Nolberto Munier

Universitat Politècnica de València | UPV · Institute for the Management and Innovation of Knowledge (INGENIO)

# 102

Dear Tran Van Dua

I read your article:

Development of a new multi-criteria decisionmaking method

My comments:

1- In the abstract you say: “That difference is reflected in the fact that when applying this method, the decision maker does not need to normalize the data nor determine the weights for the criteria”

Effectively, since everything is reduced to three integers 1, 0, -1, it is obvious that you don’t need normalization, since they are no units of measure.

However, you give the same number to a difference of say 3 and 8 than another between 0.5 and 4500. I don’t think that this is correct.

2- You say “In each example, the result of ranking the alternatives using the CURLI-2 method has been compared with those using other different MCDM methods.”

This comparison is irrelevant, it does not have any meaning and there it could also be due to coincidence

3-“The best alternative determined when using the CURLI-2 method always coincides with the use of existing MCDM methods”

This sounds strange, because this normally does not happen with other methods, when different MCDM methods, addressing the same problem, yield different results, including the best alternative, and you state it explicitly. I don’t understand why CURLI-2 is the exception, although could be, if you explain its algorithm.

4- In page 1 “Thus, it can be seen that when using the method of group four, the decision maker will eliminate the difficulties in data normalization as well as determining the weights for the criteria”

Normally, you may eliminate normalization, but not criteria weighting because that means that all criteria have the same importance, and in general each one has a different importance.

5- In page 3 “The result of ranking the alternative done by this method will be used to compare to the ranking result done by CURLI-2 method”

And what these comparisons prove? Nothing

6- In page 4 “Add the scoring matrix for each criterion”

In my opinion, computing each criterion independently and further adding up results is incorrect. Why?

Because the decision matrix represents a system where everything is related to something else. Therefore, you can have criterion C6 that receives input from criterion C2. How do you compute the contribution of C2 on C6?

I hope that these comments can be of help

Nolberto Munier

# 101

Dear Nik Muhammad Farhan Hakim NikKu; Muhammad Naim Ku Khalif; Nor Izzati Jaini

I read your paper

Analytic Hierarchy Process based on the magnitude of z-numbers

My comments:

1- What is Z-numbers? You don’t explain

2- In the aabstract you ay “The integration of the AHP with fuzzy Z”

Did you know that Saaty, creator of the AHP, said that fuzzy should not be used in AHP, because it is already fuzzy?

3- “Judgment is followed by a degree of certainty or sureness”

Where did you get this from? A judgement is never 100 % reliable

4- “Most of the existing decision-making models based on Z-numbers transform the Z-numbers into regular fuzzy numbers by integrating the reliability parts into the restriction parts, causing a significant loss of information”

Could you demonstrate this assertion?

5- “The Analytical Hierarchy Process (AHP) is one of the most powerful of these methods”

As a matter of fact, it is the opposite. It is one of the most elemental of MCDM methods, only good for simple and trivial problems, since it is unable to solve medium complex problems., because its lineal hierarchically structure

6- “Construct the pairwise comparison matrices to represent the decision maker’s preferences on the restriction and reliability of each criterion”

And what happens if another DM thinks differently?

7- In addition of what Saaty said, where is the logic in using fuzzy to refine invented values?

8- Page 8. A re you sure that in Figure 3 all criteria are independent as requiredby AHP?

Don’t you think that a criterion may be affected by another?

9- Page 13 “In fact, the ranking of alternatives will not be affected as much when a sensitivity analysis is performed and consistent criteria weights are obtained”.

Sensitivity analysis is not related to consistent criteria weights. It is related with the degree or range a criterion can change without altering a solution. By the way, criteria weights do not define alternatives ranking; this is reserved to objective weights

10- “C3 and C4 were increased by 40%,”

And how do you know that you can increase those criteria in a 40%? To do than you need to

know the allowable range of variation of each criterion and you don’t have that in AHP, and by the way, both variations must be considered not separately, but jointly

I hope that these comments may help you.

Nolberto Munier

Dear Ahmad Fairuz, Liane Okdinawati, and Adirizal Niza

I have read your paper

AHP Application to Select Logistical Location in Upstream Oil and Gas Operation: A Case Study

My comments

1.- In the abstract you refer to three criteria, when in reality you are considering five. However, in my opinion, these are not near enough criteria to use in a project of this magnitude.

