Pearson Education, Inc.

Twilio Inc.

Srirama Kolla

Victoria Kortan

Daniel L Ensign

Sumona J Routh

Clayton Tong

Mark E Liedtke

Scott Reynolds

Sriram Ramarathnam

Ravindra Ishmitra Bhanot

Minakshi Chandrashekhar Korad

Thomas William D'Silva

A method is disclosed for reducing inaccuracies in counts related to communication of messages in a manner that efficiently uses computer resources, including processing power and/or memory. An alert condition pertaining to delivery of a plurality of messages is received. The alert condition specifies a threshold number of dropped or failed deliveries. Based on a first time period elapsing, a first system check is performed. Based on a second time period elapsing, a second system check is performed. The second system check includes, based on a detection that the first message has failed during the second time period, decrementing the count for the dropped queue associated with the plurality of messages and incrementing a count for a failed queue associated with the plurality of messages, and, based on a detection that a second message has been dropped during the second time period, incrementing the count for the dropped queue.

Real-time alerting

Systems and methods are provided by which a machine learning model may be executed to determine the probability that a given user will respond correctly to a given assessment item of a digital assessment on their first attempt. The machine learning model may process feature data corresponding to the user and the assessment item in order to determine the probability. The feature data may be calculated periodically and/or in real time or near-real time according to a machine learning model definition based on assessment data corresponding to the user's activity and/or based on responses submitted by all users to the assessment item and/or to content related to the assessment item.

Systems and methods for predictive modelling of digital assessment performance

Systems and methods are provided by which an adaptive learning engine may be executed to determine the probability that a given user will respond correctly to a given assessment item of a digital assessment on their first attempt. The adaptive learning engine may apply one or more machine learning models to feature data corresponding to the user and the assessment item in order to determine the probability. The feature data may be calculated periodically and/or in real time or near-real time according to a machine learning model definition based on assessment data corresponding to the user's activity and/or based on responses submitted globally by users to the assessment item and/or to content related to the assessment item. Based on the correct first attempt probability, the adaptive learning engine may identify and recommend assessment items for which a user should be preemptively assigned credit.

Systems and methods for assessment item credit assignment based on predictive modelling

Growing community of inventors

Highlands Ranch, CO, United States of America

Srirama Kolla