Microsoft Technology Licensing, LLC

Lingjie Weng

Rupesh Gupta

Shaunak Chatterjee

Jeffrey Gee

Deepak Kumar

Gungor Polatkan

Rohan Ramanath

Shipeng Yu

Yao Chen

Romer E Rosales-Delmoral

Yiping Yuan

Konstantin Salomatin

Smriti R Ramakrishnan

Sara Smoot Gerrard

Onkar Anant Dalal

Jiaqi Ge

Arvind Murali Mohan

Dipen Thakkar

Hongbo Zhao

Shifu Wang

Xiaoxi Zhao

Daniel D Thorndyke

Lu Chen

Jim Chang

In an example embodiment, machine learning is utilized to make recommendations for next actions by users of an online network. These next actions are called 'next best actions.' The machine learning may be performed to train a multitask deep machine learning model to make recommendations based on a series of inputs, including, for example, contextual information that relies upon action sequences of the user and historical users, and user intent. The use of a multitask deep machine learning model allows for the model to generate action recommendations that are personalized, contextual, and coordinate across various different aspects of the online network, rather than being limited to only a single aspect. Likewise, the multi-task deep machine learning model can also be tailored to optimized different use-case specific objectives while at the same time being easy to scale and maintain.

Machine learning for predicting next best action

In some embodiments, a computer system generates a recommendation for a user of an online service based on user actions that have been performed by the user within a threshold amount of time before the generation of the recommendation. For each user action, the computer system determines an intent classification that identifies an activity of the user and that corresponds to different types of user actions, as well as a preference classification that identifies a target of the activity, and then stores these intent and preference classifications as part of indications of the user actions for use in generating different types of recommendations using different types of recommendation models. Additionally, the computer system may use mini-batches of data from an incoming stream of logged data to train an incremental update to one or more recommendation models.

Recommendations using session relevance and incremental learning

A method can include determining a first probability that a first member of members of a website will visit the website within a specified time window if the first member is provided an intervention at a specified time, determining a second probability that the first member will visit the website within the specified time window without being provided the intervention, determining a difference between the first and second probability, and in response to determining the difference is greater than a first specified threshold, providing the intervention at the specified time.

Predicting site visit based on intervention

Growing community of inventors

Sunnyvale, CA, United States of America

Lingjie Weng