For instance, I think that you need to consider also distances, and in risk, many different cases like personal, equipment failure, fatalities, damages by storms, potential blackout because failures of electrical generating equipment on board of platform. What about emergencies and potential evacuations, shortage of spare parts, for pumps and drilling, etc.?

Even when you present a very good collection of valuable opinions from experts regarding criteria, I believe that they are incomplete.

Do you have contingency and remediation plan?

2- In page 1 you say “To reduce the complexity, the Analytical Hierarchy Process (AHP) is used in this study as part of Multi-Criteria Decision Making (MCDM) that can break down the problem into a hierarchy and provide the weight of each element which will result in one best option as a business solution”

You can break a problem to study it in more detail, but not to solve it, because normally, all aspects of the problem are related. For instance, you can have a very ill person on the platform who needs to transported to a hospital, and you need to coordinate many things that link these two issues, the ill guy, the transportation to a hospital and the treatment.

You can plan and study the health problem on a platform and take all the necessary measures, and also analyze independently the general transportation problem, but it is evident that the health problem on the platform may be related with transportation. Consequently, you cannot make a pair-wise comparison between health and transportation criteria and determine which is more important, let alone, in what degree, because health has a component of transportation, and both are complementary. How do you evaluate the mutual contribution?

Because of this, this scenario can be solved by MCDM method, but not using AHP or using the weights its generate.

You agree with this when you say “This will involve the use of specialized transport equipment and material storage in strategic locations, as well as the coordination of complex supply chains involving multiple related stakeholders”.

Therefore, why do you use a MCDM method that does not consider dependency between criteria, but the opposite? It is not an AHP fault, because its structure if for other kind of problems, but it is on the people that use it incorrectly, which, in my opinion, is your case.

Chang et al, that you mention, are by far more realistic that the others experts that are happy with only 4 or 5 criteria

3- In page 3 you say “AHP is one of the MCDM methods found by Thomas Saaty, which is useful for organizing complex problem”

This is incorrect. AHP is unable to deal with complex problems because its hierarchical lineal structure, that is not followed by real-life problems. Today problems have many elements interlinked, in some sort of a network, instead of a lineal vertical relationship.

4- In page 3 “AHP breaks down the problem into a hierarchy, which helps simplify its complexity and displays the connections between various objectives (or criteria) and potential alternatives”

Not really. By breaking a problem, you certainly can better understand it and simplify your comprehension, but the problem is not altered by that. It remains the same.

Just take a car as example; you can break it is engine, body, transmission, etc. to study each separately, but you cannot improve the engine if you do not consider the other parts that are intimately related to it, like power transmission needed to the wheels, type of tires, body weight, body aerodynamics, electrical system, etc. This is a system, and you cannot break it, the same in MCDM problems, they are normally systems, and must be solved as a whole.

5- The AHP method arbitrarily estimates the trade-offs of criteria or objectives, and assumes (Saaty words), that they are equivalent to weights. In addition, since these weights were conceived WITHOUT considering the alternatives, they do not play any role in selecting alternatives. This is not only my opinion but comes from the Shannon Theorem

6- In page 3 “judgment is consistent and does not cause bias in the result”

You forgot to say that if is not consistent, it is forced to be, using a formula.

In addition, even if there is consistency, why is it assumed that what is in the mind of as person is applied to reality?

I hope these comments may help you

Nolberto Munier

Dear Ram Kumar Dhurkari

I have read your paper

MCDM methods: Practical difficulties and future directions for improvement

My comments:

1- In page 1, you say“The paper also emphasizes why a benchmark decision situation is essentialin assessing the capabilities of any multi-criteria decision-making method”.

In my opinion, it is impossible to have a benchmark decision situation. To do that you need a certain result to compare your results to, and you don’t have it. If you had, you wouldn’t need MCDM!

I also believe that the capability of a MCDM method is not related with accuracy in modelling the human decision-making process. What you need, first of all, is to model accurately the problem, that is, reproduce in a matrix all its characteristics. If you don’t have it, it does not matter the accuracy of the DM, because results will be based on incomplete information, derived from his personal estimates.

2- In page 1 “However, if the prescriptions of multi-criteria decisionmaking method do not resemble actual or real decision of the very same decision-maker, then multicriteria decision-making method failed in either capturing the true preferences of the decision-maker or in aggregating these preferences as per the expectations of the decision-maker”

It is difficult to understand your sentence due to the use of the word ‘prescription’. What do you intend to say with that? Do you mean a result using MCDM?

