PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD

Lukić, Radojko

SKEI–MEĐUNARODNI INTERDISCIPLINARNI ČASOPIS, Vol. 4 No. 1, 2023.

Review article

PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD

Radojko Lukić orcid.org/0000-0001-6529-0297 ; Faculty of Economics, University of Belgrade *

* Corresponding author.

Full text: english pdf 385 Kb

page 85-102

downloads: 151

cite

APA 6th Edition

Lukić, R. (2023). PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD. SKEI–MEĐUNARODNI INTERDISCIPLINARNI ČASOPIS, 4 (1), 85-102. Retrieved from https://hrcak.srce.hr/307841

MLA 8th Edition

Lukić, Radojko. "PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD." SKEI–MEĐUNARODNI INTERDISCIPLINARNI ČASOPIS, vol. 4, no. 1, 2023, pp. 85-102. https://hrcak.srce.hr/307841. Accessed 20 Nov. 2024.

Chicago 17th Edition

Lukić, Radojko. "PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD." SKEI–MEĐUNARODNI INTERDISCIPLINARNI ČASOPIS 4, no. 1 (2023): 85-102. https://hrcak.srce.hr/307841

Harvard

Lukić, R. (2023). 'PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD', SKEI–MEĐUNARODNI INTERDISCIPLINARNI ČASOPIS, 4(1), pp. 85-102. Available at: https://hrcak.srce.hr/307841 (Accessed 20 November 2024)

Vancouver

Lukić R. PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD. SKEI–MEĐUNARODNI INTERDISCIPLINARNI ČASOPIS [Internet]. 2023 [cited 2024 November 20];4(1):85-102. Available from: https://hrcak.srce.hr/307841

IEEE

R. Lukić, "PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD", SKEI–MEĐUNARODNI INTERDISCIPLINARNI ČASOPIS, vol.4, no. 1, pp. 85-102, 2023. [Online]. Available: https://hrcak.srce.hr/307841. [Accessed: 20 November 2024]

Download JATS file

Abstract

Recently, the importance of applying multi-criteria decision-making methods in the economy has been increasing. With their help, more realistic results are achieved in the function of improvement in the future by applying relevant measures. Based on that, this paper analyzes the performance of companies in Serbia based on the LMAW-DNMA method. According to the results of the DNMA method, the top five companies in Serbia include: TELEKOM SRBIJA AD BELGRADE, DELTA HOLDING DOO BELGRADE, MK GROUP DOO BELGRADE, JP SRBIJAGAS NOVI SAD and HEMOFARM AD VRŠAC. The best performance was recorded at the company TELEKOM SRBIJA AD, BELGRADE. The company with the worst performance is YURA CORPORATION DOO RAČA. This positioning of companies in Serbia according to performance was influenced by numerous factors. These are: general economic conditions, inflation, interest rate, exchange rate, employment, living standards of the population, the Covid-19 pandemic, and the energy crisis. Likewise, the efficiency of human resource, asset, capital, sales and profit management. The application of new concepts of cost management (for example, calculation of costs by basic activities) and digitization of the entire business play a significant role in this. Effective control of these and other factors can significantly influence the achievement of the target performance of companies in Serbia.

Keywords

performance, companies, Serbia, LMAW-DNMA method

Hrčak ID:

307841

URI

https://hrcak.srce.hr/307841

Publication date:

8.9.2023.

Visits: 596 *

Article information

License (open-access, http://rightsstatements.org/vocab/InC/1.0/):

InCopyright

License (open-access):

“SKEI” – međunarodni interdisciplinarni časopis je u potpunosti otvorenog pristupa, što osigurava da je sav sadržaj slobodno dostupan na web stranici časopisa za osobnu ili obrazovnu upotrebu, bez ikakvih troškova za autore za prijavu ili objavljivanje njihovih radova ili drugih materijala. Autori koji objavljuju svoje radove u časopisu “SKEI” pristaju na uvjete Creative Commons licencu Atribucija-Nekomercijalno-Bez Izvoda (CC BY-NC-ND) Međunarodnu licencu (https://creativecommons.org/licenses/by-nc-nd/4.0/). Ova licenca omogućava drugima da preuzmu, podijele i koriste objavljene radove, uz uvjet da se autorima pravilno daje zasluga. Dodatno, radovi se ne smiju koristiti u komercijalne svrhe i ne smiju se stvarati izvedena djela iz originalnih radova.

License (open-access):

"SKEI" – an international interdisciplinary journal is entirely open access, ensuring that all content is freely available on the journal's website for personal or educational use, without any charges to authors for the submission or publication of their papers or other materials. Authors who publish their works in the "SKEI" journal agree to the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND) International License (https://creativecommons.org/licenses/by-nc-nd/4.0/). This license allows others to download, share, and use the published works, with the requirement that proper credit is given to the authors. Furthermore, the works may not be used for commercial purposes, and no derivative works can be created from the original papers.

Publication date: 08 September 2023

Volume: 4

Pages: 85-102

Article Information (continued)

Categories:

Subject: Pregledni rad

Categories:

Subject: Review article

Keywords:

Keyword: performance, companies, Serbia, LMAW-DNMA method

PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD

Radojko Lukić

Email: radojko.lukic@ekof.bg.ac.rs

Faculty of Economics, University of Belgrade

Abstract

PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD

ANALIZA PERFORMANSI PREDUZEĆA U SRBIJI NA BAZI LMAW-DNMA METODA

Radojko Lukić1

ABSTRACT

Key words: performance, companies, Serbia, LMAW-DNMA method

SAŽETAK

U poslednje vreme sve je veći značaj primene metoda višekriterijumskog odlučivanja u ekonomiji. Pomoću njih se dolazi do realnijih rezultata u funkciji unapređenja u budućnosti primenom relevantnih mera. Polazeći od toga, u ovom radu se analiziraju performanse preduzeća u Srbiji na bazi LMAW-DNMA metoda. Prema rezultatima DNMA metodi u top pet preduzeća u Srbiji spadaju: TELEKOM SRBIJA A.D., BEOGRAD, DELTA HOLDING DOO BEOGRAD, MK GROUP DOO BEOGRAD, JP SRBIJAGAS NOVI SAD i HEMOFARM AD VRŠAC. Njabolje performanse su zabeležene kod preduzeća TELEKOM SRBIJA A.D., BEOGRAD. Sa najlošijim performansama je preduzeće YURA CORPORATION DOO RAČA. Na ovakvo pozicioniranje preduzeća u Srbiji prema performansama uticali su brojni faktori. To su: opšti uslovi privređivanja, inflacija, kamatna stopa, devizni kurs, zaposlenost, životni standard stanovništva, pandemija korona virusa Covid-19, i energetska kriza. Isto tako, i efikasnost upravljanja ljudskim resursima, aktivom, kapitalom, prodajom i profitom. U tome značajnu ulogu ima primena novih koncepata upravljanja troškovima (na primer, obračun troškova po baznim aktivnostima) i digitalizacija celokupnog poslovanja. Efikasnom kontrolom ovih i drugih faktora može se znatno uticati na ostvarenje ciljnih performansi preduzeća u Srbiji.

