Using entropy for quantitative measurement of operational complexity of supplier-customer system: case studies

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23510%2F16%3A43925028" target="_blank" >RIV/49777513:23510/16:43925028 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/s10100-015-0386-7" target="_blank" >http://dx.doi.org/10.1007/s10100-015-0386-7</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10100-015-0386-7" target="_blank" >10.1007/s10100-015-0386-7</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Using entropy for quantitative measurement of operational complexity of supplier-customer system: case studies

Popis výsledku v původním jazyce

The paper concerns with analysis of operational complexity of company supplier-customer relations. Well-known approach for measuring of operational complexity is based upon entropy. However, there are several approaches thereon. In the first part, we discuss various general measures of uncertainty of states, the power entropies in particular. In the second part, we use Shannon entropy as a base framework for our two case studies - the first, a supplier-customer system which implements managerial thresholds for processing product delivery term deviations, the second, a supplier system of the most important commodity in brewery industry, the malted barley. In both cases, we assume an existence of problem-oriented databases, which contain detailed records of all product orders, deliveries and forecasts in quantity and time having been scheduled and realized. Our general procedure elaborated consists of three basic steps - pre-processing of data with consistency checks in Java, calculation of histograms and empirical distribution functions, and finally, evaluation of conditional entropy. The last two steps are realized by Mathematica modules. Illustrative results of operational complexity measurement using entropy are provided for both case studies.

Název v anglickém jazyce

Using entropy for quantitative measurement of operational complexity of supplier-customer system: case studies

Popis výsledku anglicky

The paper concerns with analysis of operational complexity of company supplier-customer relations. Well-known approach for measuring of operational complexity is based upon entropy. However, there are several approaches thereon. In the first part, we discuss various general measures of uncertainty of states, the power entropies in particular. In the second part, we use Shannon entropy as a base framework for our two case studies - the first, a supplier-customer system which implements managerial thresholds for processing product delivery term deviations, the second, a supplier system of the most important commodity in brewery industry, the malted barley. In both cases, we assume an existence of problem-oriented databases, which contain detailed records of all product orders, deliveries and forecasts in quantity and time having been scheduled and realized. Our general procedure elaborated consists of three basic steps - pre-processing of data with consistency checks in Java, calculation of histograms and empirical distribution functions, and finally, evaluation of conditional entropy. The last two steps are realized by Mathematica modules. Illustrative results of operational complexity measurement using entropy are provided for both case studies.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

BB - Aplikovaná statistika, operační výzkum

OECD FORD obor

—

Projekt

<a href="/cs/project/GA15-20405S" target="_blank" >GA15-20405S: Modelování procesů na finančních trzích a predikce bankrotu firem aparátem reálných opcí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Central European Journal of Operations Research

ISSN

1435-246X

e-ISSN

—

Svazek periodika

24

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

17

Strana od-do

371-387

Kód UT WoS článku

000374450100008

EID výsledku v databázi Scopus

2-s2.0-84924691928