Why the method has to capture the preferences of the DM? You cannot solve a problem, other than a personal or trivial one, by preferences. You can incorporate some justified preferences, and the method must consider them, but it does not mean that the result must adjust to those preferences.

Why?

Because there are many relationships that can offset this preference in one criterion relative to others. For instance, you can establish in the initial matrix that criterion ‘cost’ has a preference value of 8, out of 10, and criterion contamination a maximum limit of limit of CO2 of 45ppm.

The method has to consider that, and may find that with that cost it is impossible to have a contamination of 45 ppm, and then, the problem is not feasible.

And how do you determine the ‘actual or real decision of the very same decision-maker’?

On what basis? Using what procedure?

3- “The multi-criteria discrete alternative problem and the multicriteria optimization problem”

Normally, it does not exist a multicriteria optimization problem, because you cannot have the highest benefit and the lowest cost at the same time; they are opposite. MCDM problems aim at finding a compromise or balanced solution, not an optimal one

4- What do you mean by “feasible alternatives”? If you consider them is because they are feasible.

What may be unfeasible is the problem as a whole, as exemplified above.

5- “The decision-making process relies on the DM’s judgment on the objective values of the alternatives”

I don’t see how the DM may judge about the cost to build a building for instance, something that was computed by engineers and financial studies. The DM only may judge on the relative value of each criterion, and, in my opinion, it could be very arbitrary.

6- Page 2 “however, it is likely that the prescribed decision is optimal but may be far from reality.”

Again, there is not an optimal decision, except if you use Linear Programming and with only one objective, which is not our case.

7- In page 2 “The foremost objective of MCDA is to reduce the complexity of the MCD problem by breaking it into multiple and single-criterion problems”

This is NOT the main objective of MCDM.

It is to find the best alternative satisfying all criteria as best as possible. It has nothing to do with complexity. It applies the same to a problem of 3 alternatives and 6 criteria, that to one with hundreds of alternatives and criteria. This is not complexity.

Most probably you took this concept from AHP, and it is false, according to Systems Theory, common sense and many researchers. You can’t partition a problem, solve each part independently and that add-up results. The total is not always equal to the sum of the parts, at least in MCDM.

As in the human body, there could be a disease but you cannot cure it if you don’t also find and treat its cause

8- “Therefore, it is highly desirable that the MCDM method must not exceed the capabilities of the human information processing system”

If this were true, mankind never would have reached the Moon.

What are the computers for? The trick is that the DM must know what to input in the computer, using a rational algorithm, and let the software make the computations. The DM is totally responsible and fundamental in both ends of the process:

1) Furnishing correct data, and

2) 2) Analysing results. not for computations.

It is impossible to perform and combine thousands of operations. The DM must not interfere in the processing of the data. What he MUST do, is analyze the result, and there, he can modify data in accordance with his experience and know-how, not by intuition or feeling

9- In page 2 “Similarly, very few studies have used any MCDM method for rank order calculation in an informed multi-criteria decision situation”

You are ill informed, since there are thousands of articles solving this kind of problems since the 80s. Your comparison with AHP is invalid, because it was not designed for problems with criteria interrelations

10- Page 3 “They compared the rank order generated before and after adding a new alternative into the problem”

What you mention is a phenomenon called ‘Rank Reversal’, probably the most analyzed problem in MCDM, still unsolved, and that was discovered by Belton and Gear in the 80s.

11- Page 3 “The actual decision can be arrived at without using any MCDM method”

Wrong, normally you can’t, because an alternative does not have the best value in all criteria

12- In page 3 “This is because as the size increases, the cognitive burden on the DM to remain consistent in judgment and decision-making also increases”

It appears that you refer everything to the AHP procedure where you need consistency of the DM estimates, but 99% of MCDM methods don’t use this approach, and they do not need to keep any consistency

Complex problems involve more issues than number of elements and they need to be solved using multiple relationships, something that is not allowed in AHP. Apparently, you ignore the realities of AHP, that is only good for trivial problems. The reason?

13- Page 5 “However, if the customer finds brand B more attractive, it is likely that the MCDM method failed to either capture the true preferences of the DM or process them as per the expectations of the DM (the customer in this case).”