Key words: performanse, preduzeća, Srbija, LMAW-DNMA metoda

INTRODUCTION

The issue of company performance analysis is very challenging, complex and significant. Various methodologies are used: ratio analysis, statistical analysis, DEA analysis and multi-criteria decision-making methods. When analyzing the efficiency of companies, DEA models are used to a significant extent (Park, & Kim, 2022; Zohreh Moghaddas et al., 2022; Amirteimoori et al., 2022; Alam et al., 2022; Photos Čiković & Lozić, 2022; Sala-Garrido, 2023; Andersen, & Petersen, 1993; Banker et al., 1984; Chen et al., 2021, Chang et al., 2020; Guo, & Cai, 2020; Lee et al., 2011; Lin et al., 2020; Pendharkar et al., 2021; Tone, 2002; Dobrović et al., 2021; Podinovski et al., 2021; Rostamzadeh et al., 2021; Fenyves, & Tarnóczi, 2020; Amini et al., 2019; Tsai et al., 2021; Mandić et al., 2017; Martić, & Savić, 2001; Cooper et al., 1999; Amin, & Hajjami, 2021; Chen et al., 2018, 2020, 2021a,b, Đurić et al., 2020; Lukić 2022a,b,c; Radonjić, 2020; Stević et al., 2022; Stojanović et al., 2022; Rasoulzadeh et al., 2021). This is also the case with the analysis of the efficiency of companies in Serbia (Lukic et al., 2017, 2020; Lukic, 2018, 2021, 2022a,b, 2023; Lukic & Kozarevic, 2019; Lukic & Hadrovic Zekic, 2019; Vojteški Kljenak & Lukić, 2022) . DEA models provide a realistic picture of which companies are efficient and which are not and which measures should be taken in order to increase efficiency. Likewise, in recent times, multi-criteria decision-making methods have been increasingly applied when analyzing the company's performance, for the reason that they lead to more realistic results compared to classical methods (such as ratio analysis) as a basis for improvement in the future by applying relevant measures (Ayçin & Arsu, 2021; Popović et al., 2022; Ecer & Aycin, 2022; Mishra et al., 2022; Nguyen et al., 2022; Rani et al., 2022; Toslak et al., 2022) . Having that in mind, the subject of research in this paper is the analysis of the performance of companies in Serbia based on the LMAW-DNMA method. The aim and purpose of this is to look at the performance of companies in Serbia as realistically as possible in order to improve them in the future by applying relevant measures. The primary research hypothesis in this work is reflected in the fact that knowing the real situation regarding the company's performance is a prerequisite for improvement in the future by applying relevant measures. In addition to ratio analysis, statistical analysis and DEA approach, multi-criteria decision-making methods, including the LMAW-DNMA method, play a significant role in this. Empirical data needed for the research of the treated problem in this paper were collected from the Agency for Economic Registers of the Republic of Serbia. In terms of international comparability, there are no restrictions because they are "manufactured" in accordance with the relevant international standards.

METHODOLOGY

In further presentations, we will point out the theoretical and methodological characteristics of the LMAW and DNMA methods (Demir, 2022).

LMAW method

The LMAW method is the latest method used to calculate criteria weights and rank alternatives (Liao, & Wu, 2020; Demir, 2022). It takes place through the following steps : m alternatives [TeX:] A = \left\{ A_{1},A_{2},\ldots,A_{m} \right\}\text{\ \ \ } $A = {A_{1}, A_{2}, \dots, A_{m}}$ are evaluated in comparison with n criteria [TeX:] C = \left\{ C_{1},C_{2},\ldots,C_{n} \right\}\text{\ \ } $C = {C_{1}, C_{2}, \dots, C_{n}}$ with the participation of k experts [TeX:] E = \left\{ E_{1},E_{2},\ldots,E_{k} \right\} $E = {E_{1}, E_{2}, \dots, E_{k}}$ and according to a predefined linguistic scale (Pamučar et al, 2021) .

Step 1: Determination of weight coefficients of criteria

Experts [TeX:] E = \left\{ E_{1},E_{2},\ldots,E_{k} \right\}\text{\ \ } $E = {E_{1}, E_{2}, \dots, E_{k}}$ set priorities with criteria [TeX:] C = \left\{ C_{1},C_{2},\ldots,C_{n} \right\}\text{\ \ } $C = {C_{1}, C_{2}, \dots, C_{n}}$ in relation to previously defined values of the linguistic scale. At the same time, they assign a higher value to the criterion of greater importance and a lower value to the criterion of less importance on the linguistic scale. By the way, the priority vector is obtained. The label [TeX:] \gamma_{\text{cn}}^{e}\text{\ \ \ } $γ_{cn}^{e}$ represents the value of the linguistic scale that the expert [TeX:] e\left( 1 \leq e \leq k \right)\text{\ \ \ } $e (1 \leq e \leq k)$ assigns to the criterion [TeX:] C_{t}\left( 1 \leq t \leq n \right) $C_{t} (1 \leq t \leq n)$ .

Step 1.1: Defining the absolute anti-ideal point[TeX:] \ \ \gamma_{\text{AIP}} $γ_{AIP}$

The absolute ideal point should be less than the smallest value in the priority vector. It is calculated according to the equation:

[TeX:] \gamma_{\text{AIP}} = \frac{\gamma_{\min}^{e}}{S}

γ_{AIP} = \frac{γ_{min}^{e}}{S}

where is [TeX:] \gamma_{\min}^{e}\text{\ \ \ } $γ_{min}^{e}$ the minimum value of the priority vector and S should be greater than the base logarithmic function. In the case of using the function Ln, the value of S can be chosen as 3.

Step 1.2 : Determining the relationship between the priority vector and the absolute anti-ideal point. The relationship between the priority vector and the absolute anti-ideal point is calculated using the following equation:

[TeX:] n_{\text{Cn}}^{e} = \frac{\gamma_{\text{Cn}}^{e}}{\gamma_{\text{AIP}}}\ \ \ \ \ (1)

n_{Cn}^{e} = \frac{γ_{Cn}^{e}}{γ_{AIP}} (1)

so the relational vector [TeX:] R^{e} = \left( n_{C1}^{e},n_{C2}^{e},\ldots,n_{\text{Cn}}^{e} \right)\text{\ \ \ } $R^{e} = (n_{C 1}^{e}, n_{C 2}^{e}, \dots, n_{Cn}^{e})$ is obtained, where it [TeX:] n_{\text{Cn}}^{e}\text{\ \ \ } $n_{Cn}^{e}$ represents the value of the real vector derived from the previous equation.

Step 1.3: Determination of the vector of weight coefficients

The vector of weight coefficients [TeX:] w = \ \left( w_{1},w_{2},\ldots,w_{n} \right)^{T}\text{\ \ } $w = {(w_{1}, w_{2}, \dots, w_{n})}^{T}$ is calculated by the expert [TeX:] e\left( 1 \leq e \leq k \right)\text{\ \ \ } $e (1 \leq e \leq k)$ using the following equation:

[TeX:] w_{j}^{e} = \ \frac{\log_{A}\left( n_{Cn}^{e} \right)}{\log_{A}\left( \prod_{j = 1}^{n}n_{Cn}^{e} \right)},A > 1\ \ \ \ \ (2)

w_{j}^{e} = \frac{{log}_{A} (n_{C n}^{e})}{{log}_{A} (\prod_{j = 1}^{n} n_{C n}^{e})}, A > 1 (2)

where [TeX:] w_{j}^{e} $w_{j}^{e}$ it represents the weighting coefficients obtained according to expert evaluations [TeX:] e^{\text{th}}\text{\ \ } $e^{th}$ and the [TeX:] n_{\text{Cn}}^{e}\text{\ \ \ } $n_{Cn}^{e}$ elements of the realization vector R. The obtained values for the weighting coefficients must meet the condition that [TeX:] \sum_{j = 1}^{n}{w_{j}^{e} = 1} $\sum_{j = 1}^{n} w_{j}^{e} = 1$ .

