewer) by various parameters and store it in a profile database 115 as will be described in detail in FIG. 2.
According to some embodiments of the present invention, a clustering module 120 may monitor viewers by various parameters and cluster them into groups, as will be described in detail in FIG. 3.
The process of clustering viewers into groups involves analysis of big data. In order to save time and computer resources, proprietary heuristics are being implemented. These proprietary heuristics are taking into account intersections of profiles of visitors and industries. For example, a viewer that was clustered into a group of venture capital industry may view content related to currency rate and stocks.
According to some embodiments of the present invention, an anonymous profile generating module 117 may handle data on each viewer and assign each viewer to a group, as will be described in detail in FIG. 4.
According to some embodiments of the present invention, an assignment module 125 may handle a profile of a user and assign it to a predefined group, as will be described in detail in FIG. 5.
According to some embodiments of the present invention, a nearby neighbor module 140 may analyze behavior pattern of user's content usage, as will be described in detail in FIG. 7A.
According to some embodiments of the present invention, a CRM association module 145 may analyze behavior pattern of user's for associating with CRM data, as will be described in detail in FIG. 7 b.
According to some embodiments of the present invention, a probability module 160 may analyze behavior pattern of correlation between visitors navigation content usage activates, as will be described in detail in FIG. 8A.
According to some embodiments of the present invention, a scoring module 165 may analyze behavior patterns of correlation between visitors navigation and content usage activates, as will be described in detail in FIG. 8B.
According to some embodiments of the present invention, a prediction module 160 may operate to evaluate content usage of the visitors, provide recommendation for further engagements based on the marketing state and identifying market scenarios.
FIG. 2 is a flowchart illustrating a method of tracking visitors, according to some embodiments of the invention.
According to some embodiments of the present invention, tracking module 110 in FIG. 1 may monitor traffic in a specified website (stage 210).
According to some embodiments of the present invention, user communication device 105 in FIG. 1 of a viewer (i.e. user) that is navigating in the monitored website may be tracked to identify various parameters (stage 220) such as: (i) identifying geographic origin of the tracked viewer (stage 230); For example, a viewer coming from London and another viewer that is coming from New Delhi. (ii) Identifying organization or private origin of the tracked viewer (stage 240); In other words, checking if the viewer is navigating from a working place or from a residential place (iii) identifying social origin, of the tracked viewer, meaning checking if the user was referred from a social website such as Facebook™ (stage 250); (iv) identifying origin of website that the user is coming from (stage 260) For example, search engines like Google and Bing (v) identifying and checking actions of visitors (i.e. viewers) in the monitored website (stage 270). For example, search actions by keywords in the monitored website or navigating in a specific section of the website such as careers and openings, content selections and usage (consumption), content type, history (number of visits), geo location and goals.
According to some embodiments of the present invention, after performing various identifications, as mentioned above, the tracking module 110 in FIG. 1 may audit all identified data related to each tracked user and store it in a unique caching repository for enabling real time statistics and data retrieval on future engagements (stage 280).
FIG. 3 is a flowchart illustrating a method of generating anonymous profile of a user, according to some embodiments of the invention.
According to some embodiments of the present invention, anonymous profile generation module 125 in FIG. 1 may receive data for each user (stage 310) that was collected from tracking module 110. Next, behavior of each user in the website may be monitored (stage 320).
According to some embodiments of the present invention, period of time of exposure to webpages in the website may be checked and correlated with content and profile of visitors (stage 330).
According to some embodiments of the present invention, the monitored behavior may be analyzed (stage 340) and industry or geo location of the user may be identified (stage 350).
According to some embodiments of the present invention, the generation of user anonymous profile (step 360) is based on analyzed behavior and the groups classification according user's industry and organization association
FIG. 4 is a flowchart illustrating a method of clustering algorithm, according to some embodiments of the invention.
According to some embodiments of the present invention, clustering module 120 in FIG. 1 may monitor visitors that are navigating in a specified website (stage 410). During the monitoring, some or all of the following information is collected from the monitored visitors: origin details, contact details, navigation path (stage 410).
According to some embodiments of the present invention, clustering module 120 is checking usage of visitors contact details in the website via the website and other communication parties such as email, etc. (stage 420). The clustering module may check feedback and action of the visitors that are navigating in the monitored website such as registering to the monitored website (including its services) or initiation of contact via the website by the user such as, sending an email or calling representatives of the monitored website. Such information can be used to indicate on successful matching between the visitors' profile and behavior and the presented content adjusted by the application 100 in FIG. 1.
According to some embodiments of the present invention, clustering module 120 in FIG. 1 may check visitors' login to the website via a social network website such as Facebook™ (stage 430).
Finally, clustering module 120 in FIG. 1 may cluster visitors by generation of groups using analysis of statistics of the results of all checks and identifications as mentioned above (step 440): clicks, visits, geo location, revenue, organization size (optionally: navigation path, origin, social/organization/industry, association, history (number of visits), search terms, visitors' behavior including navigation path, selections, keywords used in information searches, and user feedback. The classification process may find correlation between the different parameters which characterize the user profile and its behavior for identifying groups of visitors which their characteristics indicate of at least one common interest or common behavior, such that the same content may be targeted to most visitors of the group.
