Adaptive Feature Oriented Recommender Engine, Phase II

Principal Investigator: William Rand

Sponsor: Defense Advanced Research Projects Agency

Award Period: 8/24/2018 - 8/24/2020

Amount: $80,000

Description: Working through a subaward from Perceptronics Solutions, Inc. the NC State team is supporting this DARPA funded project in the following areas: 1 - exploring and evaluating alternative features for causal state modeling such as different time resolutions, transducer models, and alternate input encoding. 2. extending previous work for using causal state modeling to inform classification of users into known groups. 3. exploring using causal state modeling techniques to detect changes / anomalies in trend data. 4. exploring combining individual-level and content-level recommendations together to improve the performance of each other. and 5. assisting and advising in the development of methods to predict which users will be influential in the future, based on dynamics observed in the past.