Methods and systems for predicting performance of creative content are disclosed. Exemplary implementations may: receive a collection of images; provide a context to a user; serially cause display of pairs of images on a computer interface; receive user responses indicating which image of each pair is preferred given the context; determine a resonance value for each image based on a number of times the user responses indicate each image is preferred when displayed in a pair of images; determine a confidence score for each image; generate one or more models for predicting image performance based on one or more of the resonance value and the confidence score for each image; receive a plurality of candidate images; determine, using at least one model, a first metric set for each candidate; and cause display of a listing of the candidate images, the listing including the first metric set for each candidate image.

Methods, apparatus, systems, and articles of manufacture to perform computer-based monitoring of audiences of network-based media using information theory to estimate intermediate level unions are disclosed. An example apparatus to determine a deduplicated, census-based audience metric of media includes panel union calculator circuitry to calculate a threshold statistic corresponding to an intermediate union of a panel hierarchy, and census union calculator circuitry to calculate a deduplicated audience value corresponding to the intermediate union of the census hierarchy based on the threshold statistic.

In an illustrative embodiment, systems and methods for an augmented reality (AR) system enable merchant-to-customer engagement through context-aware digital content placement. In an embodiment, one element of the system allows merchants to upload, customize, and place AR media objects, and another element allows customers to discover and interact with said content in real-world environments. In an embodiment, another element of the system dynamically ranks and serves AR content based on user behavior, demographics, time, and location. In alternative embodiments, an artificial intelligence engine dynamically generates personalized AR media objects based on real-time user preferences, history, and environmental context. In some embodiments, features include interactive merchant storefronts, digital promotions, real-time analytics, user rewards, breadcrumb-based AR trails, and dynamically personalized AR experiences to encourage repeated engagement.

Systems, apparatuses, and methods are described for adjusted exposure threshold values. Each user may be associated with one or more of a plurality of exposure threshold values, for example, a frequency cap value, that may be a cap (e.g., threshold) on the number of times a repeat advertisement content may be output to a user. Exposure threshold values may be modified based on one or more viewing statistics, for example, information about one or more interactions of the user associated with one or more outputs of repeat advertisement content, environment information, and/or one or more advertisement characteristics.

This document describes the collection, generation, distribution, and management of online web content. The devices, systems, and methods described herein can be used to collect and generate online web content and communications. Specifically, the disclosed devices and systems may be employed to produce one or more marketing and/or advertising campaigns, as well as for monitoring, managing, defining the efficiency, effectiveness, and workability of the campaign with respect to generating user engagement, thereby accurately determining the cost benefits of the campaign. The analytic results provided may then be used to guide the generation of original web content, such as for the purposes of enhancing customer or follower experience, driving business, and for driving advertising campaigns. Alternatively, web content that is in the public domain, and determined to perform well, can be reproduced, referenced, or otherwise referred to, in the context of promoting or presenting the user's web content.

Computer implemented methods and systems for controlling sending of messages to retailers utilizing a B2B marketplace platform are described herein. Machine learning is used to train a communications timing model and a retailer interest model based on past messages sent to and received by each retailer of a plurality of retailers. The trained communications timing model is used to determine, for each retailer, a preferred timing for the retailer receiving messages from the B2B marketplace. The trained retailer interest model is used to determine, for each retailer, a respective level of interest for each of a plurality of different message types that may be sent to the retailer by the B2B marketplace. A decision engine schedules and controls sending of the messages to each retailer based on outputs of the communications timing model and the retailer interest model.

The subject technology identifies obfuscated email events received from one or more internet service providers (ISPs). The data deobfuscation layer may identify email messages including obfuscated open events and locations by monitoring the open rates of email messages received by different operating systems, ISPs, and/or device types. The data deobfuscation layer may determine accurate campaign level metrics and/or user open probabilities for batches of email messages having obfuscated events. For example, one or more machine learning models may predict an email open rate for one or more email campaigns and identify the users having the highest probability of generating a true open event. The data deobfuscation layer may be used to improve the performance of email communication networks and/or increase engagement metrics for media campaigns.

For at least a selected class attribute of the multiple class attributes, one or more bias metrics are determined that estimate a degree to which a particular workflow (having a set of processing stages) is biased in association with the class attribute. Each user of a set of users is associated with a set of user data to be processed by the particular workflow. At least one of the set of processing stages includes executing a machine-learning model. It can be detected that a bias-mitigation option corresponding to a specific class attribute has been selected. For each of at least two of the set of processing stages: a de-biasing technique is selected; and the processing stage is modified by applying the de-biasing technique. A modified version of the particular workflow (which includes the modified processing stages) is applied to each of a set of input data sets.

Integrated methods and systems are provided for offering and managing targeted advertising content and campaigns. More particularly, an exchange platform and method of its use are provided for offering and managing the identification and purchase of advertising space or inventory by advertisers that is available on virtual or physical media which has already been purchased, designed and used by distributors. The exchange platform includes a supply side for capturing, receiving, and managing supply side information which is then reorganized, analyzed, and collated to facilitate research and analysis by advertisers to determine whether suitable advertising inventory is available for the advertiser's advertising content, as well as which distributors and their media are likely to reach or contact desired or preferred market segments and consumer populations for targeted advertising campaigns. Tracking and monitoring the reach and successful consumer engagement by media and advertising content thereon are also enabled by the exchange platform.

A computer-implemented method for enhancing and utilizing user data derived from digital interactions includes receiving user submission data comprising records generated by input into a client side application interface by a first user on a first computing device and transmitted from the first computing device to the aggregation point via at least one of a data transmission service and a data transmission provider. The method includes generating a first dataset associated with the first user, generating a data model based on data in the first dataset and one or more correlations based on attributes in the first dataset, and generating a modeled dataset based on the data model.