The generation of groups may be based on the analyzed behavior using proprietary heuristics that were collected regarding a user's behavior as described above.
The proprietary heuristics techniques are used to analyze the user's grouping clustering data for reducing the scale of the big data problem by cross analyzing the group clustering data according to attributes (i.e. geo location, industry or organization association) of the user. In other words, instead of processing a large amount of data in case of a matching of a user to a group it may require to process only reduced amount of data records of group clustering data, using the heuristics related to the geo location, industry or organization association which may reduce usage of resources such as computer resources and time in the process.
To provide quick response, i.e. in less than 50 milliseconds, the present application clusters big data based on timeline of the navigation process, public digital organization and/or social data and actual visit timestamp. Indexing the data based on those parameters makes it possible to track trends, and retrieve relevant data for personalization of “anonymous visitors” while maintaining of a sustainable data model.
According to some embodiments of the present invention, clustering module may store clustered groups in unique caching repository for enabling real time statistics and data retrieval for engagement.
The unique caching repository utilizes an in-memory optimized matrix model, which allows real-time interactions on big data. This model is optimized for the usage of each statistical algorithms by implementing one of the following: high density matrix which filters out the low relevancy recommendation mapping, aggregated clustering data (hence eliminating duplicate content items records) or caching next best offer based on visitor timeline to enable real-time retrieval while the user navigates through the website and/or filtering out, less relevant or deprecated/older visitors.
This unique caching repository enables to optimize memory footprint from Giga bytes on disk to megabytes in memory.
FIG. 5 is a flowchart illustrating a method of assigning visitors to clustered groups, according to some embodiments of the invention.
According to some embodiments of the present invention, assignment module 125 may receive a profile of a user (stage 510) and analyze it (stage 520). Next, assignment module 125 may assign the user to a predefined group using the profile of the user and to calculate correlation (stage 530). The present application suggests a classification process, which utilizes correlation of time and IP and name of an organization to identify visitors and their clustered groups.
Finally, in case there is a specified amount of exceptional visitors that are not assigned to the group, a training process of clustering user profiles is reactivated (stage 540). The user profiles and behavior may change over time; therefore accordingly the group clustering has to be adapted to reflect the change. The present invention provides a dynamic model by continuously analyzing statistics regarding a user's profile and behavior in comparison to the group clustering definition and identifying when statistically the amount of exceptional visitors has exceeded a predefined level. In this case, the training process is reactivated for a predefined time period for redefining the group clustering.
FIG. 6 is a flowchart illustrating a method of analyzing organizational behavior, according to some embodiments of the invention. The module analyzes anonymous profiles to identify visitors associated with the same organization by checking the identified origin of the user (step 610), contact details entered by the visitors or communication message used by the user. The activities of identified visitors of the same organization are analyzed for identifying behavior patterns of an organization by checking time period usage, association and type of activities of the visitors (step 620). This analysis enables to identify functions of each user in the organization and classifying his behavior for analyzing marketing behavioral patterns of the organization (step 630). Optionally based on analyzing marketing behavioral pattern can be generated marketing scenarios templates (steps 640 and 650).
FIG. 7A is a flowchart illustrating a method of nearest neighbor algorithm, according to some embodiments of the invention. The nearest neighbor algorithm include the following steps: analyzing visitors actions sequence in the website such as the sequence of content selection and usage (step 710), classifying visitors actions by type to identify content consumption action (step 720), analyzing actions in relation to their occurrence time (step 730), for example if they occurred in the first visit of the user or the second one and finally applying nearest neighbor algorithm using collaborative filtering (step 740) for creating nearby neighbor groups based on behavior including URLs and content items (Asset) consumed by visitors. Optionally the creation neighbor groups, is further depended on search terms, content selections, content type, visits history (number of visits). The created nearby neighbor groups are stored in unique caching repository for enabling real time statistics and data retrieval for engagement (step 750).
FIG. 7B is a flowchart illustrating a method of CRM Association module, according to some embodiments of the invention. The CRM Association module applies one of the following steps: classifying behavior patterns of visitors to characterize their intentions, needs and marketing state/status within a sales scenario (step 770), such as awareness, interest, evaluation etc. Based on user profiles, classified pattern behavior and marketing state are identified returning clients in CRM database (step 780).
FIG. 8A is a flowchart illustrating a method of probability algorithm, according to some embodiments of the invention. The probability module applies at least one of the following steps: analyzing navigation path of the visitors, content selection and consumption (step 810), identifying statistical correlation or association between successive action of navigation and content selection and consumption (step 820) and accordingly build content items (Assets) probability tree based on visitors action (click stream) or identified correlation (step 830). The created probability tree is stored in a unique caching repository for enabling real time statistics and data retrieval for engagement (step 840).
FIG. 8B is a flowchart illustrating a method of scoring according to some embodiments of the invention. The scoring algorithm includes at least one of the flowing steps: using probability tree data for scoring content items, using statistics of nearest neighbor algorithm for scoring content items and integrating scores content items of the probability tree nearest neighbor algorithm. Optionally the module may score incoming leads based on CRM accounts similarity.
FIG. 9 is a flowchart illustrating a method of prediction module, according to some embodiments of the invention.
The prediction module provides two types of recommendations:

