Adobe, Inc.

Nikolaos Vlassis

Georgios Theocharous

Branislav Kveton

Hung Hai Bui

Jaya Kawale

Suvash Sedhain

Trevor Paulsen

David Arbour

Craig Mathis

Ivan Andrus

Kristopher Paries

Michael Rimer

Mandana Hamidi Haines

Ehsan Amid

Shreyas Chaudhari

The present disclosure relates to systems, non-transitory computer-readable media, and methods for performing off-policy evaluations of slate recommendation policies through additive decomposition. In particular, in one or more embodiments, the disclosed systems receive historical data corresponding to digital slate recommendations performed by a first slate recommendation policy, with each slate recommendation comprising a plurality of digital slot recommendations. Additionally, in some embodiments, the disclosed systems generate a second slate action using a second slate recommendation policy conditioned on user context. Further, in some embodiments, the disclosed systems generate a plurality of importance weights by summing a plurality of slot-level density ratios generated by comparing the slate actions of the second slate recommendation policy to the slate actions of the first slate recommendation policy. In some embodiments, the disclosed systems apply the plurality of importance weights to generate a predicted reward distribution for evaluation of the second slate recommendation policy.

Utilizing additive decomposition for universal off-policy evaluation of digital content slate recommendations

Techniques disclosed herein provide more efficient and more relevant item recommendations to users in large-scale environments in which only positive interest information is known. The techniques use a rank-constrained formulation that generalizes relationships based on known user interests in items and/or use a randomized singular value decomposition (SVD) approximation technique to solve the formulation to identify items of interest to users in an efficiently, scalable manner.

Item recommendation techniques

Systems and methods are disclosed herein for providing a user interface representing differences between segments of end users. The systems and methods receive user input on a user interface identifying a first segment, the first segment being a subset of the end users having a particular characteristic, determine differences between the first segment and a second segment, and represent, on the user interface, the differences between the first segment and the second segment based on relative significances of the differences. The marketer using the user interface is able to quickly and easily identify the metrics, dimensions, and/or relationships to other segments that most distinguish the compared segments from one another.

Audience comparison

Certain embodiments involve generating personalized recommendations for users by inferring a propensity of each individual user to accept a recommendation. For example, a system generates a personalized user model based on a historical transition matrix that provides state transition probabilities from a general population of users. The probabilities are adjusted based on the propensity for a user to accept a recommendation. The system determines a recommended action for the user to transition between predefined states based on the user model. Once the user has performed an activity that transitions from a current state, the system adjusts a probability distribution for an estimate of the propensity based on whether the activity is the recommended action.

Techniques for providing sequential recommendations to users

Certain embodiments involve learning user preferences and predicting user behavior based on sequential user behavior data. For example, a system obtains data about a sequence of prior actions taken by multiple users. The system determines a similarity between a prior action taken by the various users and groups the various users into groups or clusters based at least in part on the similarity. The system trains a machine-learning algorithm such that the machine-learning algorithm can be used to predict a subsequent action of a user among the various users based on the various clusters. The system further obtains data about a current action of a new user and determines which of the clusters to associate with the new user based on the new user's current action. The system determines an action to be recommended to the new user based on the cluster associated with the new user. The action can include a series or sequence of actions to be taken by the new user. The system further provides the series or sequence of actions or an action of the series or sequence to the new user.

Learning user preferences using sequential user behavior data to predict user behavior and provide recommendations

The present disclosure relates to a triplet embedding system that improves dimensionality reduction through exponential triplet embedding. In particular, the triplet embedding system employs heavy-tailed properties of t-exponential distributions and robust non-convex loss functions to improve visualizations in the presence of noisy data. In addition, the triplet embedding system uses triplet similarity weighting and improved sampling to improve and accelerate triplet embedding in large datasets. Overall, the triplet embedding system produces improved dimensionality reduction visualizations, which accurately reveal the underlying structure of the real-world high-dimensional datasets in lower-dimensional space.

Growing community of inventors

San Jose, CA, United States of America

Nikolaos Vlassis