Back to results
US 11,238,391 B2Granted
Prediction of business outcomes by analyzing resumes of users
AssigneeDotin Inc.
InventorsGanesh Iyer, Roman Samarev
Life of this patent
Estimating the term…
Abstract
Predicting business outcomes for a target user includes generation of predictor models based on test data of tests users. The test data includes historical data of the test users, resumes of the test users, and answers provided by the test users to psychometric questions. The predictor models are then used to predict psychometric features and business outcomes based on target data of the target user. The target data includes a resume of the target user, historical data of the target user, and answers provided by the target user to the psychometric questions.
Claims20
A method comprising:
- retrieving, by a server, historical data of a plurality of test users, a first set of answers provided by each of the plurality of test users to a set of psychometric questions, and a plurality of test resumes of the plurality of test users, wherein each test resume of the plurality of test resumes includes first text data;
- deriving, by the server, one or more psychometric features of each of the plurality of test users based on the first set of answers provided by each of the plurality of test users;
- extracting, by the server, from each of the plurality of test resumes, a portion of the first text data that corresponds to a set of features, wherein the extracted portion of the first text data includes one or more first phrases and one or more first terms that are indicative of the set of features;
- generating, by the server, a first predictor model and a second predictor model based on the historical data of the plurality of test users, the one or more psychometric features of each of the plurality of test users, and the portion of the first text data extracted from each of the plurality of test resumes;
- receiving, by the server, a target resume of a target user, wherein the target resume includes second text data;
- extracting, by the server, from the target resume, a portion of the second text data that corresponds to the set of features, wherein the extracted portion of the second text data includes one or more second phrases and one or more second terms that are indicative of the set of features;
- predicting, by the server, one or more first psychometric features of the target user by using the extracted portion of the second text data as an input to the first prediction model;
- predicting, by the server, one or more business outcomes for the target user based on the extracted portion of the second text data, the predicted one or more first psychometric features of the target user, and the second predictor model, wherein the one or more business outcomes include at least an employment affinity of the target user;
- receiving, by the server, from a target user device of the target user, a feedback on a relevance of the predicted one or more business outcomes;
- and
- updating, by the server, the first predictor model and the second predictor model based on the received feedback to increase a prediction accuracy of the first predictor model and the second predictor model.
8 more elements
A system comprising:
- a server that is configured to:
- retrieve historical data of a plurality of test users, a first set of answers provided by each of the plurality of test users to a set of psychometric questions, and a plurality of test resumes of the plurality of test users, wherein each test resume of the plurality of test resumes includes first text data;
- derive one or more psychometric features of each of the plurality of test users based on the first set of answers provided by each of the plurality of test users;
- extract, from each of the plurality of test resumes a portion of the first text data that corresponds to a set of features, wherein the extracted portion of the first text data includes one or more first phrases and one or more first terms that are indicative of the set of features;
- generate a first predictor model and a second predictor model based on the historical data of the plurality of test users, the one or more psychometric features of each of the plurality of test users, and the portion of the first text data extracted from each of the plurality of test resumes;
- receive a target resume of a target user, wherein the target resume includes second text data;
- extract a portion of the second text data that corresponds to the set of features from the target resume, wherein the extracted portion of the second text data includes one or more second phrases and one or more second terms that are indicative of the set of features;
- predict one or more first psychometric features of the target user by using the extracted portion of the second text data as an input to the first prediction model;
- predict one or more business outcomes for the target user based on the extracted portion of the second text data, the predicted one or more first psychometric features of the target user, and the second predictor model, wherein the one or more business outcomes include at least an employment affinity of the target user;
- receive a feedback from a target user device of the target user on a relevance of the predicted one or more business outcomes;
- and
- update the first predictor model and the second predictor model based on the received feedback to increase a prediction accuracy of the first predictor model and the second predictor model.
9 more elements
A non-transitory computer readable medium having stored thereon, computer executable instructions, which when executed by a computer, cause the computer to execute operations, the operations comprising:
- retrieving historical data of a plurality of test users, a first set of answers provided by each of the plurality of test users to a set of psychometric questions, and a plurality of test resumes of the plurality of test users, wherein each test resume of the plurality of test resumes includes first text data;
- deriving one or more psychometric features of each of the plurality of test users based on the first set of answers provided by each of the plurality of test users;
- extracting, from each of the plurality of test resumes a portion of the first text data that corresponds to a set of features, wherein the extracted portion of the first text data includes one or more first phrases and one or more first terms that are indicative of the set of features;
- generating a first predictor model and a second predictor model based on the historical data of the plurality of test users, the one or more psychometric features of each of the plurality of test users, and the portion of the first text data-extracted from each of the plurality of test resumes;
- receiving a target resume of a target user, wherein the target resume includes second text data;
- extracting a portion of the second text data corresponding to the set of features from the target resume, wherein the extracted portion of the second text data includes one or more second phrases and one or more second terms that are indicative of the set of features;
- predicting one or more first psychometric features of the target user by using the extracted portion of the second text data as input to the first prediction model;
- predicting one or more business outcomes for the target user based on the extracted portion of the second text data, the predicted one or more first psychometric features of the target user, and the second predictor model, wherein the one or more business outcomes include at least an employment affinity of the target user;
- receiving a feedback from a target user device of the target user on a relevance of the predicted one or more business outcomes;
- and
- updating, the first predictor model and the second predictor model based on the received feedback to increase a prediction accuracy of the first predictor model and the second predictor model.
8 more elements
Dependencies are inferred from the claim text.