I don’t share this opinion. The failure is not attributable to the method, but to the client, since he did not input his preference in the decision matrix. Consequently, the method assumed that there are not preferences, and evaluated alternatives using the other criteria

14- In page 5. “The complexity does not end here. Suppose the customer notices another brand D that is different from brands A, B, and C. On comparing the features of brand D, the customer finds brand C as the most attractive option. It is paradoxical”.

No, it is not paradoxical. I have studied it, and in my reasoning, it is rational, because by introducing a new alternative the whole problem is changed from three dimensions or three alternatives problem, to one of four dimensions or four alternatives problem. This change can modify everything or not.

“How the introduction of a new and a different alternative can cause rank reversal?”

Find my answer above.

“Surprisingly, many studies have reported such rank reversal phenomena [12, 31, 97, 98, 108]. To understand and explain such phenomena, it is necessary that the MCDM methods connect the objective measures of alternatives on various attributes to the observed choices. Various descriptive theories of decision-making, primarily from the fields of economics and psychology, can be used to understand the choice behavior of individuals.”

What do you mean by ‘connect’? The original objective values do not change, unless the DM change them, but it is the matrix which is spatially changed by adding a new alternative. Please leave psychology out of this, we are talking mathematics, and most especially dimensional geometric spaces. The number of these spaces is equal to the number of alternatives. In my hypothesis, rank reversal may occur when the slope of the hyperplane corresponding to the alternatives, changes in such extend, that it is no longer tangents the polytope that contains all feasible solutions. This is linear algebra, not my invention.

15- In page 6 “Valuation involves elicitation of preferences from the DM for the criteria weight and on the performance of alternatives on various criteria”

If you use subjective weights, coming from the DM intuition, this is not evaluation but invented values, and that everybody can refute or change

16- On page 7, it is evident that you equal criteria to attributes. Criteria are the conditions that must be satisfied by the alternatives, while attributes are the characteristic of the data within each criterion. Thus, attributes may be: positive or negative, integer or decimal, formulas, degree of dispersion of values, etc. Objective weights like those obtained by entropy, determine the weight of each criterion regarding the dispersion of its values. (Shannon, Theorem)

17- In page 7 “The problem formulation is important because, when the axiomatic rules or the principles of the MCDM method are not attuned to the DM’s psychology, the prescriptions will diverge.”

From where did you get this fantastic assertion?

18- In page 9 “In addition, there is also a lack of work describing the means to verify the potential of an MCDM method using simple decision-making problems where the DM can make decisions with relative ease and without using any MCDM method.”

Did you realize that this is the second or third time you express the same concept?

19- “The philosophy of MCDM methods is to split the MCDM problem into multiple single-criterion problems”

I already expressed my opinion and reasons on this wrong concept. Suppose you have alternatives A, B and C that are evaluated by criteria C1 and C2. What happens if there is a cause-and-effect relationship between C1 and C2? For instance, in a mountain road C1 is speed and C2 is snow. During an intense snowfall, the snow makes mandatory to reduce speed for alternative A and perhaps B. How then, can you evaluate alternative A by C1 and later by C2? Where do you consider the influence of C2 on C1?

20- On page 10 “Many of the extant MCDM methods have normative foundations leading to rational decision-making, which often differs from the actual decision. Theories that have evolved from the field of psychology and behavioral sciences can explain these departures. Recent developments propose new models and concepts that can better explain the decision-making”

Therefore, according to your own words, only normative methods, not precisely AHP and ANP, are rational. And this is true.

It is irrational to think that what is in the DMs’ mind can be applied to real-life. It means that if the same problem is solved by two different DMs, reaching different results, then, there could be TWO real-worlds Please, think about this.

I hope my comments may help you

Nolberto Munier

Dear Marco Cinelli , Peter Burgherr , Miłosz Kadzinski , Roman Słowinski

I have read your paper

Proper and improper uses of MCDA methods in energy systems analysis

My comments

1- In the abstract you say “lead Decision Makers in shaping the energy systems of the future”

Sorry, but I disagree. As far as I know no MCDM method, except Linear Programming (LP), can handle it. Why?