- “action” recommendation including future communication/actions to be taken based on neighborhood and/or clustering groups or probability tree.

According to further option the recommended actions are based on marketing status/stage in the sale process which may be predefined by using marketing scenarios or identified pattern of actions(step 950)

- replacement and content recommendation (which can be optionally based on automatic rules) for the specific user, these recommendations are predicted using the results analysis of clustering and/or neighborhood grouping and or probability tree. Optionally the prediction is based on marketing status in a sale or analyzed behavioral pattern.

According to other embodiments of the present invention the content recommendation is based on content items (Assets) clustering algorithm which enable classifying content into groups by analyzing plurality of attributes of the visitors that consumed the content (i.e. clicks, visits, Geo, location, industry, revenue, organization size, organization revenue).
According to some embodiments of the present invention, the module further comprises at least one of the following steps: Optional analyzing marketing state of the visitors is a sale process (step 910), optional, analyzing organization interaction pattern between the organization organs (step 920), optional comparing analysis results to predefined marketing scenarios templates (step 930), optional Predicting/Estimating marketing status/stage of user or organization within a sale scenario (step 940),
Optionally the module may check analysis results against CRM data. The estimation may be used for providing recommendation for further communications/actions to be taken based on estimated marketing status/stage and predefined marketing scenarios.
Many alterations and modifications may be made by those having ordinary skill in the art without departing from the spirit and scope of the invention. Therefore, it must be understood that the illustrated embodiment has been set forth only for the purposes of example and that it should not be taken as limiting the invention as defined by the following invention and it's various embodiments.
Therefore, it must be understood that the illustrated embodiment has been set forth only for the purposes of example and that it should not be taken as limiting the invention as defined by the following claims. For example, notwithstanding the fact that the elements of a claim are set forth below in a certain combination, it must be expressly understood that the invention includes other combinations of fewer, more or different elements, which are disclosed in above even when not initially claimed in such combinations. A teaching that two elements are combined in a claimed combination is further to be understood as also allowing for a claimed combination in which the two elements are not combined with each other, but may be used alone or combined in other combinations. The excision of any disclosed element of the invention is explicitly contemplated as within the scope of the invention.
The words used in this specification to describe the invention and its various embodiments are to be understood not only in the sense of their commonly defined meanings, but to include by special definition in this specification structure, material or acts beyond the scope of the commonly defined meanings. Thus if an element can be understood in the context of this specification as including more than one meaning, then its use in a claim must be understood as being generic to all possible meanings supported by the specification and by the word itself.
The definitions of the words or elements of the following claims are, therefore, defined in this specification to include not only the combination of elements which are literally set forth, but all equivalent structure, material or acts for performing substantially the same function in substantially the same way to obtain substantially the same result. In this sense it is therefore contemplated that an equivalent substitution of two or more elements may be made for any one of the elements in the claims below or that a single element may be substituted for two or more elements in a claim. Although elements may be described above as acting in certain combinations and even initially claimed as such, it is to be expressly understood that one or more elements from a claimed combination can in some cases be excised from the combination and that the claimed combination may be directed to a sub-combination or variation of a sub-combination.
Insubstantial changes from the claimed subject matter as viewed by a person with ordinary skill in the art, now known or later devised, are expressly contemplated as being equivalently within the scope of the claims. Therefore, obvious substitutions now or later known to one with ordinary skill in the art are defined to be within the scope of the defined elements.
The claims are thus to be understood to include what is specifically illustrated and described above, what is conceptually equivalent, what can be obviously substituted and also what essentially incorporates the essential idea of the invention.
Although the invention has been described in detail, nevertheless changes and modifications, which do not depart from the teachings of the present invention, will be evident to those skilled in the art. Such changes and modifications are deemed to come within the purview of the present invention and the appended claims.

