Microsoft Technology Licensing, LLC

Ada Cheuk Ying Yu

Dhruv Arya

Saurabh Kataria

Girish Kathalagiri Somashekariah

Huichao Xue

Ye Yuan

Swanand Wakankar

Lin Guo

Junrui Xu

Meng Meng

Varun Mithal

Gheorghe Muresan

Chunzhe Zhang

Linda Fayad

Satej Milind Wagle

In an example embodiment, a specialized machine learned model, called a look-alike model, is trained using a machine learning algorithm to predict future job engagement for a user. This look-alike model is then used to create new segments on top of the segments provided by a rules-based approach. Specifically, the look-alike model is designed to take users who have been segmented by a rule-based approach into an 'inactive job seeker' categorization (such as those assigned to the resting users and dormant users segments) and calculate a predicted job engagement score for these users. Based on the predicted job engagement score, a user may then be reassigned from one of the inactive job seeker categorizations to one of one or more new job seeker categorizations (such as predicted open job seekers or predicted opportunistic job seekers).

Integrated explicit intent and inference based job seeker identification and segmentation

The disclosed embodiments provide a system for processing data. During operation, the system obtains labels for entities found in portions of text in a first set of jobs. Next, the system inputs the portions of text and the labels as training data for a machine learning model. The system then applies the machine learning model to a second set of jobs to generate predictions of additional entities in additional portions of text in the second set of jobs. Finally, the system creates, based on the predictions, an index containing mappings of the additional entities to subsets of the second set of jobs in which the additional entities are found.

Semantic matching of search terms to results

The disclosed embodiments provide a system for performing activity-based inference of title preferences. During operation, the system determines features and labels related to first title preferences for jobs sought by a first set of candidates. Next, the system inputs the features and the labels as training data for a machine learning model. The system then applies the machine learning model to additional features for a second set of candidates to produce predictions of second title preferences for the second set of candidates. Finally, the system stores the predictions in association with the second set of candidates.

Activity-based inference of title preferences

In some embodiments, a computer system selects a first subset of candidate content items based on their filter scores that are generated based on a partial generalized linear mixed model comprising a baseline model and a user-based model, with the baseline model being a generalized linear model, and the user-based model being a random effects model based on user actions by the target user directed towards reference content items related to the candidate content items. In some embodiments, the computer system then selects a second subset from the first subset based on recommendation scores that are generated based on a full generalized linear mixed model comprising the baseline model, the user-based model, and an item-based model, with the item-based model being a random effects model based on user actions directed towards the candidate online content item by reference users related to the target user.

Filtering content using generalized linear mixed models

Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system executes a search query based on a search term and the geographic indicator. In response to determining that a number of the search results is less than a threshold number, the search system determines, based on historical search logs from other users in the first geographic region, a likelihood value indicating a likelihood that the other users in the first geographic region expanded the geographic region of their search queries. The search system compares the likelihood value to a threshold likelihood value, and determines, based on the comparison, that the likelihood value meets or exceeds the threshold likelihood value. The search system then executes an expanded search based on the search term and an expanded geographic indicator that encompasses the first geographic region.

Expanding search queries

Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system determines a set of candidate alternate search terms based on historical search logs that include records of previously submitted search terms, corresponding search results that were presented to users, and corresponding search results that were selected by the users. The set of candidate alternate search terms is selected from titles of the corresponding search results that were selected by the users. The search system ranks the set of candidate alternate search terms based on determined probabilities that each of the alternate candidate search terms will be selected if presented to a user, and selects a first candidate alternate search term from the set of candidate alternate search terms based on the ranking. The search system generates an expanded search term based on the first candidate alternate search term.

Growing community of inventors

Santa Clara, CA, United States of America

Ada Cheuk Ying Yu