Adobe, Inc.

Oath Inc.

Zheng Wen

Branislav Kveton

Yasin Abbasi Yadkori

Vishwa Vinay

Yale Song

Iftikhar Ahamath Burhanuddin

Mohammad Ghavamzadeh

Haojian Jin

Shuai Li

Claire Vernade

Sungchul Kim

Georgios Theocharous

Handong Zhao

Gaurush Hiranandani

Harvineet Singh

Prakhar Gupta

Abhilasha Sancheti

Sheng Li

Yang Cao

Qingyun Wu

Systems and techniques for multi-task equidistant embedding are described that process categorical feature data to explore feature interactions. A digital analytics system enforces an equidistant relationship among features within a category while extracting high-order feature interactions by punishing both positive correlations and negative correlations among low-dimensional representations of different features. By enforcing an equidistant embedding, information is retained and accuracy is increased while higher order feature interactions are determined. Further, the digital analytics system shares knowledge among different tasks by connecting a shared network representation common to multiple tasks with exclusive network representations specific to particular tasks.

Multi-task equidistant embedding

A method for recommending digital content includes: determining user preferences and a time horizon of a given user; determining a group for the given user based on the determined user preferences; determining a number of users of the determined group and a similarity of the users; applying information including the number of users, the similarity, and the time horizon to a model selection classifier to select one of a personalized model of the user and a group model of the determined group; and running the selected model to determine digital content to recommend.

Method and system for recommending digital content

Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing offline models to warm start online bandit learner models. For example, the disclosed system can determine relevant offline models for an environment based on reward estimate differences between the offline models and the online model. The disclosed system can then utilize the relevant offline models (if any) to select an arm for the environment. The disclosed system can update the online model based on observed rewards for the selected arm. Additionally, the disclosed system can also use entropy reduction of arms to determine the utility of the arms in differentiating relevant and irrelevant offline models. For example, the disclosed system can select an arm based on a combination of the entropy reduction of the arm and the reward estimate for the arm and use the observed reward to update an observation history.

Utilizing relevant offline models to warm start an online bandit learner model

The present disclosure is directed toward systems, methods, and computer readable media for training and utilizing an item-level importance sampling model to evaluate and execute digital content selection policies. For example, systems described herein include training and utilizing an item-level importance sampling model that accurately and efficiently predicts a performance value that indicates a probability that a target user will interact with ranked lists of digital content items provided in accordance with a target digital content selection policy. Specifically, systems described herein can perform an offline evaluation of a target policy in light of historical user interactions corresponding to a training digital content selection policy to determine item-level importance weights that account for differences in digital content item distributions between the training policy and the target policy. In addition, the systems described herein can apply the item-level importance weights to training data to train item-level importance sampling model.

Method, medium, and system for utilizing item-level importance sampling models for digital content selection policies

Methods, systems, and non-transitory computer readable storage media are disclosed for determining parameters for digital campaign content in connection with executing digital campaigns using a rank-one assumption and a best-arm identification algorithm. For example, the disclosed system alternately explores response data in the first dimension and response data in the second dimension using the rank-one assumption and the best-arm identification algorithm to estimate highest sampling values from each dimension. In one or more embodiments, the disclosed system uses the estimated highest sampling values from the first and second dimension to determine a combination with a highest sampling value in a parameter matrix constructed based on the first dimension and the second dimension, and then executes the digital campaign using the determined combination.

Multivariate digital campaign content exploration utilizing rank-1 best-arm identification

Multivariate digital campaign content testing utilizing rank-1 best-arm identification

A machine-learning framework uses partial-click feedback to generate an optimal diverse set of items. An example method includes estimating a preference vector for a user based on diverse cascade statistics for the user, the diverse cascade statistics including previously observed responses and previously observed topic gains. The method also includes generating an ordered set of items from the item repository, the items in the ordered set having highest topic gain weighted by similarity with the preference vector, providing the ordered set for presentation to the user, and receiving feedback from the user on the ordered set. The method also includes, responsive to the feedback indicating a selected item, updating the diverse cascade statistics for observed items, wherein the updating results in penalizing the topic gain for items of the observed items that are not the selected item and promoting the topic gain for the selected item.

Online diverse set generation from partial-click feedback

Recommendation systems and techniques are described that employ change point detection to generate recommendations for digital content. In one example, a change point detection technique is employed by a recommendation system to identify when a change point has occurred at a respective time step of a series of time steps. Detection of this change point may then be used by the recommendation system to reset the statistical model to address this change as well as generate a subsequent recommendation configured for exploration of reward distributions of the items of digital marketing content.

Change point detection in a multi-armed bandit recommendation system

Method, medium, and system for training and utilizing item-level importance sampling models

Disclosed herein is a content-adaptive digital media content adjustment system, method and architecture. Playback rate of a media content item comprising audio and video content can be increased by removing a portion of the content item's audio content and a corresponding portion of the content item's video content. An increased playback rate of a multimedia content item is accomplished by decreasing the length of the multimedia content item by removing portions of the multimedia content item's audio and video content.

Content-adaptive digital content adjustment method and system

Growing community of inventors

Fremont, CA, United States of America

Zheng Wen