By applying the Bonferroni aggregator shown in the following equation, the aggregated vector of weight coefficients is determined [TeX:] w = \ \left( w_{1},w_{2},\ldots,w_{n} \right)^{T}\text{\ \ \ \ } $w = {(w_{1}, w_{2}, \dots, w_{n})}^{T}$ :

[TeX:] W_{j} = \left( \frac{1}{\text{k.}\left( k - 1 \right)}.\sum_{x = 1}^{k}\left( w_{j}^{\left( x \right)} \right)^{p}.\sum_{\begin{matrix} y = 1 \\ y \neq x \\ \end{matrix}}^{k}\left( w_{\text{ij}}^{\left( y \right)} \right)^{q} \right)^{\frac{1}{p + q}}\ \ \ \ \ (3)

W_{j} = {(\frac{1}{k. (k - 1)} . \sum_{x = 1}^{k} {(w_{j}^{(x)})}^{p} . \sum_{\begin{matrix} y = 1 \\ y \neq x \end{matrix}}^{k} {(w_{ij}^{(y)})}^{q})}^{\frac{1}{p + q}} (3)

The value of p and q are stabilization parameters and [TeX:] p,q\ \geq 0 $p, q \geq 0$ . The resulting weight coefficients should fulfill the condition that [TeX:] \sum_{j = 1}^{n}w_{j} = 1 $\sum_{j = 1}^{n} w_{j} = 1$ .

DNMA method

DNMA is a newer method for identifying alternatives (Demir, 2022). Two different normalized (linear and vector) techniques are used, as well as three different coupling functions (full compensation - CCM, non-compensation - UCM and incomplete compensation - ICM). The steps of applying this method are as follows (Liao & Wu, 2020; Ecer, 2020):

Step 1: Normalized decision matrix

The elements of the decision matrix are normalized with linear [TeX:] \left( {\widehat{x}}_{\text{ij}}^{1N} \right)\text{\ \ \ } $({\hat{x}}_{ij}^{1 N})$ normalization using the following equation:

[TeX:] {\widehat{x}}_{\text{ij}}^{1N} = 1 - \frac{\left| x_{\text{ij}} - r_{j} \right|}{\max\left\{ \max_{i}{x_{\text{ij}},r_{j}} \right\} - min\left\{ \min_{i}{x_{\text{ij}},r_{j}} \right\}}\ \ \ \ \ (4)

{\hat{x}}_{ij}^{1 N} = 1 - \frac{| x_{ij} - r_{j} |}{max {max_{i} x_{ij}, r_{j}} - m i n {min_{i} x_{ij}, r_{j}}} (4)

The vector [TeX:] \left( {\widehat{x}}_{\text{ij}}^{2N} \right)\text{\ \ \ } $({\hat{x}}_{ij}^{2 N})$ is normalized using the following equation:

[TeX:] {\widehat{x}}_{\text{ij}}^{2N} = 1 - \frac{\left| x_{\text{ij}} - r_{j} \right|}{\sqrt{\sum_{i = 1}^{m}{\left( x_{\text{ij}} \right)^{2} + \left( r_{j} \right)^{2}}}}\ \ \ \ \ (5)

{\hat{x}}_{ij}^{2 N} = 1 - \frac{| x_{ij} - r_{j} |}{\sqrt{\sum_{i = 1}^{m} {(x_{ij})}^{2} + {(r_{j})}^{2}}} (5)

The value [TeX:] r_{j}\text{\ \ \ \ } $r_{j}$ is the target value for [TeX:] c_{j}\text{\ \ \ } $c_{j}$ the criterion and is considered [TeX:] \max_{i}x_{\text{ij}}\text{\ \ \ } ${max}_{i} x_{ij}$ for both utility and [TeX:] \min_{i}x_{\text{ij}}\text{\ \ \ } ${min}_{i} x_{ij}$ cost criteria.

Step 2: Determining the weight of the criteria

This step consists of three phases:

Step 2.1: In this phase, the standard deviation [TeX:] \left( \sigma_{j} \right)\text{\ \ \ } $(σ_{j})$ for the criterion [TeX:] c_{j}\text{\ \ } $c_{j}$ is determined with the following equation where m is the number of alternatives:

[TeX:] \sigma_{j} = \sqrt{\frac{\sum_{i = 1}^{m}\left( \frac{x_{\text{ij}}}{\max_{i}x_{\text{ij}}} - \frac{1}{m}\sum_{i = 1}^{m}\left( \frac{x_{\text{ij}}}{\max_{i}x_{\text{ij}}} \right) \right)^{2}}{m}\ \ \ \ \ \ (6)}

σ_{j} = \sqrt{\frac{\sum_{i = 1}^{m} {(\frac{x_{ij}}{max_{i} x_{ij}} - \frac{1}{m} \sum_{i = 1}^{m} (\frac{x_{ij}}{max_{i} x_{ij}}))}^{2}}{m} (6)}

Step 2.2: Values of the standard deviation calculated for the criteria are normalized with the following equation:

[TeX:] w_{j}^{\sigma} = \frac{\sigma_{j}}{\sum_{i = 1}^{n}\sigma_{j}}\ \ \ \ \ (7)

w_{j}^{σ} = \frac{σ_{j}}{\sum_{i = 1}^{n} σ_{j}} (7)

Step 2.3: Finally, the weights are adjusted with the following equation:

[TeX:] {\widehat{w}}_{j} = \frac{\sqrt{w_{j}^{\sigma}.w_{j}}}{\sum_{i = 1}^{n}\sqrt{w_{j}^{\sigma}.w_{j}}}\ \ \ \ \ (8)

{\hat{w}}_{j} = \frac{\sqrt{w_{j}^{σ} . w_{j}}}{\sum_{i = 1}^{n} \sqrt{w_{j}^{σ} . w_{j}}} (8)

Step 3: Calculating the aggregation model

Three aggregation functions (CCM, UCM and ICM) are calculated separately for each alternative.

The CCM (Complete Compensation Model) is calculated using the following equation:

[TeX:] u_{1}\left( a_{i} \right) = \sum_{j = 1}^{n}\frac{{\widehat{w}}_{j}.{\widehat{x}}_{\text{ij}}^{1N}}{\max_{i}{\widehat{x}}_{\text{ij}}^{1N}}\ \ \ \ \ (9)

u_{1} (a_{i}) = \sum_{j = 1}^{n} \frac{{\hat{w}}_{j} . {\hat{x}}_{ij}^{1 N}}{max_{i} {\hat{x}}_{ij}^{1 N}} (9)

The UCM (non-compensatory model) is calculated using the following equation:

[TeX:] u_{2}\left( a_{i} \right) = \max_{j}{{\widehat{w}}_{j}\left( \frac{1 - {\widehat{x}}_{\text{ij}}^{1N}}{\max_{i}{\widehat{x}}_{\text{ij}}^{1N}} \right)\ \ \ \ \ (10)}

u_{2} (a_{i}) = max_{j} {\hat{w}}_{j} (\frac{1 - {\hat{x}}_{ij}^{1 N}}{max_{i} {\hat{x}}_{ij}^{1 N}}) (10)

The ICM (Incomplete Compensation Model) is calculated using the following equation:

[TeX:] u_{3}\left( a_{i} \right) = \prod_{j = 1}^{n}{\left( \frac{{\widehat{x}}_{\text{ij}}^{2N}}{\max_{i}{\widehat{x}}_{\text{ij}}^{2N}} \right)^{{\widehat{w}}_{j}}\ \ \ \ \ (11)}

u_{3} (a_{i}) = \prod_{j = 1}^{n} {(\frac{{\hat{x}}_{ij}^{2 N}}{max_{i} {\hat{x}}_{ij}^{2 N}})}^{{\hat{w}}_{j}} (11)

Step 4: Integration of utility values

The calculated utility functions are integrated with the following equation using the Euclidean principle of distance:

