A method includes receiving location reports indicating locations of mobile devices associated with users of an internet platform, registering a count for each location report, determining, for each location report received from a mobile device, a recent location report received from the mobile device indicating a previous location and registering a transition for each of a paired location report and recent location report, corresponding to a pair of locations. The method includes counting a number of transitions corresponding to a particular pair of locations and determining common transitions by comparing the number of transitions to a threshold value. The method includes comparing a location report received from a user's mobile device with location reports included in common transitions, and predicting, based on the comparison, a likelihood the user will arrive at a particular place within a particular time period or a likelihood that the user was at a particular place within a particular time before the current time.

The disclosed embodiments provide a system for performing unified propensity modeling across product versions. During operation, the system determines features and labels related to converting to multiple versions of a product by a first set of members, wherein the features and the labels span a unified timeframe and adhere to a unified data logic. Next, the system inputs the features and the labels as training data for one or more machine learning models. The system then applies the machine learning model(s) to additional features for a second set of members to produce scores representing likelihoods of the second set of members converting to the multiple versions of the product. Finally, the system generates, based on the scores, output for targeting the second set of members with the product.

An information processing apparatus comprises a controller configured to execute displaying an advertisement; specification of a moving body that moves at a place at which the advertisement to be displayed can be viewed; storing attribute information of the specified moving body; performing statistical processing for the stored attribute information of the moving body; and determining the advertisement to be displayed on the basis of a result of the statistical processing.

A method includes identifying, by a server, a content location assigned to a first content slot of a schedule template defining a display rotation loop based on multiple content slots. Each of the content slots in the schedule is associated with slot criteria, and the schedule template is associated with a digital display. The server generates schedule data that indicates the display rotation loop, the content location, and the slot criteria. Dynamic content retrievable from the content location is displayable at the digital display at a first time. The first time is based on the first slot criteria of the first content slot. The server transmits the schedule data via a network to the digital display.

The present invention relates to methods and systems for targeting and retargeting individuals with advertisement spots during television broadcasting. The method and system enable an advertiser for identifying and categorizing a set of viewers or individuals for retargeting advertisement based on parameters such as, but not limited to, interests or preferences of the individuals, past purchases and interactions of the individuals with the advertiser. The method and system further enable the advertiser to segregate the plurality of individuals into subgroups on the basis of information such as, but not limited to, demography, psychographic and behavioral characteristics of the plurality of individuals. The method and system then enable the advertiser to define one or more advertisement spots and corresponding advertisements to be delivered to different sub groups of individuals based on the categorization. Thereafter, the method and system retarget individuals by sending individualized messages in the one or more advertisement spots.

The method and system disclosed herein enables non-spamming dissemination of environment and proximity aware information and advertisements to a user of a mobile device. The method disclosed herein provides a client application on the mobile device. The client application detects the presence of base station sensor devices in proximity to the user. Service offerings information of vendors is then transferred to the client application. The client application categorizes the service offerings information into multiple categories. The client application communicates with the base station sensor devices to receive business information and advertisements of the vendors based on categories selected by the user. Environmental sensors capture environmental data of a region surrounding the base station sensor devices. The business information and advertisements are correlated with the environmental data and local time data. The correlated information and advertisements are then transferred to the client application.

Machine-learning based multi-step engagement strategy modification is described. Rather than rely heavily on human involvement to manage content delivery over the course of a campaign, the described learning-based engagement system modifies a multi-step engagement strategy, originally created by an engagement-system user, by leveraging machine-learning models. In particular, these leveraged machine-learning models are trained using data describing user interactions with delivered content as those interactions occur over the course of the campaign. Initially, the learning-based engagement system obtains a multi-step engagement strategy created by an engagement-system user. As the multi-step engagement strategy is deployed, the learning-based engagement system randomly adjusts aspects of the sequence of deliveries for some users. Based on data describing the interactions of recipients with deliveries served according to both the user-created and random multi-step engagement strategies, the machine-learning models generate a modified multi-step engagement strategy.

The present disclosure relates to a computer system configured establish and utilize a database for online ad realization prediction in an ad display platform associated with N parties, wherein N is a positive integral greater than 1. The computer system is configured obtain a party hierarchy for each of the N parties including a plurality of features of the party; select a target ad display event including N features, each of the N features corresponding to a node in a party hierarchy; obtain a prior probability reflecting an unconditional probability of ad realization occurrence at the target ad display event among all possible ad display events; for each of the N features: determine a marginal prior probability by decomposing components associated with the other N1 features from the prior probability; determine a marginal posterior probability based on the marginal prior probability; and save the marginal posterior probability in the corresponding node of the party hierarchy.

The invention provides, in some aspects, digital data processing methods of generating digital content pieces (e.g., email messages or portions thereof) that are customized in accord with individual recipient behaviors. Such methods include the step of generating and digitally transmitting to a digital data devices of a recipient a digital content piece that (i) has a call to action to which the recipient can respond and (ii) that has a plurality of features selected so as to maximize a probability, P(b.sub.1, b.sub.2, . . . , b.sub.M, x.sub.1, x.sub.2, . . . , x.sub.M), that the recipient will respond to that call to action, where that probability is defined by the relation
P(b.sub.1,b.sub.2, . . . , b.sub.M,x.sub.1,x.sub.2, . . . , x.sub.M)=exp(.sub.j=1, . . . , Mb.sub.jx.sub.j)/(1+exp(.sub.j=1, . . . , Mb.sub.jx.sub.j)) where x.sub.1, x.sub.2, . . . , x.sub.M are values for each of a plurality, M, of features characterizing the digital content piece and/or the recipient, b.sub.1, b.sub.2, . . . , b.sub.M are respective coefficients for each of the values x.sub.1, x.sub.2, . . . , x.sub.M.

Systems and methods are provided for automatically generating and maintaining user profile cookie sets. The user profile cookie sets may be used by a web crawler when gathering data such as advertisement data associated with one or more websites. The cookie sets may be generated by choosing a user profile with a set of user traits, selecting a set of websites related to the user traits, and browsing the selected set of websites using a web crawler while allowing the website to place cookies in storage of the web crawler. The cookie sets may be maintained by selecting a website to browse, selecting a user profile associated with the selected website, loading a previously generated cookie set for the selected user profile into the storage of a web crawler, and loading the webpage while allowing the website to place, update, or replace cookies in the storage of the web crawler.