Claims

What is claimed is:

1. A method for providing prediction of content usage in a website, said method comprising the steps of:

real time monitoring traffic of visitors in a website;

tracking visitors that are visiting the monitored website to identify one or more parameters relating to user profile, navigation path or content usage;

applying at least one statistical algorithm on identified parameters, said algorithm is at least one of: clustering algorithm, nearest neighbor algorithm or probability algorithm and

defining content replacement and recommendation for visitors when visiting the monitored website according the statistical algorithm analysis results of the at least one statistical algorithm.

2. The method of claim 1 clustering algorithm enable classifying user into groups by analyzing of profile and navigation activities parameters of the user.

3. The method of claim 1 wherein the probability algorithm enables analyzing the monitored user behavior and identifying correlation or association between visitors profile parameters, navigation path and/or content usage for creating probability tree.

4. The method of claim 1 wherein the nearest neighbor algorithm enable classifying visitors into groups by analyzing content usage parameters of the user.

5. The method of claim 1 further comprising the step of scoring the content items according to a probability tree created by the probability algorithm.

6. The method of claim 1 further comprising the step of scoring the content items according to Neighborhoods created by the nearest neighbor algorithm.

7. The method of claim 1 further comprising the step of analyzing organization behavior by Identifying function of each user in the organization and classifying his behavior for generating marketing scenarios based on analyzed organization behavioral.

8. The method of claim 1 further comprising the step of checking user profiles and classified pattern behavior for identifying correlation with existing clients in CRM database.

9. The method of claim 1 further comprising the step of characterizing user marketing state in a sale scenario based on comparing analysis results to predefined marketing templates.

10. The method of claim 1 further comprising the step of scoring incoming leads based on CRM accounts similarity.

11. The method of claim 1 further comprising the step of providing recommendation for further communication or actions to be taken based on one of the following: neighborhood and/or clustering groups or probability algorithm.

12. The method of claim 1 wherein the statistical algorithm analysis results are cached using in-memory optimized matrix model, which allow real-time interactions on big data.

13. The method of claim 1 wherein the content recommendation is based on content items clustering algorithm which enable classifying content into groups by analyzing plurality of attributes of the visitors that consumed the content.

14. A system for providing prediction of content usage in a website, said system comprised of:

A tracking module for monitoring traffic of visitors in a website and identifying one or more parameters relating to user profile, navigation path or content usage;

statistical algorithm for analyzing identified parameters, said algorithm is at least one of: clustering algorithm, nearest neighbor algorithm or probability algorithm and

prediction module for defining content replacement and recommendation for visitors when visiting the monitored website according to analysis results of the at least one statistical algorithm.

15. The system of claim 14 wherein the clustering algorithm enables classifying user into groups by analyzing of profile and navigation activities parameters of the user.

16. The system of claim 14 wherein the probability algorithm enables analyzing the monitored user behavior and identifying correlation/association between visitors profile parameters, navigation path and/or content usage for creating probability tree.

17. The system of claim 14 wherein the nearby neighbor algorithm enables classifying user into groups by analyzing content usage parameters of the user.

18. The system of claim 14 wherein the prediction is further based on scoring the content items according to probability tree created by the probability algorithm.

19. The system of claim 14 wherein the statistical algorithm further comprises the step of analyzing organization behavior by Identifying function of each user in the organization and classifying his behavior for generating marketing scenarios based on analyzed organization behavioral.

20. The system of claim 14 wherein the prediction is further based on checking user profiles and classified pattern behavior for identifying existing clients in CRM database.

21. The system of claim 14 the statistical algorithm further comprise characterizing user marketing state in a sale scenario based on comparing analysis results to predefined marketing templates.

22. The system of claim 14 wherein the prediction module is further based on scoring incoming lead based on CRM accounts similarity.

23. The system of claim 14 wherein the prediction module further providing recommendation for further communication or actions to be taken, based on neighborhood and/or clustering groups or probability algorithm.