Because analysis of energy systems involves aspects like contamination, installation costs, variable demand, factor load, replacement time, construction time, new technologies, peak loads, global warming, sun radiation, maintenance costs, final disposal cost (fundamental in nuclear systems and wind blades), material reuse, wild life impact, simultaneous use of wind and PV (photovoltaic cells) installations, wind losses in parallel wind installations, etc., and fundamentally, all of them interconnected, something that is alien to all MCDM, expect LP.

In addition, it is necessary to consider dates as far as 2035, 2050 and 2075, and the energy installations that must last for decades, as well at the advent of hydrogen cells plants (until now, only to 1 MW) in portable units (Ballard, Canada), as well as nuclear fusion plants (D-T), working with hydrogen and lithium (INTER project, in South France).

We also need to consider plants operated by ocean waves movement, some of them already working, as in Brazil.

2- In my opinion weights must not be used. How do you rate the relative importance or utility of wind turbines and PVs? On what basis?

3- Page 1 you say “The energy systems analysis community has shown considerable advancements in the last decades in terms of approaches and strategies for assessing these systems”

Sorry, I cannot support this assertion. What they did is to treat problems with different menthols, considering in each one a total independency of alternatives and not taken into account that the whole energy system is a SYSTEM, and as such, it must be considered holistically, and in addition, they are using invented subjective weights to quantify criteria.

Where is the advance since the 80s?

4- In page 1 “the fit between the types of DMPs and the suitability of the used MCDA methods has been rarely verified”

This is undoubtedly true. It can’t be verified because none of them give information on the extent or range in which each objective is satisfied. Then don’t even demonstrate that the problem is feasible, and they assume that it is, without any proof.

Your box 2.4 in Figure 1 is fundamental. The procedure normally followed at present is that if some characteristic of a problem can’t be modelled, it is easier just to ignore it. For instance, how are at present considered the construction of energy plants for say in 2035? That is, how a precedence or continuity of actual plants is taken into account? Will they continue in that future or will be shut down?

How energy decarbonization is assured? Replaced by what, and on what reasons?

How do they consider that PV installations cannot work the whole day, but that a solar thermal plant may continue working long hours after the sunset?

It appears that the trend is to concentrate in mathematics rather than in reality.

5- In page 2 “The MCDA-MSS is freely accessible software that provides a structured and traceable path for the identification of the MCDA methods most suitable to a specific DMP, applicable to both new (prospective) and published (retrospective) case studies. The upgrade consisted in formulating the guidelines to be respected when choosing an MCDA method”

Do you see? The main problem which is MODELING REALITY, is not even mentioned

6- In page 8 you refer about guidelines for DM and they are indeed useful to select a method.

Don’t you think that the best and unique guideline could be ‘Select the MCDM method that best models all characteristics of a problem’?

7- In page 8 “In case the answer is “Yes” to the question “Does the MCDA method support this(these) missed feature(s)?”, it implies that the MCDA method chosen by the authors of the publication supports the missed feature(s), which leads to outcome 4 in Fig. 1. This implies that the developers of the MCDA-MSS can update its database, re-run the software and obtain outcome 1”

In my opinion, this must be the first stepin the selection of a MCDM method. Once you know the alternatives, and all the characteristics of the problem, expressed by the responsible of e ach area, the DM can define the corresponding criteria and be in a position to see which method fits them the best. Then, going back to the responsibles of each area and consult them about the whole scheme and getting their approval. Normally this people are very knowledgeable in their respective areas and completely ignorant, and not interested in the methods to be used, let alone in their mathematics.

8- In page 8 “Importance coefficients weights express the intrinsic importance of each criterion, meaning their voting power”

Subjective criteria weights are trade-offs that don’t have any voting power, because they are not related to the alternatives they should evaluate. Different is the case of objective criteria weights from entropy, CRITIC or standard deviation.

9- In page 9 “The formulation of every DMP requires selecting the type of decision recommendation the stakeholders would like to receive”

This makes a lot of sense but is difficult in practice. A production engineer may need a costly equipment that the financial officer does not want to buy. The only solution is a compromise solution where each part cedes something, but for that, these two stakeholders must be linked, something that does not happen in MCDM methods.

10- In my opinion, there are three expressions that should be banned in MCDM. They are subjective weights , preferences, and pair-wise comparison. They do not have room in real-life scenarios, unless they refer to trivial and personal scenarios like selecting a movie, choosing a mode to travel, or picking a restaurant for dinner.

