Oracle International Corporation

Simon Chow

Sonali Vijay Inamdar

Suman Gupta

Mahesh Siddirampura

Rajiv Kumar

Trevor Mathers

Carlos E Hernández Rincón

Abhishek Verma

Carlos E Hernández-Rincón

Carolina Elizabeth Elias Arenas

Michael Richard Palmeter

Satheesh Kumar Reddy Challaveera

Systems and methods for candidate recommendation are provided. Candidate vectors are generated from candidate documents, and an initial ranking is performed according to a distance metric between the candidate vector and an objective vector generated based on an objective document to select a subset of the candidate documents. A feature vector is generated for each of the selected candidate documents. The feature vector includes features derived from a first vectorized representation of content from one of the candidate document and the objective document and a second vectorized representation of content from the one of the candidate document and the objective document. The feature vector is provided to a machine learning model to generate a score for each of the selected candidate documents. The selected candidate documents are ranked according the scores generated at the machine learning model to provide a ranked candidate list.

Method and system for multistage candidate ranking

Techniques are disclosed for organizing and distributing artifacts generated by processing pipelines for the training or application of machine learning models. An application may subscribe to a playlist of a stream of events and locally store a copy of the playlist. The subscriber may merge locally stored and/or selected events to generate a merged stream of events. The subscriber may then execute the merged event stream including the newly added instance of the event.

Modifying event playlists

Techniques for determining a Next Best Action (NBA) are disclosed, with the determination being based on a position within an application, past actions by a user when experiencing a similar application context, and/or tasks in queue for the user to execute from current state of the application. Techniques are also disclosed for displaying an interface that includes the NBA in conjunction with a specific rationale for presenting the NBA, such as recommendations by a trusted person, based on the user's and/or other users' past behavior, and descriptions developed based on the specific NBA. Also, methods for determining a best NBA are disclosed, with the NBA being selected by applying static rules to a data set, heuristically analyzing the data set, and/or applying a machine learning model to the data set.

Generating a next best action recommendation using a machine learning process

In some examples a first parameter for respective applicants or candidates can be computed based on respective text data from a text dataset that can include a plurality of different types of text data. The first parameter can be populated with a given portion of text of the respective text data. A second parameter for a job requisition can be computed based on the respective text data used to compute the first parameter for a given applicant or candidate. The second parameter can be populated with a different portion of text of the respective text data used to compute the first parameter. Synthetic test data can be generated based on the computed parameters to test a machine learning (ML) ranking model that has been trained on training data that is from a different data source than the text dataset to validate a performance of the ML ranking model.

System and method for validating a candidate recommendation model

A system and method are presented for cold start candidate recommendation. In some examples, a search query request that includes a candidate search parameter can be received for a candidate list. During a first search query, a subset of candidates from a plurality of candidates can be identified based on a comparison of each candidate vector for each candidate and a candidate search parameter vector for the candidate search parameter, and ranked to provide an initial ranked candidate list based on assigned scores for the subset of candidates. During a second search query, the search parameter a candidate index can be evaluated to identify a set of candidates from the plurality of candidates, re-ranked to provide an updated ranked candidate list corresponding to the candidate list based on updated assigned scores for the set candidates and a re-ranking parameter.

Growing community of inventors

San Francisco, CA, United States of America

Simon Chow