D. Ezra Sidran

Tiger:: an Unsupervised Machine Learning Tactical Inference Generator D. Ezra Sidran

TIGER is a Tactical Inference Generator computer program designed to test the following hypotheses: Hypothesis 1: There is agreement among military experts that tactical situations exhibit certain features and that these features can be used to group tactical situations by similarity. Hypothesis 2: The best match by TIGER of a new scenario to a scenario from its historical database predicts what the experts would choose. We have conducted three surveys of SMEs and have concluded that there is a statistically significant confirmation of Hypothesis 1. The statistical confidence level for this confirmation of Hypothesis 1 is greater than twice the prior probability. In order to test Hypothesis 2 we constructed a series of algorithms for the analysis of SME identified tactical features including: interior lines, restricted avenues of approach, restricted avenues of attack, slope of attack, weighted force relationships and anchored or unanchored flanks. Lastly, we present TIGER?s classification of 20 historical tactical situations and 5 hypothetical tactical situations and the SME survey that resulted in TIGER correctly predicting what the SMEs would choose in 4 out of 5 tests.