Analytic Hierarchy Process (AHP)
The Analytic Hierarchy Process is a multi-criteria decision-making method that derives priority weights for criteria and alternatives from pairwise comparison judgments, with a consistency check on those judgments.
계층분석법(AHP)은 쌍대비교 판단으로부터 기준과 대안의 우선순위 가중치를 도출하고 그 판단의 일관성을 점검하는 다기준 의사결정 방법입니다.
How do I derive importance weights for decision criteria from expert judgments?
전문가 판단으로 의사결정 기준의 중요도 가중치를 어떻게 도출하나요?
The Analytic Hierarchy Process structures a decision as a hierarchy of goal, criteria, and alternatives, then asks experts to compare elements in pairs on a ratio scale and converts those comparisons into priority weights. It fits decisions involving several partly subjective criteria, and judgments are usually considered acceptably consistent when the consistency ratio is 0.10 or less.
When to use Analytic Hierarchy Process (AHP)
- Weighting policy, site selection, or investment criteria from expert opinion
- A small number of criteria and alternatives that can be compared in pairs
- Combining judgments from several experts into group weights
When to use something else
- Alternatives are scored on measured data and only ranking is needed: use TOPSIS
- Criteria influence one another: use the Analytic Network Process
Assumptions and requirements
- Decision structured as a hierarchy of criteria and alternatives
- Pairwise comparisons on Saaty's 1-9 ratio scale
- Acceptably consistent judgments in each comparison matrix (conventionally a consistency ratio of 0.10 or less)
- Group judgments aggregated with the geometric mean
What the analysis reports
- Pairwise comparison matrices
- Local and global priority weights
- Maximum eigenvalue, consistency index, and consistency ratio
- Final ranking of alternatives
- Sensitivity analysis of weights
How to report it
AHP results indicated that [criterion] was the most important criterion (weight = [value]), and all comparison matrices were acceptably consistent (CR ≤ [value]).
Related methods
- TOPSIS
- Analytic Network Process
- Fuzzy AHP
Run Analytic Hierarchy Process (AHP) on Quorant
- Data you need
- a table (CSV or Excel) with predictor (feature) columns
- Price
- 150 credits for one analysis up to 10,000 rows (complexity level 1); larger or wider data costs more. Optional methodologist review: 900 credits.
- Checking
- Python results are cross-checked against R reference outputs in every deployment
- Before you pay
- A free pre-analysis diagnosis checks your data and gives an exact quote; nothing is deducted until you approve it.