Premium
A method of finding business risk factors using the characteristics of probability distributions of effect ratios on qualitative and quantitative hybrid simulation
Author(s) -
Samejima Masaki,
Negoro Keisuke,
Mitsukuni Koshichrio,
Akiyoshi Masanori
Publication year - 2012
Publication title -
electronics and communications in japan
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.131
H-Index - 13
eISSN - 1942-9541
pISSN - 1942-9533
DOI - 10.1002/ecj.10369
Subject(s) - probability distribution , computer science , recall rate , econometrics , recall , series (stratigraphy) , statistics , data mining , algorithm , mathematics , artificial intelligence , psychology , paleontology , cognitive psychology , biology
We propose a method of finding business risk factors in a qualitative and quantitative hybrid time‐series simulation. The effect ratios of qualitative arcs in the hybrid simulation vary the output values of the simulation, so we define the effect ratios causing risks as business risk factors. Finding business risk factors in the entire ranges of effect ratios is time‐consuming. It is considered that the probability distributions of effect ratios at the present time step and those at the previous time step are similar, and thus that the probability distributions at the present time step can be estimated. Our method finds business risk factors effectively in only the estimated ranges. Experimental results show that the precision and recall rate are 86%, and that search time is decreased by at least 20%. © 2012 Wiley Periodicals, Inc. Electron Comm Jpn, 95(3): 55–65, 2012; Published online in Wiley Online Library ( wileyonlinelibrary.com ). DOI 10.1002/ecj.10369