Classifier Monitoring using Statistical Tests

Rafal Latkowski(1,2) and Cezary Glowinski(1)

(1) SAS Institute
    ul. Gdanska 27/31, 01-633 Warszawa, Poland
    Cezary.Glowinski@spl.sas.com

(2) Warsaw University
    Institute of Computer Science,
    ul. Banacha 2, 02-097 Warszawa, Poland,
    R.Latkowski@mimuw.edu.pl


Abstract

This paper is addressed to methods for early detection of
classifier fall-down phenomenon, what gives a possibility to react
in advance and avoid making incorrect decisions. For many
applications it is very essentials that decisions made by machine
learning algorithms were as accurate as it is possible. The
proposed approach consists in applying a monitoring mechanism only
for result of classification, what not cause an additional
computational overhead. The empirical evaluation of monitoring
method is presented based on data extracted from simulated robotic
soccer as an example of autonomous agent domain and synthetic data
that stand for standard industrial application.