We have to work with facts, with reasoned assumptions, with research and with information, not based on intuitions, pair-wise comparisons or using a MCDM method because it is popular’

Of course, there are subjective issues, that can be described by surveys and by using a simple scale for criteria considered independently.

Participation and opinion of the DM is absolutely necessary, utterly important and essential.

But there must be a symbiosis between the mathematics of a method’s result and the DM. For this reason, it is not advisable that the DM modifies, according to his/her idea or opinion the initial data.

Once the result is achieved by any method, not using wrights and preferences, the DM is the person to analyze the result, make whatever changes in the initial matrix according to his judgement, (not preferences), and even reject the result. He may decide selecting the second-best alternative instead of the best, according to his interpretation of result and sensitivity analysis, analyzing aspects that can vary and change the result, etc.

11- In page 11 “The research we propose in this paper shows an interesting link with what Robyn Dawes did in the late 1970s’, when he studied the proper and improper strategies to develop (linear) psychological models”

Not in my opinion, psychology is not related to MCDM

The article puts emphasis in weights. Naturally, not all criteria have the same importance and this is a fact that must be considered. As an example, Linear Programming does not use weights, however, the significance of each criterion is analyzed and modified at each iteration (and there could be thousands in a complex problem), and is an essential part in the method.

12- In page 12 “This research points out the need to stress that MCDA methods have their own implementation checklists, which can vary notably from one method to another’

Possibly this is true, but what happened when there is no method that is able to manage the problem?

The reason? Its inability to model all characteristics of the problem.

What I can assure you because I proved it, is that a method based on Linear Programming may address the very difficult problem of energy analysis.

13- In page 11 “This paper presents the first systematic assessment of the suitability of using MCDA methods in a representative set of real-world case studies concerning energy systems analysis”

I am afraid that this assertion in inexact. There is a paper published by Springer as a pre-print months ago, that address extensively this subject. Its title is:

These are my comments. I will be more than glad to discuss this problem in depth with my colleagues of Poland, either in RG or using my email

Hope these comments may be useful

Nolberto Munier

Dear Sandile Thamie Mhlanga and Manoj Lall

I have read your paper

Influence of Normalization Techniques on Multicriteria Decision-making Methods

My comments:

1- In page 4 you say “The AHP method is used to solve complex decisions by arranging the alternatives into hierarchical form”

Precisely, due to that AHP works with a lineal hierarchy and thus, without any transversal and down-bottom-up links, it is not suitable to solve complex problems. The method was conceived to work with projects that follow the top-down military lineal approach, and at the time it was developed, it was ‘discovered’ by companies working in that mode since centuries, and hence its success.

But that happened in the 70s, more than 50 years ago, when companies’ structures changed due to the necessity to incorporate multiple interrelations, and adopting another type of organizational structure, pressured by social and environmental organizations. You can read this in any book on industrial organization, and gradually, the AHP method ceased to represent reality.

It is not coincidence that years later Saaty developed ANP, which working with a network, is able to address medium complex problems. Therefore, this inability to solved complex scenarios is not a failure of the AHP method, simply because it was not conceived for that.

2. Page 4- “To solve complex decisions by means of the AHP method, the alternatives are arranged into hierarchical form”

I don’t think this is correct. The hierarchical structure starts with a main and unique objective, down to criteria and sub criteria, and further down to alternatives and sub alternatives.

3- In page 10 “The results obtained highlight the importance of normalization in the AHP-VIKOR approach. It is apparent that a applying a particular normalization technique may result in different outcomes”

This is your conclusion, but you did not need to perform this study to demonstrate it, since it is a very-well phenomenon in MCDM.

The causes for this discrepancy, as per my reasoning, is that the distances between alternatives are not proportional, and then, in a method like VIKOR or TOPSIS, that work based on distances, this is a fundamental reason for the discrepancy, and consequently, the different in rankings do not depend on the normalization method used, but in the MCDM method employed.

There is a tangible proof of this. If you solve a problem using Linear Programming (LP)/SIMUS method, all rankings are the same, irrelevant of the normalization employed, because LP does not work with distances, with the possible exception of using max-min, and in some problems.

Therefore, in my opinion, what would be a relevant progress is determining which normalization method is the most appropriate for each MCDM method.