[TeX:] \text{DN}_{i} = \ w_{1}\sqrt{\varphi \bullet \left( \frac{u_{1}\left( a_{i} \right)}{\max_{i}{u_{1}\left( a_{i} \right)}} \right)^{2} + \left( 1 - \varphi \right) \bullet \left( \frac{m - r_{1}\left( a_{i} \right) + 1}{m} \right)^{2}} - w_{2}\sqrt{\varphi \bullet \left( \frac{u_{2}\left( a_{i} \right)}{\max_{i}{u_{2}\left( a_{i} \right)}} \right)^{2} + \left( 1 - \varphi \right) \bullet \left( \frac{r_{2}\left( a_{i} \right)}{m} \right)^{2}} + w_{3}\sqrt{\varphi \bullet \left( \frac{u_{3}\left( a_{i} \right)}{\max_{i}{u_{3}\left( a_{i} \right)}} \right)^{2} + \left( 1 - \varphi \right) \bullet \left( \frac{m - r_{3}\left( a_{i} \right) + 1}{m} \right)^{2}}\ \ \ \ \ (12)

{DN}_{i} = w_{1} \sqrt{φ • {(\frac{u_{1} (a_{i})}{max_{i} u_{1} (a_{i})})}^{2} + (1 - φ) • {(\frac{m - r_{1} (a_{i}) + 1}{m})}^{2}} - w_{2} \sqrt{φ • {(\frac{u_{2} (a_{i})}{max_{i} u_{2} (a_{i})})}^{2} + (1 - φ) • {(\frac{r_{2} (a_{i})}{m})}^{2}} + w_{3} \sqrt{φ • {(\frac{u_{3} (a_{i})}{max_{i} u_{3} (a_{i})})}^{2} + (1 - φ) • {(\frac{m - r_{3} (a_{i}) + 1}{m})}^{2}} (12)

In this case, the means [TeX:] r_{1}\left( a_{i} \right)\text{\ \ } $r_{1} (a_{i})$ and [TeX:] r_{3}\left( a_{i} \right)\text{\ \ \ } $r_{3} (a_{i})$ represent the ordinal number of the alternative [TeX:] a_{i}\text{\ \ \ } $a_{i}$ sorted by CCM and ICM functions in descending value (higher value first). On the other hand, [TeX:] r_{2}\left( a_{i} \right)\ $r_{2} (a_{i})$ shows the sequence number in the obtained order according to the increasing value (smaller value first) for the UCM function used. The label [TeX:] \text{φ\ \ \ } $φ$ is the relative importance of the child value used and is in the range [0;1]. It is considered that it can be taken as [TeX:] \varphi = 0.5 $φ = 0.5$ . The coefficients [TeX:] w_{1},w_{2},w_{3} $w_{1}, w_{2}, w_{3}$ are obtained weights of the used functions CCM, UCM and ICM, respectively. The sum should be equal [TeX:] w_{1} + w_{2} + w_{3} = 1 $w_{1} + w_{2} + w_{3} = 1$ . When determining the weights, if the decision maker attaches importance to a wider range of performance alternatives, he can set a higher value for [TeX:] w_{1} $w_{1}$ . In case the decision maker is not willing to take risks, ie. to choose a poor alternative according to some criterion, he can assign a higher weight to [TeX:] w_{2} $w_{2}$ . However, the decision maker may assign a greater weight to [TeX:] w_{3} $w_{3}$ if he simultaneously considers overall performance and risk. Finally, the DN values are sorted in descending order, with the higher value alternatives being the best.

2. RESULTS AND DISCUSSION

For the purpose of analyzing the performance of companies in Serbia, the following criteria were chosen: C1 - number of employees, C2 - business assets, C3 - capital, C4 - business income and C5 - net profit/net loss. They were chosen because they are good measures of company performance. Alternatives are observed companies in Serbia. According to what criteria were the companies selected? The selection of companies was made according to the realized business income in 2021. They have different ownership structures. However, the ownership structure of the company does not affect the results of multi-criteria decision-making methods. This means, in other words, that the results obtained in this paper are valid. Criteria, alternatives and initial data are shown in Table 1 for 2021.

Table 1. Initial data

		Sector	(I) Number of employees	(I) Business assets	(I) Capital	(O) Business income	(O)Net gain / Net loss
			C1	C2	C3	C4	C5
A1	JP EPS BELGRADE	D-supply of electricity, gas, steam and air conditioning	24.013	959.978	602.051	319.834	- 15.492
A2	NIS AD NOVI SAD	B-mining	11.544	411.025	262.836	310.238	20.957
A3	TELEKOM SRBIJA AD, BELGRADE	J-information and communications	12.333	490.964	185.581	144.701	6.709
A4	JP SRBIJAGAS NOVI SAD	D-supply of electricity, gas, steam and air conditioning	2.471	287.578	129.753	122.489	5.802
A5	DELHAIZE S	G-wholesale and retail trade; repair of motor vehicles and motorcycles	11.637	83.293	42.881	118.912	2.989
A6	NELT CO. DOO BELGRADE	G-wholesale and retail trade; repair of motor vehicles and motorcycles	3.121	37.637	18.721	87.126	248
A7	DELTA HOLDING DOO BELGRADE	M-professional, scientific, innovative and technical activities	3.311	149.188	83.718	76.424	2.497
A8	MERCATA VT DOO	G-wholesale and retail trade; repair of motor vehicles and motorcycles	1.078	12.763	1.093	75.391	958
A9	PHOENIX PHARMA DOO BELGRADE	G-wholesale and retail trade; repair of motor vehicles and motorcycles	2.749	39.024	10.837	74.941	1.772
A10	COCA-COLA HBC - SERBIA DOO ZEMUN	C-processing industry	1.623	56.832	43.084	64.769	6.783
A11	MY KIOSK GROUP DOO	K-financial activities and insurance activities	3.589	12.247	2.622	64.365	596
A12	TARKETT DOO BACA PALANKA	C-processing industry	3.215	38.174	19.813	58.565	2.493
A13	MK GROUP DOO BELGRADE	K-financial activities and insurance activities	2.151	94.429	46.830	57.675	17.461
A14	KNEZ PETROL COMPANY DOO BELGRADE	M-professional, scientific, innovative and technical activities	1.183	11.849	3.417	52.652	3.447
A15	HEMOFARM AD VRŠAC	C-processing industry	3.922	68.380	47.524	49.284	5.091
A16	MILŠED DOO BELGRADE	H-transport and storage	2.758	27.749	3.547	45.553	1.084
A17	FCA SERBIA DOO KRAGUJEVAC	C-processing industry	2.072	49.521	31.195	41.512	- 3.866
A18	EMSAD BELGRADE	D-supply of electricity, gas, steam and air conditioning	1.656	105.336	69.530	39.043	2.362
A19	KOEFIK DOO BELGRADE	G-wholesale and retail trade; repair of motor vehicles and motorcycles	2.983	34.703	8.502	38.062	152
A20	YURA CORPORATION DOO RACA	C-processing industry	6.913	27.713	4.458	37.188	- 1.092

Note: Data are expressed in millions of dinars. The number of employees is expressed in whole numbers. I - input. O - output

Source: Annual report on the operations of economic units in the economy in 2021. Agency for Economic Registers of the Republic of Serbia

The weighting coefficients of the criteria were determined using the LMAW method. Tables 2-5 show the calculations and results of the LMAW method. (In this paper, all calculations and results are the authors).

