登录查看更多内容

Last updated on 2024年7月30日

How do you compare and combine different types of criteria in multi-criteria decision making?

由人工智能和领英社区提供技术支持

Multi-criteria decision making (MCDM) is a process of evaluating and ranking alternatives based on multiple criteria that may have different units, scales, and preferences. MCDM can help you make better and more transparent decisions in complex and uncertain situations, such as choosing a project, a supplier, a location, or a policy. However, comparing and combining different types of criteria in MCDM can be challenging and require some steps and methods. In this article, we will explain how you can do that effectively and efficiently.

此文章中的业界达人

由社区从 6 条内容中精选。了解更多

1 Identify the criteria

The first step in MCDM is to identify the criteria that are relevant and important for your decision problem. Criteria are the attributes or factors that you use to measure the performance or value of the alternatives. They can be quantitative or qualitative, objective or subjective, and benefit or cost. You should select the criteria that reflect your goals, preferences, and stakeholders' interests, and avoid redundant, irrelevant, or conflicting criteria. You can use brainstorming, literature review, expert opinion, or other techniques to generate and select the criteria.

添加您的观点

Thomas Chappell

I help executives make better decisions and gain clarity in 90 days, avoiding loss of confidence, frustration, and turnover. My approach improves decision outcomes, morale, and focus. Ask about my 4Sight Matrix.
举报内容
Ever felt overwhelmed by too many choices? Welcome to the world of Multi-Criteria Decision Making (MCDM)! The magic starts with identifying your criteria—those golden factors that measure how well each option stacks up. Think of them as your decision-making superheroes: they can be quantitative or qualitative, objective or subjective, beneficial or costly. To find your dream team, consider your goals, preferences, and stakeholder interests. Avoid redundant or conflicting criteria by brainstorming, reviewing literature, or seeking expert opinions. Ready to make smarter, more confident decisions? Let’s dive in and discover the power of well-chosen criteria!

已翻译

赞
Dr. Erik Pohl

Data Scientist Operations Research and Decision Science
举报内容
Die englische Beschreibung ist soweit korrekt, allerdings werden die Methoden der MCDA genau dort verwendet, wo konfligierende Kriterien auftreten. Bei der Auswahl der Kriterien sollte unbedingt darauf geachtet werden, dass sie unabh?ngig voneinander sind. Es gibt aber auch MCDA-Methoden bei denen man die Abh?ngigkeiten zwischen Kriterien analysieren kann (z. B. PROMETHEE-GAIA).

已翻译

赞

2 Normalize the criteria

The second step in MCDM is to normalize the criteria to make them comparable and consistent. Normalization is a process of transforming the criteria values into a common scale, such as 0 to 1, or -1 to 1. Normalization can help you eliminate the effects of different units, scales, and ranges of the criteria, and make them easier to aggregate. You can use different methods of normalization, such as min-max, linear, vector, or goal programming, depending on the nature and distribution of the criteria.

添加您的观点

Dr. Erik Pohl

Data Scientist Operations Research and Decision Science
举报内容
Die Normalisierung der Kriterienauspr?gungen ist nicht unbedingt notwendig. Vielmehr ist der zweite Schritt abh?ngig von der gew?hlten MCDA-Methode.

已翻译

赞

3 Assign the weights

The third step in MCDM is to assign the weights to the criteria to reflect their relative importance or preference. Weights are numerical values that indicate how much each criterion matters for your decision. They can be subjective or objective, and derived from different sources, such as direct judgment, pairwise comparison, rating, ranking, trade-off analysis, or entropy. You should assign the weights carefully and consistently, and check for their sensitivity and robustness.