Hope these comments may help you

Nolberto Munier

Dear Zaher Sepehrian , Sahar Khoshfetrat , and Said Ebad

I read your paper

Approach for Generating Weights Using the Pairwise Comparison Matrix

My comments:

1- In page 1, you say” Several methods have been proposed in AHP-related articles for the determination of local weights based on the pairwise comparison matrices [9–18]. Each of these methods has specific advantages and disadvantages, and thus, none of them can be considered the best”

I can’t speak about the several methods you mention because you do not enumerate them, but in principle, using pair-wise comparisons is a technique that has been considered arbitrary and of dubious reliance , and without any mathematical support since the 80s. For this reason, I don’t understand why many papers are published using that procedure without analyzing if it is worth its use.

You use DEA and I wonder, which is the importance in determining efficiencies when data is invented? Honestly, it is time wasted for me.

You can weight criteria subjectively, one by one, using a simple scale. Why to consider a pair that requires to put a value of dominance that nobody knows and that can change with different DM? Where is the logic? Different is if you evaluate subjectively each criterion independently, where it is possible to use preferences, but more important, employing reasoning, analysis, research and common sense.

If once you have finished with the pair-wise comparison and present your result to the stakeholders, how are you going to answer if a stakeholder asks for the origin of that comparison value?

You will say that it comes by intuition? Do you think that it is a valid answer?

Instead, if you evaluate each criterion separately, you have a lot to talk, explain and justify the value or utility you assigned to each criterion. Or even better, why don’t you use objective weights than can also incorporate the DM justified preferences?

2- In page 1 “Although DEAHP can generate true weights for consistent pairwise comparison matrices, it generates illogical and meaningless weights when it comes to inconsistent pairwise comparison matrices”

Can generate true weights? Could you tell me what is the theorem or axiom that support that?

3- In page 2 “When a decision criterion or alternative evaluates its best weight, it also evaluates other decision criteria or alternatives.”

In my humble opinion, this is incorrect. What AHP determines are not weights but trade-offs that are useless to evaluate alternatives; even Saaty said that this equivalence was only an assumption

The only weights than can evaluate alternatives are those from entropy and from standard deviation, two well-established mathematical concepts, with no relation to the DM estimates.

4- On page “analysis of the most undesirable weight,”

And how do you determine them?

5- In page 2 “The principal condition for the analysis of the most undesirable weight is that, in addition to the most desirable weight, the most undesirable weight can also be assigned to every decision criterion and alternative”

Not in my opinion. When you compare two criteria weights, you do not take into account that in general all criteria are related, and thus, individually a criterion may be unimportant per se, however, its influence on other criteria may be paramount.

For instance, you may have a problem where one criterion is contamination, and another criterion is cost. You can say that contamination has a very low weight, and thus, it is not significant, however, it couldn’t be negligible because the company invested a lot of money in installing cost equipment to avoid contamination, like in a coal-fired powerhouse in installing gas cleaning equipment. If the company allows for a little higher contamination, for sure, it will produce a decrease in equipment costs and perhaps in operating costs.

In this way cost are linked to environment and vice versa, and this is real-life, not a school blackboard example

By the way, do you realize that Saayy clearly said that AHP is only applicable when criteria are independent, or not related, and you igored it?

6- In page 6 you say that equations 11 and 13 are non-linear? If they are the result of the Eigen Value procedure, I believe they are.

7- I don’t have any opinion on your method; however, I believe that by using par-wise comparisons and the AHP, its basis is very weak, and barely credible.

I hope that these comments can help

Nolberto Munier

Dear Mahmut Baydas, Tevfik Eren, Željko Stević, Vitomir Starčevic

I read your paper

Proposal for an objective binary benchmarking framework that validates each other for comparing MCDM methods through data analytics

My comments

1- I am not sure that the title is correct since benchmark is defined by the Dictionary as “a standard or point of reference against which things may be compared or assessed”

If you compare two results, obtained analytically what is happening is that they are checking each other, but it does not imply that the coincident result is correct, regarding the real thing, although it speaks favourably of the method in comparison to others.

2- As I understand, ‘stock return’ is the “the positive or negative change in value of an investment or asset over time” (Money Sense Editors, February 27 2023).

As well, ‘financial performance’ is “A complete evaluation of a company's overall standing in categories such as assets, liabilities, equity, expenses, revenue, and overall profitability (CFI Team)”

These are criteria, evaluating 140 companies or alternatives. You want to demonstrate that both criteria validate each other, therefore, you are establishing that a correlation may quantify this relationship. In my opinion, the word ‘validate’ is incorrect. Correlation shows that both variables move in a large stent in the same sense in their ups and downs

, but this is not validation, because you are not comparing them with a known yardstick.