Table 2. Prioritization scale

Prioritization Scale
Linguistic Variables	Abbreviation	Prioritization
Absolutely Low	AL	1
Very Low	VL	1.5
Low	L	2
Medium	M	2.5
Equal	E	3
Medium High	MH	3.5
High	H	4
Very High	VH	4.5
Absolutely High	AH	5

Source: author

Table 3. Evaluation of criteria

KIND	1	1	1	1	1
	C1	C2	C3	C4	C5
E1	H	AH	H	E	MH
E2	VH	VH	MH	H	H
E3	E	MH	VH	AH	AH
E4	MH	E	E	VH	AH
ϒ_AIP	0.5

	C1	C2	C3	C4	C5	LN(Πη)
R1	8	10	8	6	7	10.199
R2	9	9	7	8	8	10.499
R3	6	7	9	10	10	10.540
R4	7	6	6	9	10	10.029

Source: author

Table 4. Weight coefficients of criteria and aggregated fuzzy vectors

Weight Coefficients Vector	C1	C2	C3	C4	C5
W1j	0.204	0.226	0.204	0.176	0.191
W2j	0.209	0.209	0.185	0.198	0.198
W3j	0.170	0.185	0.208	0.218	0.218
W4j	0.194	0.179	0.179	0.219	0.230
Aggregated Fuzzy Vectors	C1	C2	C3	C4	C5
W1j	0.010	0.011	0.010	0.009	0.010
W2j	0.010	0.010	0.009	0.010	0.011
W3j	0.009	0.009	0.010	0.011	0.011
W4j	0.009	0.009	0.009	0.011	0.012
SUM	0.038	0.040	0.038	0.041	0.044
Aggregated Weight Coefficient Vectors	0.1941	0.1993	0.1940	0.2026	0.2090

Source: author

In the specific case, therefore, the most important criterion is C5 - net gain/net loss. This means, in other words, that, among other things, more efficient profit management can achieve the target performance of companies in Serbia. Tables 5 - 11 show the calculations and results of the DNMA method.

Table 5. Initial Matrix

INITIAL MATRIX	KIND	1	1	1	1	1
	Weight	0.1941	0.1993	0.1940	0.2026	0.2090
		C1	C2	C3	C4	C5
	A1	24.013	959.978	602.051	319.834	-15.492
	A2	11.544	411.025	262.836	310.238	20.957
	A3	12.333	490.964	185.581	144.701	6.709
	A4	2.471	287.578	129.753	122.489	5.802
	A5	11.637	83.293	42.881	118.912	2.989
	A6	3.121	37.637	18.721	87.126	248
	A7	3.311	149.188	83.718	76.424	2.497
	A8	1.078	12.763	1.093	75.391	958
	A9	2.749	39.024	10.837	74.941	1.772
	A10	1.623	56.832	43.084	64.769	6.783
	A11	3.589	12.247	2.622	64.365	596
	A12	3.215	38.174	19.813	58.565	2.493
	A13	2.151	94.429	46.83	57.675	17.461
	A14	1.183	11.849	3.417	52.652	3.447
	A15	3.922	68.38	47.524	49.284	5.091
	A16	2.758	27.749	3.547	45.553	1.084
	A17	2.072	49.521	31.195	4.512	-3.866
	A18	1.656	105.336	69.53	39.043	2.362
	A19	2.983	34.703	8.502	38.062	152
	A20	6.913	27.713	4.458	37.188	-1.092
MAX		24.0130	959.9780	602.0510	319.8340	958.0000
MIN		1.0780	11.8490	1.0930	37.1880	-15.4920

Source: author

Table 6. Linear Normalization Matrix

	C1	C2	C3	C4	C5	MAX
A1	1.0000	1.0000	1.0000	1.0000	0.0000	1.0000
A2	0.4563	0.4210	0.4355	0.9660	0.0374	0.9660
A3	0.4907	0.5053	0.3070	0.3804	0.0228	0.5053
A4	0.0607	0.2908	0.2141	0.3018	0.0219	0.3018
A5	0.4604	0.0754	0.0695	0.2891	0.0190	0.4604
A6	0.0891	0.0272	0.0293	0.1767	0.2707	0.2707
A7	0.0974	0.1449	0.1375	0.1388	0.0185	0.1449
A8	0.0000	0.0010	0.0000	0.1352	1.0000	1.0000
A9	0.0729	0.0287	0.0162	0.1336	0.0177	0.1336
A10	0.0238	0.0474	0.0699	0.0976	0.0229	0.0976
A11	0.1095	0.0004	0.0025	0.0962	0.6281	0.6281
A12	0.0932	0.0278	0.0312	0.0756	0.0185	0.0932
A13	0.0468	0.0871	0.0761	0.0725	0.0339	0.0871
A14	0.0046	0.0000	0.0039	0.0547	0.0195	0.0547
A15	0.1240	0.0596	0.0773	0.0428	0.0211	0.1240
A16	0.0733	0.0168	0.0041	0.0296	0.0170	0.0733
A17	0.0433	0.0397	0.0501	0.0153	0.0000	0.0501
A18	0.0252	0.0986	0.1139	0.0066	0.0183	0.1139
A19	0.0831	0.0241	0.0123	0.0031	0.1721	0.1721
A20	0.2544	0.0167	0.0056	0.0000	0.0000	0.2544

Source: author

Table 7. Vector Normalization Matrix

	C1	C2	C3	C4	C5	MAX
A1	1.0000	1.0000	1.0000	1.0000	0.0000	1.0000
A2	0.7001	0.6459	0.6357	0.9849	0.3790	0.9849
A3	0.7190	0.6974	0.5528	0.7245	0.3695	0.7245
A4	0.4818	0.5662	0.4928	0.6896	0.3689	0.6896
A5	0.7023	0.4345	0.3996	0.6839	0.3670	0.7023
A6	0.4974	0.4050	0.3736	0.6339	0.5294	0.6339
A7	0.5020	0.4770	0.4434	0.6171	0.3667	0.6171
A8	0.4483	0.3890	0.3547	0.6155	1.0000	1.0000
A9	0.4885	0.4059	0.3651	0.6148	0.3662	0.6148
A10	0.4614	0.4174	0.3998	0.5988	0.3696	0.5988
A11	0.5087	0.3886	0.3563	0.5981	0.7601	0.7601
A12	0.4997	0.4053	0.3748	0.5890	0.3667	0.5890
A13	0.4741	0.4416	0.4038	0.5876	0.3766	0.5876
A14	0.4508	0.3884	0.3572	0.5797	0.3674	0.5797
A15	0.5167	0.4248	0.4045	0.5744	0.3684	0.5744
A16	0.4887	0.3986	0.3573	0.5685	0.3658	0.5685
A17	0.4722	0.4127	0.3870	0.5622	0.0000	0.5622
A18	0.4622	0.4487	0.4282	0.5583	0.3666	0.5583
A19	0.4941	0.4031	0.3626	0.5567	0.4658	0.5567
A20	0.5887	0.3986	0.3583	0.5554	0.0000	0.5887
Adj Wj	0.1938	0.1994	0.1927	0.2056	0.2086

Source: author

Table 8. CCM (Complete Compensatory Model)

u1(ai)	C1	C2	C3	C4	C5	SUM
A1	0.1938	0.1994	0.1927	0.2056	0.0000	0.7914
A2	0.0915	0.0869	0.0869	0.2056	0.0081	0.4789
A3	0.1882	0.1994	0.1171	0.1547	0.0094	0.6687
A4	0.0390	0.1921	0.1367	0.2056	0.0151	0.5885
A5	0.1938	0.0326	0.0291	0.1291	0.0086	0.3932
A6	0.0638	0.0200	0.0209	0.1342	0.2086	0.4475
A7	0.1302	0.1994	0.1829	0.1970	0.0266	0.7361
A8	0.0000	0.0002	0.0000	0.0278	0.2086	0.2366
A9	0.1057	0.0428	0.0234	0.2056	0.0277	0.4051
A10	0.0472	0.0969	0.1380	0.2056	0.0489	0.5366
A11	0.0338	0.0001	0.0008	0.0315	0.2086	0.2748
A12	0.1938	0.0594	0.0644	0.1669	0.0414	0.5258
A13	0.1041	0.1994	0.1684	0.1711	0.0811	0.7240
A14	0.0162	0.0000	0.0136	0.2056	0.0742	0.3096
A15	0.1938	0.0959	0.1200	0.0709	0.0356	0.5162
A16	0.1938	0.0456	0.0107	0.0831	0.0485	0.3817
A17	0.1677	0.1581	0.1927	0.0628	0.0000	0.5812
A18	0.0429	0.1726	0.1927	0.0118	0.0336	0.4536
A19	0.0935	0.0279	0.0138	0.0037	0.2086	0.3476
A20	0.1938	0.0131	0.0042	0.0000	0.0000	0.2111

