The present disclosure includes a system, method, and article of manufacture for measuring the effectiveness of an advertisement. In various embodiments, the system may compare exposed data indicating that a first customer was exposed to a targeted advertisement to a first spending activity associated with the first customer. The system may further compare unexposed data indicating that a second customer was exposed to a neutral advertisement to a second spending activity associated with the second customer. Further still, the system may, in various embodiments, generate a spend report based on the comparing the exposed data to the first spending activity and the comparing the unexposed data to the second spending activity.

An advertisement distribution device includes: an arrangement position acquisition unit configured to acquire an arrangement position on a display screen of a terminal to display advertisement information; an attention degree index extracting unit configured to extract an attention degree index of the arrangement position based on acquisition of a specific position on the display screen and an attention degree index of the specific position; an arrangement position ranking unit configured to rank a plurality of arrangement positions based on a plurality of attention degree indices extracted by the attention degree index extracting unit; a distribution information ranking unit configured to rank a plurality of pieces of advertisement information based on a predetermined ranking process; and a distribution unit configured to distribute the plurality of pieces of advertisement information based on the ranks of the plurality of pieces of advertisement information and the ranks of the plurality of arrangement positions.

Portable devices include environmental sensors that generate metrics about the environment (e.g., accelerometers detecting impulses and vibration, and GPS receivers detecting position and velocity). Such devices often use environmental metrics to extract user input directed at the device by the user, and status information about the device and the environment. Presented herein are techniques for using environmental metrics to infer physical activities performed by the user while attached to the device. For example, jogging may be inferred from regular, strong impulses and typical jogging speed; walking may be inferred from regular, weak impulses and typical walking speed; and riding in a vehicle may be inferred from low-level vibrations and high speed (optionally identifying the type of vehicle ridden by the user). Based on these inferences, the device may automatically present applications and/or or adjust user interfaces suitable for the user's physical activity, rather than responsive to user input.

The present disclosure includes a system, method, and article of manufacture for spend based targeting. In various embodiments, the system may transmit, to a third party system, a spend data file associating a first party cookie ID with spend data, as well as a first party cookie ID and/or a third party cookie ID to a web client. The web client may transmit the first party cookie ID and/or the third party cookie ID to the third party system, and the third party system may generate a look alike model for targeting advertisements to the web client based on the spend data file and clickstream data associated with the web client. In various embodiments, the third party system may match the third party cookie ID with the first party cookie ID in the spend data file, which may associate a customer with a segment.

A method and system for analysis and evaluation of branding of commercial products embedded in entertainment programming. The entertainment programming may be divided into blocks that are compared to several rule sets defining audio visual and other attributes of the commercial products to evaluate parameters such as recall of the product by viewers.

The present disclosure includes a system, method, and article of manufacture for targeting ad impressions. A list of customer records may be transmitted to a service provider system that identifies a matched customer and installs a cookie on a web client associated with the matched customer. The system may further receive a campaign request from a merchant and transmit the campaign request to the service provider system which may add a flag to the cookie based on the campaign request as well as instruct a media buyer system to bid on an ad impression for the matched customer based on the flag. The system may further receive an expenditure associated with the matched customer who received the ad impression and compare the expenditure to an expenditure associated with a customer who did not receive targeted ad impression but fits parameters associated with the campaign request.

The disclosed systems evaluate user responses to various potential meal-kit menu designs and isolate variables having an impact on customer conversion, enabling a meal-kit company to select more effective meal-kit menus and to avoid waste associated with inaccurately predicting demand for meal-kits.

A method that incorporates teachings of the present disclosure may include, for example, transmitting media content to a group of set top boxes for presentation with an overlay superimposed onto the media content, where the overlay can include a timeline corresponding to the presentation of the media content and receiving a first comment from a first set top box of the group of set top boxes, where the first comment is presentable with the overlay and the media content by the group of set top boxes. Additional steps can include receiving a tag generated at a first set top box during presentation of the media content, presenting the tag while the media content is presented, correlating the tag to a portion of the media content timeline and analyzing metadata associated with the portion of the timeline that is tagged to determine a first marketing parameter. Other embodiments are disclosed.

Embodiments of the invention present an approach to conversion rate estimation which relies on using past performance observations along user, publisher, and advertiser data hierarchies. More specifically, embodiments of the invention model the conversion event at different select hierarchical levels with separate binomial distributions and estimate the distribution parameters individually. It is shown how to combine these individual estimators using logistic regression to identify conversion events accurately. Embodiments of the invention can also handle many practical issues, such as data imbalance, missing data, and output probability calibration, which render this estimation problem more difficult for a real-world implementation of the approach.

Groups of social media influencers may be organized and managed to execute advertising campaigns. The groups may be organized to reach targeted demographics for the campaign. The management tools for the group may include synchronization and timing interfaces that may coordinate and schedule posts amongst the group members, feedback and analytics displays that may show progress against group and individual goals, and interaction mechanisms by which group members may communicate. In some cases, groups may be self-organizing, where a group member may recruit and manage other members. In other cases, groups may be organized by an advertiser, or may be organized by a third party, such as an advertising platform.