Then you use nine different MCDM methods, and what do you get out of that? Since all methods work with the same initial matrix, the existing relationship does not change, although what can change is the ranking of alternatives.

Therefore, what is the purpose of the article?

After that, you introduced the RR concept, which I don’t see its relationship with the former problem.

You say “ According to the findings obtained entirely through data analytics, Faire Un Choix Adéquat (FUCA) and (which is a fairly new method) the compromise ranking of alternatives from distance to ideal solution (CRADIS) were determined as the most appropriate methods by the joint agreement of both criteria”

Using FUCA and CRADIS may indicate what you say, but where is the proof?

3- In page 3 “Simply put, MCDM methods can be compared based on their ability to relate to real life.This brings to mind the naturally occurring sequences in real life”

This is a most important definition of MCDM methods.

4- I have only notions on financing, but in my understanding this sentence is incorrect “The share price is an example, and similar rankings can also be used in other scientific fields”

In MCDM we work with facts that derive from the scenarios, like calculated costs, estimated gains, wished ROE, estimated working capital, and all of them are related through the projected financial statements, etc., and are mostly constant, at least during a certain period, but the share price does not belong to this category, because it is highly dynamic, depends on the markets, social issues, wars, etc., on what we don’t have any control. I think I discussed this same issue with Mr. Baydas long time ago.

Page 3“MCDM inputs; a character analysis based on MCDM outputs can show us a clearer path. In this sense, “price”,

For ‘price’ in financing I understand that you refer to “the price for which the stock is purchased, and thus, becoming the new market price (Investopedia)”

In my opinion what you say is incorrect, for the price depends on thousands of people buying and selling. Of course, it is a part of real-life, but that we cannot control, like cost, working capital, expenses, etc., and it is not similar to performance, as you say, fundamentally because its intangibility (the purchaser is buying hope), and dynamicity.

Not surprising, you say the same, thus, how can you compare performance to price?

You say “Moreover, the level of this existing relationship varies according to the ability of MCDM methods”

Perhaps you should explain how.

Page 4 “In this study, an “output-based” solution obtained with “data analytics” is proposed as an alternative to a classical “input-based” methodological solution’

In this, I agree in a 100%

5- In page 5 you mention SWOT analysis on MCDM methods.

In general, what is made is the opposite, starting with a SWOT analysis that identifies different strategies, MCSDM selects the best of them

6- “For this reason, it has been suggested to apply more than one method to the same problem in order to give a more comprehensive result to the decision makers and it is still widely applied”

And what is it good for?

7- page 6- “On the other hand, compared to its competitors, AHP (Analytic Hierarchy Process) can produce consistency, time and energy problems as it makes many pairwise comparisons with subjective expert opinion”.

Energy problems are not based on opinions but in a set of conditions or criteria to be met like demand, cost, load factor, reliability, efficiency, equipment, atmospheric conditions, environment, health, new development, etc. Do you think that all of these criteria are subject opinions

8- RR is not due to normalization, but to passing from one dimensional space to another. That is, adding an alternative C to two alternatives A and B (in 2D,) transforms in in a different space (3D) and vice versa, according to my hypothesis

9- If we have to select a MCDM from the axiomatic point of view, probably none would be selected

The best MCDM method for a certain problem is which best can model all the characteristics of the problem.

10- In page 7 “In MCDM-based FP studies, there is generally a lack of objective justification for choosing and using an MCDM method”

Why? Can’t you establish a value for IRR, or NPV or Recovery time or whatever other financial index?

11- In page 8 you speak of measuring sensitivity to RR. It is za very interesting concept, and I will investigate it

12- In page 8 “It is a difficult and chronic problem to determine which of the MCDM methods is more suitable and which one should be chosen”

Again, it is no difficult. The only thing to do is to have all characteristics of the problem, and look for the MCDM that best adapt or can model them all. For instance, if you have exclusive alternatives, you must use binary performance values. Just look for the method that can handle them. For simple and personal problems, probably the best method is AHP , because it considers personal points of view, that not other method does.

These are my comments, hope they can help you

Nolberto Munier