Source: author

Table 9. UCM (Uncompensatory Model)

u2(ai)	C1	C2	C3	C4	C5	MAX
A1	0.0000	0.0000	0.0000	0.0000	0.0000	0.0000
A2	0.1022	0.1125	0.1058	0.0000	0.2006	0.2006
A3	0.0056	0.0000	0.0756	0.0508	0.1992	0.1992
A4	0.1548	0.0073	0.0560	0.0000	0.1935	0.1935
A5	0.0000	0.1667	0.1636	0.0765	0.2000	0.2000
A6	0.1300	0.1793	0.1718	0.0714	0.0000	0.1793
A7	0.0635	0.0000	0.0098	0.0086	0.1820	0.1820
A8	0.1938	0.1992	0.1927	0.1778	0.0000	0.1992
A9	0.0881	0.1566	0.1693	0.0000	0.1809	0.1809
A10	0.1466	0.1024	0.0547	0.0000	0.1597	0.1597
A11	0.1600	0.1992	0.1919	0.1741	0.0000	0.1992
A12	0.0000	0.1399	0.1283	0.0387	0.1673	0.1673
A13	0.0897	0.0000	0.0243	0.0345	0.1276	0.1276
A14	0.1775	0.1994	0.1791	0.0000	0.1345	0.1994
A15	0.0000	0.1035	0.0726	0.1346	0.1731	0.1731
A16	0.0000	0.1537	0.1819	0.1225	0.1601	0.1819
A17	0.0261	0.0412	0.0000	0.1428	0.0000	0.1428
A18	0.1509	0.0267	0.0000	0.1937	0.1750	0.1937
A19	0.1002	0.1714	0.1789	0.2019	0.0000	0.2019
A20	0.0000	0.1862	0.1884	0.2056	0.0000	0.2056

Source: author

Table 10. ICM (Incomplete Compensatory Model)

u3(ai)	C1	C2	C3	C4	C5	MAX
A1	1.0000	1.0000	1.0000	1.0000	0.0000	0.0000
A2	0.9360	0.9193	0.9191	1.0000	0.8193	0.6480
A3	0.9985	0.9924	0.9492	1.0000	0.8689	0.8174
A4	0.9329	0.9615	0.9373	1.0000	0.8776	0.7379
A5	1.0000	0.9087	0.8970	0.9946	0.8734	0.7080
A6	0.9541	0.9146	0.9031	1.0000	0.9631	0.7590
A7	0.9608	0.9499	0.9383	1.0000	0.8971	0.7683
A8	0.8560	0.8284	0.8190	0.9050	1.0000	0.5256
A9	0.9564	0.9206	0.9045	1.0000	0.8976	0.7148
A10	0.9508	0.9306	0.9251	1.0000	0.9042	0.7401
A11	0.9251	0.8748	0.8642	0.9519	1.0000	0.6658
A12	0.9686	0.9282	0.9166	1.0000	0.9059	0.7465
A13	0.9593	0.9447	0.9303	1.0000	0.9114	0.7683
A14	0.9524	0.9233	0.9109	1.0000	0.9092	0.7283
A15	0.9797	0.9416	0.9347	1.0000	0.9115	0.7860
A16	0.9711	0.9317	0.9144	1.0000	0.9121	0.7546
A17	0.9668	0.9402	0.9306	1.0000	0.0000	0.0000
A18	0.9641	0.9574	0.9502	1.0000	0.9160	0.8033
A19	0.9771	0.9377	0.9207	1.0000	0.9635	0.8128
A20	1.0000	0.9252	0.9088	0.9881	0.0000	0.0000

Source: author

Table 11. Ranking of alternatives according to the DNMA method

											w1	w2	w3
											0.6	0.1	0.3
		CCM	φ	UCM	φ	ICM	φ	Utility Values	Rank Order
		u1(ai)	Rank	0.5	u2(ai)	Rank	0.5	u3(ai)	Rank	0.5
JP EPS BELGRADE	A1	0.7914	1	1.0000	0.0000	1	0.0354	0.0000	18	0.1061	0.6354	0.6354	9
NIS AD NOVI SAD	A2	0.4789	10	0.5783	0.2006	18	0.9386	0.6480	16	0.5878	0.6171	0.6171	11
TELEKOM SRBIJA AD, BELGRADE	A3	0.6687	4	0.8475	0.1992	15	0.8666	0.8174	1	1.0000	0.8952	0.8952	1
JP SRBIJAGAS NOVI SAD	A4	0.5885	5	0.7723	0.1935	11	0.7710	0.7379	11	0.7297	0.7594	0.7594	4
DELHAIZE S	A5	0.3932	14	0.4298	0.2000	17	0.9137	0.7080	14	0.6606	0.5474	0.5474	15
NELT CO. DOO BELGRADE	A6	0.4475	12	0.5110	0.1793	7	0.6646	0.7590	7	0.8223	0.6198	0.6198	10
DELTA HOLDING DOO BELGRADE	A7	0.7361	2	0.9401	0.1820	10	0.7191	0.7683	6	0.8503	0.8911	0.8911	2
MERCATA VT DOO	A8	0.2366	19	0.2229	0.1992	13	0.8250	0.5256	17	0.4762	0.3591	0.3591	19
PHOENIX PHARMA DOO BELGRADE	A9	0.4051	13	0.4594	0.1809	8	0.6837	0.7148	13	0.6800	0.5480	0.5480	14
COCA-COLA HBC - SERBIA DOO ZEMUN	A10	0.5366	7	0.6891	0.1597	4	0.5673	0.7401	10	0.7491	0.6949	0.6949	6
MY KIOSK GROUP DOO	A11	0.2748	18	0.2675	0.1992	14	0.8454	0.6658	15	0.6138	0.4292	0.4292	18
TARKETT DOO BACA PALANKA	A12	0.5258	8	0.6573	0.1673	5	0.6020	0.7465	9	0.7727	0.6864	0.6864	7
MK GROUP DOO BELGRADE	A13	0.7240	3	0.9074	0.1276	2	0.4445	0.7683	5	0.8728	0.8507	0.8507	3
KNEZ PETROL COMPANY DOO BELGRADE	A14	0.3096	17	0.3107	0.1994	16	0.8890	0.7283	12	0.7058	0.4871	0.4871	17
HEMOFARM AD VRŠAC	A15	0.5162	9	0.6267	0.1731	6	0.6320	0.7860	4	0.9075	0.7115	0.7115	5
MILŠED DOO BELGRADE	A16	0.3817	15	0.4017	0.1819	9	0.7021	0.7546	8	0.7984	0.5507	0.5507	13
FCA SERBIA DOO KRAGUJEVAC	A17	0.5812	6	0.7423	0.1428	3	0.5025	0.0000	18	0.1061	0.5274	0.5274	16
EMSAD BELGRADE	A18	0.4536	11	0.5379	0.1937	12	0.7900	0.8033	3	0.9423	0.6844	0.6844	8
KOEFIK DOO BELGRADE	A19	0.3476	16	0.3574	0.2019	19	0.9661	0.8128	2	0.9724	0.6028	0.6028	12
YURA CORPORATION DOO RACA	A20	0.2111	20	0.1919	0.2056	20	1.0000	0.0000	18	0.1061	0.2470	0.2470	20
	MAX	0.7914			0.2056			0.8174

Source: author

Therefore, according to the results of the DNMA method, the top five companies in Serbia in terms of performance are: TELEKOM SRBIJA AD, BELGRADE, DELTA HOLDING DOO BELGRADE, MK GROUP DOO BELGRADE, JP SRBIJAGAS NOVI SAD and HEMOFARM AD VRŠAC. The best performance was recorded at the company TELEKOM SRBIJA AD, BELGRADE. The company with the worst performance is YURA CORPORATION DOO RAČA. Factors for positioning companies in Serbia according to performance are numerous factors: general economic conditions, inflation, interest rate, exchange rate, employment, standard of living of the population, the Covid-19 pandemic, the energy crisis, and the efficiency of managing human resources, assets, capital, sales and profit. The application of new cost management concepts (calculation of costs by basic activities, target costs and profit, kaizen concept, etc.) and digitization of the entire business play a significant role in this. Effective control of these and other factors can significantly influence the achievement of the target performance of companies in Serbia.

