Abstract: An embodiment may involve receiving input information related to an offered product or service, two or more layouts of a print advertisement for the offered product or service, demographics of potential buyers of the offered product or service, and online behavior of the potential buyers. The information may be normalized into a predefined schema for a machine-learning-based recommendation engine operated by a computing device. The embodiment may further involve determining respective selections of the two or more layouts for the potential buyers. The machine-learning-based recommendation engine may select a layout for a potential buyer based on the offered product or service, content and organization of the layout, demographics of the potential buyer, and online behavior of the potential buyer. The embodiment may also involve transmitting, to a printing system, one or more output files representing the offered product or service, the layout, and the potential buyer.

Abstract: An embodiment may involve receiving textual search queries that were entered into a web site. The embodiment may further involve generating a set of conforming textual search queries by removing, from the textual search queries, those that contain non-alphanumeric characters, more than a threshold number of characters, or are duplicates of another of the textual search queries. The embodiment may further involve applying pre-defined transformation rules to the conforming textual search queries to create records respectively associated with the conforming textual search queries, wherein each of the records contains a particular conforming textual search query, a reference to a web page on the web site containing content related to the particular conforming textual search query, and text describing a category of the particular conforming textual search query. The embodiments may further involve transmitting, to an Internet search engine, one or more files containing the records.

Abstract: An embodiment may involve receiving input information related to an offered product or service, two or more layouts of a print advertisement for the offered product or service, demographics of potential buyers of the offered product or service, and online behavior of the potential buyers. The information may be normalized into a predefined schema for a machine-learning-based recommendation engine operated by a computing device. The embodiment may further involve determining respective selections of the two or more layouts for the potential buyers. The machine-learning-based recommendation engine may select a layout for a potential buyer based on the offered product or service, content and organization of the layout, demographics of the potential buyer, and online behavior of the potential buyer. The embodiment may also involve transmitting, to a printing system, one or more output files representing the offered product or service, the layout, and the potential buyer.

Abstract: An embodiment may involve receiving input information related to an offered product or service, two or more layouts of a print advertisement for the offered product or service, demographics of potential buyers of the offered product or service, and online behavior of the potential buyers. The information may be normalized into a predefined schema for a machine-learning-based recommendation engine operated by a computing device. The embodiment may further involve determining respective selections of the two or more layouts for the potential buyers. The machine-learning-based recommendation engine may select a layout for a potential buyer based on the offered product or service, content and organization of the layout, demographics of the potential buyer, and online behavior of the potential buyer. The embodiment may also involve transmitting, to a printing system, one or more output files representing the offered product or service, the layout, and the potential buyer.

Abstract: An embodiment may involve receiving, from a third-party computing device, a bulk representation of textual search engine queries, and in response to receiving the bulk representation, processing each textual search engine query. The processing may include detecting non-conforming textual search engine queries and generating respective online advertising information for the conforming textual search engine queries. The embodiment may further involve transmitting, to a server device, at least one file representing the respective online advertising information for the conforming textual search engine queries. Reception of the at least one file and a subsequent command by the server device may cause a search engine device to carry out paid search advertising with the conforming textual search engine queries as keywords and in accordance with the respective online advertising information for the conforming textual search engine queries.

Abstract: An embodiment may involve receiving input information related to an offered product or service, two or more layouts of a print advertisement for the offered product or service, demographics of potential buyers of the offered product or service, and online behavior of the potential buyers. The information may be normalized into a predefined schema for a machine-learning-based recommendation engine operated by a computing device. The embodiment may further involve determining respective selections of the two or more layouts for the potential buyers. The machine-learning-based recommendation engine may select a layout for a potential buyer based on the offered product or service, content and organization of the layout, demographics of the potential buyer, and online behavior of the potential buyer. The embodiment may also involve transmitting, to a printing system, one or more output files representing the offered product or service, the layout, and the potential buyer.

Abstract: An embodiment may involve obtaining a recipient-specific record of interaction data for a particular recipient, the recipient-specific record including, for each of a plurality of electronic communications: (i) a respective timestamp indicating a time the respective electronic communication was transmitted and (ii) a respective indication of whether a client device requested a respective web resource using an individual identifier embedded in the respective electronic communication.