An example method involves a computing device displaying a first action-outcome node corresponding to a first marketing-campaign action, displaying a plurality of outcomes of the first marketing-campaign action, positioned around the first action-outcome node, wherein each outcome corresponds to a potential result of the first marketing-campaign action, displaying a second action-outcome node corresponding to a second marketing-campaign action, displaying a plurality of outcomes of the second marketing-campaign action, positioned around the second action-outcome node, wherein each outcome corresponds to a potential result of the second marketing-campaign action, and displaying a graphical link connecting an outcome of the first action-outcome node to the second action-outcome node.

Systems, methods, and computer-readable storage media that may be used to generate causal models and calculate a selection bias in mixed media. In some embodiments, the selection bias calculation is in search sponsored content in the context of mixed media modeling. In some embodiments, a method for search bias correction is based on the back-door criterion from causal inference.

A method of serving targeted content messages for display in a website accessed in a browser program of a networked computer communicatively connected to a network at a network address for communications, delivers uniquely targeted content messages displayed in websites viewed in web browsers. The method includes placing a script device in a website file, processing the website file, together with the script device by a particular web browser on download of the website file, including by determining the network address of the networked computer, determining an identifier of the website file, and sending an artifact representing the network address and the identifier over the network to a server computer. The method also includes detecting the network address and the identifier by the server computer, querying a database for a database article related to the network address and the identifier, constructing a script program stored in memory of the server computer for the particular browser and website file, and constructing an ad device stored in memory of the web browser device from the script program. The method further includes calling the server computer by the ad device by communication of an identifier representing an action of the web browser device, receiving the identifier by the server computer, querying the database for a select message artifact related to the script program, the identifier, the website file, and the web browser, and responding by the server computer to the web browser with the select message artifact. A message represented by the select message artifact is displayed in the website then viewed in a browser window of the web browser. Messages can be prioritized and are uniquely targeted in content, based on real-time activities of the web browser.

Methods and systems for improved and efficient campaign message classification are disclosed. By automating the campaign message classification process, the system can improve efficiency in categorizing and managing campaign messages. The system can predict a message's type or characteristics via an ensemble model that comprises one or more logic-rule model(s) and machine learning language model(s). The ensemble model can process various data and predict a message's type or characteristics based on an aggregated prediction mechanism.

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform: tracking touchpoints by a user over a first time period; after receiving an order, determining, using a machine-learning model, a respective contribution of each of the touchpoints, wherein the machine-learning model is trained to predict a probability of the user placing the order during a second time period based on an input feature vector representing a set of touchpoints; and allocating a respective percentage of credit for the order to the each of the touchpoints based on the respective contributions of the each of the touchpoints. Other embodiments are disclosed.

A system and method enable exploration of cold ads in an online information system. Cold ads are ads that are new to the system and do not yet have reliable click through rate (CTR) estimates or click probabilities. The method and system selectively boost the click probabilities of cold ads to increase their likelihood of participating in and winning an auction so that the cold ad get more impressions, but without adversely affecting revenue in a production environment when cold ads are introduced.

An apparatus and a method of providing Internet advertising according to an exemplary embodiment is connected with a medium, an advertiser server, and a user terminal via a wired/wireless communication network, and includes: an access information collecting unit which collects access information about a user for the medium; a movement information collecting unit which collects movement information about the user for one or more advertising pages provided from the advertiser server; a user analyzing unit which analyses a tendency of the user based on the access information and the movement information; an advertising page transmission rate calculating unit which calculates an advertising page transmission rate based on a result of the analysis of the tendency of the user; and an advertising transmitting unit which transmits the one or more advertising pages to the user terminal based on the advertising page transmission rate.

Systems, methods, and non-transitory computer readable media can obtain an advertisement via a user interface associated with an application. One or more qualitative ratings associated with the advertisement can be predicted based on a machine learning model. One or more recommendations for improving the qualitative ratings associated with the advertisement can be provided, via the user interface, based at least in part on one or more advertisements that are visually similar to the advertisement.

Systems, methods, and non-transitory computer readable media can determine a representation of an advertisement based on a first machine learning model. The representation can be provided to a second machine learning model. One or more qualitative ratings associated with the advertisement can be determined based on the second machine learning model.

An advertisement management server in a communication system receives information of advertisements, determines an advertising value calculation policy, estimates a value of an advertising value element according to the information of each advertisement, calculates a value of each advertisement using the value of the advertising value element and the advertising value calculation policy as reference factors. The server instructs the communication system to broadcast the advertisements for displaying on the user terminals according to the calculated value of each advertisement.