CONCLUSION

Based on the results of empirical research on the performance of companies in Serbia, the following can be concluded: according to the results of the DNMA method, the top five companies in Serbia include: TELEKOM SRBIJA AD, BELGRADE, DELTA HOLDING DOO BELGRADE, MK GROUP DOO BELGRADE, JP SRBIJAGAS NOVI SAD and HEMOFARM AD VRŠAC. The best performance was recorded at the company TELEKOM SRBIJA AD, BELGRADE. The company with the worst performance is YURA CORPORATION DOO RAČA. There are numerous determinants of the performance of companies in Serbia. These are: general economic conditions, inflation, interest rate, exchange rate, employment, living standards of the population, the Covid-19 pandemic, the energy crisis, the efficiency of managing human resources, assets, capital, sales and profits, and the digitization of the entire business. The application of new concepts of cost management (for example, calculation of costs by basic activities) plays a significant role in this. Effective control of these and other factors can significantly influence the achievement of the target performance of companies in Serbia.

REFERENCES

Notes

[1] ^* Faculty of Economics, University of Belgrade, e-mail: radojko.lukic@ekof.bg.ac.rs

References

Alam, T.E., González, A.D. and Raman, S. 2022Benchmarking of academic departments using data envelopment analysis (DEA). Journal of Applied Research in Higher Education. 1–30. https://doi.org/10.1108/JARHE-03-2021-0087

Amini, A., Alinezhad, A., & Yazdipoor, F. 2019A TOPSIS, VIKOR and DEA integrated evaluation method with belief structure under uncertainty to rank alternatives. International Journal of Advanced Operations Management. 11(3):171–188

Amin, G. R., & Hajjami, M. 2021Improving DEA cross-efficiency optimization in portfolio selection. Expert Systems with Applications. 168:114280

Amirteimoori, A., Mehdizadeh, S., & Kordrostami, S., 2022Stochastic performance measurement in two-stage network processes: A data envelopment analysis approach. Kybernetika. 58(2):200–217. https://doi.org/DOI: 10.14736/kyb-2022-2-0200

Andersen, P., & Petersen, N.C. 1993A procedure for ranking efficient units in data envelopment analysis. Management Science. 39:1261–1264

Ayçin, E., &Arsu, T. 2021Sosyal Gelişme Endeksine Göre Ülkelerin Değerlendirilmesi: MEREC ve MARCOS Yöntemleri ile Bir Uygulama. İzmir Yönetim Dergisi. 2(2):75–88

Banker, R.D., A. Charnes, A., & Cooper, WW 1984Some models for estimating technical and scale inefficiencies in data envelopment analysis. Management Science. 30(9):1078–1092

Chang, X., & Wang, X. 2020Research Performance Evaluation of University Based on Super DEA Model.2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 1252-1255. https://doi.org/ 10.1109/ITAIC49862.2020.9339131

Chen, W., Gai, Y., & Gupta, P. 2018Efficiency evaluation of fuzzy portfolio in different risk measures via DEA. Annals of Operations Research. 269(1):103–127. DOI:. https://doi.org/10.1007/s10479-017-2411-9

Chen, W., Li, S. S., Zhang, J., & Mehlawat, M. K. 2020A comprehensive model for fuzzy multi-objective portfolio selection based on DEA cross-efficiency model. Soft computing. 24(4):2515–2526

Chen, W., Li, S. S., Mehlawat, M. K., Jia, L., & Kumar, A. 2021Portfolio Selection Using Data Envelopment Analysis Cross-Efficiency Evaluation with Undesirable Fuzzy Inputs and Outputs. International Journal of Fuzzy Systems. 23(5):1478–1509

Chen, Chunhua, Liu, Haohua, Tang, Lijun & Ren, Jianwei. 2021A Range Adjusted Measure of Super-Efficiency in Integer-Valued Data Envelopment Analysis with Undesirable Outputs. Journal of Systems Science and Information. 9(4):378–398. https://doi.org/10.21078/JSSI-2021-378-21

Cooper, W. W., Park, K. S., & Pastor, J. T. 1999RAM: a range adjusted measure of inefficiency for use with additive models, and relations to other models and measures in DEA. Journal of Productivity analysis. 11(1):5–42. DOI:. https://doi.org/10.1023/A:1007701304281

Demir, G. 2022Analysis of the financial performance of the deposit banking sector in the Covid-19 period with LMAW-DNMA methods. International Journal of Insurance and Finance. 2(2):17–36. https://doi.org/10.52898/ijif.2022.7

Ecer, F. 2020Multi-criteriad Decision-making comprehensive approach from past to present. Seçkin Publications.;

Ecer,F., & Aycin, E. 2022Novel Comprehensive MEREC Weighting-Based Score Aggregation Model for Measuring Innovation Performance: The Case of G7 Countries. Informatica. 131:101538822–10494

Đurić, Z., Jakšić,M. & Krstić, A. 2020DEA window analysis of insurance sector efficiency in the Republic of Serbia. Economic Themes. 58291310(3) https://doi.org/ 10.2478/ethemes-2020-0017

Fenyves, V., & Tarnóczi, T. 2020Data envelopment analysis for measuring performance in a competitive market. Problems and Perspectives in Management. 18(1):315–325. https://doi.org/10.21511/ppm.18(1).2020.27

Fotova Čiković, K., & Lozić, J. 2022Application of Data Envelopment Analysis (DEA) in Information and Communication Technologies. Tehnički glasnik. 16(1):129–134. https://doi.org/10.31803/tg-20210906103816

Guo, D., & Cai, Z.Q. 2020Super-Efficiency Infeasibility in the Presence of Nonradial Measurement.Mathematical Problems in Engineering, 2020 Article. 6264852:p. 7https://doi.org/10.1155/2020/6264852

Liao, H., & Wu, X. 2020DNMA: A double normalization-based multiple aggregation methods for multi-expert multi-criteria decision making. Omega. 94:102058https://doi.org/10.1016/j.omega.2019.04.001

Lee, H.S., Chu, C.W.,: & J. Zhu, J. 2011Super-efficiency DEA in the presence of infeasibility. European Journal of Operational Research. 212(1):141–147

Lin, R. 2020Cross-efficiency evaluation capable of dealing with negative data: A directional distance function based approach. Journal of the Operational Research Society. 71(3):505–516

Lukic, R., Sokic, M., & Kljenak, D.V. 2017Efficiency analysis of the banking sector in the Republic of Serbia. Business Excellence and Management. 7:5–17

Lukic, R. 2018Analysis of the efficiency of insurance companies.In: Insurance in the post-crisis era. Belgrade: Faculty of Economics, University of; Belgrade.: ISBN: 978-86-403-1548-7.

