AI Bibliography |
![]() |
Gadepally, V. N., Hancock, B. J., Greenfield, K. B., Campbell, J. P., Campbell, W. M., & Reuther, A. I. (2016). Recommender systems for the department of defense and intelligence community. Lincoln Laboratory Journal, 22(1), 74–89. |
Resource type: Journal Article BibTeX citation key: Gadepally2016 View all bibliographic details |
Categories: Artificial Intelligence, Cognitive Science, Complexity Science, Computer Science, Data Sciences, Decision Theory, General, Mathematics, Military Science Subcategories: Analytics, Behavioral analytics, Big data, Cyber, Decision making, Deep learning, Forecasting, Informatics, Machine learning, Machine recognition, Military research, Simulations Creators: Campbell, Campbell, Gadepally, Greenfield, Hancock, Reuther Publisher: Collection: Lincoln Laboratory Journal |
Attachments |
Abstract |
In the past five years, the machine learning and artificial intelligence commu- nities have done significant work in using algorithms to identify patterns within data. These patterns have then been applied to various problems, such as predicting individuals’ future responses to actions and performing pattern-of-life analysis on persons of interest. Some of these algorithms have widespread application to Department of Defense (DoD) and intelligence community (IC) missions. One machine learning and artificial intelligence technique that has shown great promise to DoD and IC missions is the recommender system, summarized by Resnick and Varian, and its extensions described by Adomavicius and Tuzhilin. A recommender system is one that uses active informa- tion-filtering techniques to exploit past user behavior to suggest information tailored to an end user’s goals. In a recent working paper, the Office of the Director of National Intelligence’s Technical Experts Group’s Return on Investments team has identified recommender systems as a key “developing application” in their process map of “The Intelligence Cycle and Human Language Technology.” |