添加您的观点

Dr. Erik Pohl

Data Scientist Operations Research and Decision Science
举报内容
Die Beschreibung "Weights are numerical values that indicate how much each criterion matters for your decision." stimmt nur bedingt. Bei den sog. klassischen MCDA-Methoden (MAUT/MAVT etc.) müssen die Kriteriengewichte als Trade-Off-Faktor angesehen werden. Bei sog. Outranking-Verfahren k?nnen die Gewichte als "Wichtigkeit" interpretiert werden. Auch hier ist die Bedeutung abh?ngig von der gew?hlten Methode. Meiner Erfahrung mit Stakeholdern nach sind die SIMOS-Methode einfach anzuwenden im Bereich der Outranking-Verfahren zur Bestimmung von Kriteriengewichte.

已翻译

赞

4 Evaluate the alternatives

The fourth step in MCDM is to evaluate the alternatives based on the normalized criteria and the weights. Evaluation is a process of calculating the scores or values of the alternatives for each criterion and for the overall decision. Evaluation can help you rank the alternatives and identify the best or most preferred one. You can use different methods of evaluation, such as weighted sum, weighted product, TOPSIS, ELECTRE, PROMETHEE, or AHP, depending on the type and structure of the criteria and the decision problem.

添加您的观点

5 Analyze the results

The fifth step in MCDM is to analyze the results and validate your decision. Analysis is a process of examining and interpreting the scores, ranks, values, or preferences of the alternatives, and checking for their validity, reliability, and stability. Analysis can help you understand the trade-offs, conflicts, uncertainties, and sensitivities involved in your decision, and justify or revise it if needed. You can use different methods of analysis, such as sensitivity analysis, robustness analysis, scenario analysis, or group decision analysis, depending on the data and the context of your decision.

添加您的观点

Dr. Erik Pohl

Data Scientist Operations Research and Decision Science
举报内容
Eine sehr sinnvoll M?glichkeit der Analyse sind die Weight Stability Intervals: Sie zeigen den Bereich, in dem Kriteriengewichtungen ver?ndert werden kann, ohne dass sich die Rangfolge der Alternativen ?ndert. Dies kann als Ma? für die Robustheit des Ergebnisses verwedet werden.

已翻译

赞

6 Communicate the decision

The final step in MCDM is to communicate the decision and its rationale to the relevant stakeholders. Communication is a process of presenting and explaining the criteria, weights, methods, results, and implications of your decision, and soliciting feedback and acceptance from the stakeholders. Communication can help you enhance the transparency, credibility, and legitimacy of your decision, and facilitate its implementation and monitoring. You can use different tools of communication, such as tables, charts, graphs, maps, dashboards, or reports, depending on the audience and the purpose of your decision.

添加您的观点

7 Here’s what else to consider

This is a space to share examples, stories, or insights that don’t fit into any of the previous sections. What else would you like to add?

添加您的观点

Deborah Ribeiro

Founder and CEO of Zayon - the 1st Decision Intelligence company in Brazil | AI/ML product strategist | Digital transformation and Innovation Management specialist | Startup mentor
举报内容
The multi-criteria decision-making process, while structured, is also inherently complex and dynamic. Beyond the core steps of identifying criteria, normalization, weight assignment, evaluation, and analysis, several additional factors warrant consideration. These include addressing uncertainty and risk associated with criteria and alternatives, incorporating stakeholder preferences effectively, and managing potential biases that may influence the decision-making process. Sensitivity analysis can be employed to assess the robustness of the decision under varying conditions. Moreover, ethical considerations and long-term implications of the chosen alternative should be carefully evaluated to ensure responsible decision-making.

已翻译

赞

Decision Support

+ 关注

给文章评分

我们借助人工智能创建了此文章。您认为这篇文章怎么样？

很棒不太好

举报此文章

查看全部

How do you compare and combine different types of criteria in multi-criteria decision making?

1

2

3

4

5

6

7

1 Identify the criteria

2 Normalize the criteria

3 Assign the weights

4 Evaluate the alternatives

5 Analyze the results

6 Communicate the decision

7 Here’s what else to consider

Decision Support

给文章评分

感谢您的反馈

更多Decision Support相关文章

更多相关阅读内容