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.

Methods and systems for presenting online content elements based on information caused to be stored on a communication apparatus by a service provider. One of the methods is a method for presenting online content at a communication apparatus. The method comprises: obtaining information caused to be stored on the communication apparatus by a service provider providing network access to the communication apparatus, the information pertaining to a profile maintained by the service provider; determining an online content element to be presented at the communication apparatus based on the information; and causing the communication apparatus to present the online content element. The online content element may be an advertising content element forming an online advertisement, a primary content element of a network site, or an online page. The information may include location information, personal information, and/or bandwidth information. Servers for implementing the methods are also provided.

A system for adjusting a relevance weight value for a content item is described. The system comprises a content delivery module configured to deliver a plurality of content items to a device via a network. The content items are displayed on the device. A content storage module is configured to store a relevance weight value and a location in association with each content item. A location detection module is configured to determine a location of the wireless device. A user provides a feedback input for a content item. The relevance weight value associated with the location and the content item is adjusted according to the feedback input provided.

Methods, and systems, including computer programs encoded on computer-readable storage mediums, including a method for presenting a video content item in a first display area; concurrently presenting, with the video content item in the first display area, objects that are displayed during the presentation of the video content item in a second display area, wherein the objects persist in the second display area after the object is no longer displayed during the presentation of the video content item in the first display area; receiving an indication identifying one of the objects presented in the first display area or the second display area; and processing a tag associated with the object, the tag comprising a reference to a media item, wherein the processing comprises: accessing the media item referenced by the tag; and presenting the media item at least partially in the first display area or the second display area.

Provided are: a method for using a cohort for both a user analysis platform and a marketing platform, a method for setting advertisement providing methods of a charging user and a non-charge user to be different; and a method for providing a reward advertisement during the execution of an application.

Techniques for text message transmission are described herein. These techniques may include collecting multiple user IDs for electronic commerce. Using the user IDs, a server transmits a text message to multiple clients, and obtains activities of particular clients of the multiple clients in response to the text message to determine particular user IDs associated with the particular clients. Based on the obtained activities, the server generates and/or updates a graylist that includes one or more user IDs of the multiple user IDs different from the particular user IDs.

Methods and systems for automatically identifying and selecting preferred classification and regression trees are disclosed. Embodiments of the disclosed invention may be used to identify a specific decision tree or group of preferred trees that are predictively consistent across train and test samples evaluated against at least one node-specific constraint imposed by the decision-maker, while also having high predictive performance accuracy. Specifically, for a tree to be identified as preferred by embodiments of the disclosed invention, the train and test samples when evaluated node-by-node must agree on at least one key measure of predictive consistency. In addition to this node-by-node criterion, the decision-maker may adjust selection constraints to permit selection of a tree having a small number of node-by-node consistency disagreements, but with high overall tree predictive performance accuracy.

The disclosure relates in some cases to a technology for selecting one or more promotions to be presented to online customers using Bayesian bandits and affinity-based dynamic user clustering In some embodiments, a computer-implemented method determines a set of offers is determined, and computes affinity scores measuring affinities of users to items included in the offers. The method builds an affinity score distribution for the offers and identifies clusters of affinity scores for the offers using the corresponding affinity score distribution.

A method of coupon distribution is used in connection with a demand response (DR) event. The method includes clustering DR customers into customer clusters based on energy use behaviors of the DR customers. Suggested coupons are received from merchants, each coupon including load serving entity (LSE) and merchant contributions. Based on energy price forecast, the suggested coupons, and customer information, a coupon distribution is found to maximizes a financial benefit to the LSE and includes an optimal number of the suggested coupons to be distributed to the customer clusters. The suggested coupons are distributed to the customer clusters per the coupon distribution and collecting responses to the suggested coupons indicating participation. Based on the customer responses, the method includes estimating energy curtailment contributions of the DR customers and an actual energy price for the DR event and communicating to an independent system operator an energy transaction bid based thereon.

The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of features for a customer of a product. Next, the system uses the set of features to identify a likelihood of purchasing the product through a first channel by the customer and estimate a first customer lifetime value (CLV) for the customer through the first channel and a second CLV for the customer through a second channel. The system then selects an acquisition channel for the customer from the first and second channels based on the likelihood and the first and second CLVs. Finally, the system outputs a recommendation of the selected acquisition channel for use in marketing the product to the customer.