The Efficacy of Machine Learning Programs for Navy Manpower Analysis
Abstract
This thesis investigated the efficacy of two machine learning programs for Navy manpower analysis. Two machine learning programs, AIM and IXL, were compared to conventional statistical techniques. A large manpower data set and a logistic regression equation were obtained. The same data set was used to generate models from the two commercial machine learning programs. Using a held out sub-set of the data the capabilities of the three models were evaluated. AIM generated results comparable to those of the logistic regression equation; both in number of correct predictions and computed partial effects of the independent variables. IXL had significantly fewer correct predictions than the other two models and does not support evaluation of partial effects. The author recommended further investigation of AIM's capabilities, and testing in an operational environment.... Machine learning, AIM, IXL.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1993
- Accession Number
- ADA267162
Entities
People
- Daniel E. Pytel Jr
Organizations
- Naval Postgraduate School