Reinforced machine learning methods for testing quality of cyber threat prediction results

A.B. Kachynskyi, N.A. Tsebrinska
2020 Theoretical and Applied Cybersecurity  
The article considered on machine learning methods with reinforcement to make decisions about evaluating the quality of a mathematical prediction model. Given the problems of cybersecurity specificity A/B testing algorithms, analysis of variance (ANOVA), as well as multi-armed bandit are presented. Features of their practical implementation are taken into account: data type and distribution function, sample size, knowledge about the dispersion of the general population, dependence and
more » ... ce of observations. The cybersecurity problems solved with the help of these algorithms are discussed and the methods of their solution are suggested.
doi:10.20535/tacs.2664-29132020.1.209432 fatcat:ilszzrxlmneyha6u3346h5keii