Lukic, R., & Hadrovic Zekic, B. 2019Evaluation of efficiency of trade companies in Serbia using the DEA approach.Proceedings of the 19 th International Scientific Conference Business Logistics In Modern Management October 10-11. Osijek, Croatia,: Josip Juraj Strossmayer University of Osijek, Faculty of Economics in Osijek,; p. 145–165

Lukić, R., & Kozarević, E. 2019Analysis of selected countries trade efficiency based on the DEA models.December 2019, Conference: The Sixth Scientific Conference with International Participation "Economy of Integration" ICEI 2019 - (E) Migrations And Competitiveness Of South-Eastern European Countries. At: Tuzla, Bosnia and Herzegovina. p. 61–71

Lukić, R., Hanić, H., & Bugarčić, M. 2020Analysis of profitability and efficiency of trade in Serbia. Economic Analusis. 53(2):39–50

Lukić, R. 2021Evaluation of the efficiency of public companies in Serbia using the ARAS method. Proceedings of the Conference. 8:43–53

Lukic, R. 2022Analysis of efficiency factors of companies in Serbia based on artificial neural networks.Анали Економског факултетa у Суботици – The Annals of the Facult y of Economics in Subotica. 58(47):p. 097–115. https://doi.org/DOI: 10.5937/AnEkSub2247097L

Lukic, R. 2022Evaluation of financial performance and efficiency of companies in Serbia. Journal of engineering management and competitiveness (JEMC). 12(2):132–141. https://doi.org/DOI: 10.5937/JEMC2202132L

Lukic, R.(2022c). Measurement and Analysis of the Dynamics of Financial Performance and Efficiency of Trade in Serbia Based on the DEA Super-Radial Model. Review of International Comparative Management. 23(5):630–645. https://doi.org/DOI: 10.24818/RMCI.2022.5.630

Lukic, R. 2023Measurement and analysis of the information performance of companies in the European Union and Serbia based on the fuzzy LMAW and MARCOS methods. Informatica Economica. 27(1):17–31. https://doi.org/DOI: 10.24818/issn14531305/27.1.2023.02

Mandić, K., Delibašić, B., Knežević, S. & Benković, S. 2017Analysis of the efficiency of insurance companies in Serbia using the fuzzy AHP and TOPSIS methods. Economic Research. 30(1):550–565

Martić, M., & Savić, G. 2001An application of DEA for comparative analysis and ranking of regions in Serbia with regards to social-economic development. European Journal of Operational Research. 132(2):343–356. https://doi.org/10.1016/S0377-22170000156–22170000159

Mishra, A.R., Saha, A., Rani, P., & Hezam, I.M. et al., 2022An Integrated Decision Support Framework Using Single-Valued-MEREC-MULTIMOORA for Low Carbon Tourism Strategy Assessment",. in IEEE Access. 10:24411–24432

Nguyen, H.-Q., Nguyen, V.-T., Phan, D.-P., Tran, Q.-H., & Vu, N.-P. 2022Multi-Criteria Decision Making in the PMEDM Process by Using MARCOS, TOPSIS, and MAIRCA Methods. Appl. Sci. 12:3720https://doi.org/10.3390/ app12083720

Zohreh Moghaddas, Z., Oukil, A., & Vaez-Ghasemi, M. 2022Global multi-period performance evaluation - new model and productivity index. RAIRO-Oper. Res. 56:1503–1521. https://doi.org/10.1051/ro/2022065

Park, W., & Kim. S-G. 2022Integrating quantitative and qualitative methodologies to build a national R&D plan using data envelopment analysis based on R&D stakeholders’ perspectives. PLoS ONE. 17(3):0265058https://doi.org/10.1371/journal.pone.0265058

Pamučar, D., Žižović, M., Biswas, S., & Božanić, D. 2021A new Logarithm Methodology of additive weights (LMAW) for multi-criteria decision-making: application in logistics. Facta Universitatis Series: Mechanical Engineering. 19(3):Special Issue: 361-380.https://doi.org/10.22190/FUME210214031P

Pendharkar, PC 2021Hybrid radial basis function DEA and its applications to regression, segmentation and cluster analysis problems. Machine Learning with Applications. 6:100092https://doi.org/10.1016/j.mlwa.2021.100092

Podinovski, V.V., & Bouzdine-Chameeva, T. 2021Optimal solutions of multiplier DEA models. J Prod Anal. 56:45–68. https://doi.org/10.1007/s11123-021-00610-3

Popović, G., Pucar, Đ., & Florentin Smarandache, F. 2022Merec-Cobra Approach In E-Commerce Development Strategy Selection. Journal of Process Management and New Technologies. 1034:66–74

Radonjić, Lj. 2020Comparative Analysis of the Regional Efficiency in Serbia: DEA Approach Comparative Analysis of the Regional Efficiency in Serbia: DEA Approach. Indistrija. 48(2):1–19. https://doi.org/DOI: 10.5937/industrija48-24343

Rani, P, Mishra, A. R., Saha, A., Hezam, I.M., Pamucar, D. 2022Fermatean fuzzy Heronian mean operators and MEREC-based additive ratio assessment method: An application to food waste treatment technology selection. Int J Intell Syst. 37:2612–2647. https://doi.org/10.1002/int.22787

Rasoulzadeh, M., Edalatpanah, S. A., Fallah, M., & Najafi, S. E. 2022A multi-objective approach based on Markowitz and DEA cross-efficiency models for the intuitionistic fuzzy portfolio selection problem. Decision Making: Applications in Management and Engineering. 5(2):241–259. https://doi.org/10.31181/dmame0324062022

Rostamzadeh, R., Akbarian, O., Banaitis, A., & Soltani, Z. 2021Application of DEA in benchmarking: a systematic literature review from 2003–2020. Technological and Economic Development of Economy. 27(1):175–222. https://doi.org/10.3846/tede.2021.13406

Sala-Garrido, R., Mocholí-Arce, M., Maziotis, A., & Molinos-Senante, M. 2023Benchmarking theperformance of water companies for regulatory purposes to improve its sustainability. npj Clean Water. 61:2023https://doi.org/10.1038/s41545-022-00218-6

Stević, Ž., Miškić, S., Vojinović, D., Huskanović, E., Stanković, M., & Pamučar, D. 2022Development of a Model for Evaluating the Efficiency of Transport Companies: PCA–DEA–MCDM Model. Axioms. 11:140https://doi.org/10.3390/axioms11030140

Stojanović, I. ., Puška, A. ., & Selaković, M. 2022A Multi-Criteria Approach To The Comparative Analysis Of The Global Innovation Index On The Example Of The Western Balkan Countries. Economics - Innovative And Economics Research JournaL. 10(2)https://doi.org/10.2478/eoik-2022-0019

Toslak, M., Aktürk, B., & Ulutaş, A. 2022MEREC ve WEDBA Yöntemleri ile Bir Lojistik Firmasının Yıllara Göre Performansının Değerlendirilmesi. Avrupa Bilim ve Teknoloji Dergisi. (33):363–372

Tone, K. 2002A slacks-based measure of super-efficiency in data envelopment analysis. European Journal of Operational Research. 143:32–41

Tsai, Chi-Mao, Lee, Hsuan-Shih, & Gan, Guo-Ya 2021A New Fuzzy DEA Model for Solving the MCDM Problems in Supplier Selection. Journal of Marine Science and Technology :. 29(1):7https://doi.org/DOI: 10.51400/2709-6998.1006

Vojteški Kljenak, D., & Lukić, R. 2022Evaluation of the efficiency of providers of financial leasing in Serbia. Glasnik društvenih nauka - Journal of Social Sciences. 14:113–144

Zhu, N., & He, K. 2023The efficiency of major industrial enterprises in sichuan province of china: a super slacks-based measure analysis. Journal of Industrial and Management Optimization. 19(2):1328–1349. https://doi.org/10.3934/jimo.2021231

This display is generated from NISO JATS XML with jats-html.xsl. The XSLT engine is libxslt.

Login and registration

SKEI–MEĐUNARODNI INTERDISCIPLINARNI ČASOPIS, Vol. 4 No. 1, 2023.

Abstract

Keywords

Hrčak ID:

URI

Publication date:

Article Information (continued)

PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD

Abstract

PERFORMANCE ANALYSIS OF COMPANIES IN SERBIA BASED ON THE LMAW-DNMA METHOD

Notes

References