Examples
Examples
Try the starting example
- Relative criterion weights
- 1,1
- Criterion directions, comma-separated benefit or cost
- benefit,cost
- Options: name, score for each criterion
- A,8,4 B,6,1
- Weighted score by option
- A: 2; B: 2.5
- Signed criterion contributions by option
- A: 4, -2; B: 3, -0.5
- Highest-scoring option(s)
- B
- Normalised criterion weights
- 0.5, 0.5
Try another scenario
- Relative criterion weights
- 3,1
- Criterion directions, comma-separated benefit or cost
- benefit,cost
- Options: name, score for each criterion
- A,8,4 B,6,1
- Weighted score by option
- A: 5; B: 4.25
- Signed criterion contributions by option
- A: 6, -1; B: 4.5, -0.25
- Highest-scoring option(s)
- A
- Normalised criterion weights
- 0.75, 0.25
Calculation method
Calculation method
Weighted score by option
Normalise supplied weights to sum to one and sum signed weighted scores. Cost criteria receive a minus sign.
Signed criterion contributions by option
Show each signed score×normalised-weight contribution in criterion order.
Highest-scoring option(s)
Select all exact maximum-score ties.
Normalised criterion weights
Divide each non-negative weight by the positive total, scaling first to avoid overflow.
Symbols and units
- a
- Relative criterion weights
- b
- Criterion directions, comma-separated benefit or cost
- c
- Options: name, score for each criterion
Use the units shown. A list keeps the order in which you enter its values. The symbol ^ means “raised to the power of”.
Assumptions & limits
Assumptions & limits
- Uses scores you have already placed on commensurate scales. It does not normalise physical units or recommend weights. For raw metrics with explicit bounds and missing values, use the vendor scorecard tool.
Are these inputs private?
These calculations run in your browser. A shared link contains the values you choose to share. Only questions submitted to the separate AI finder are sent to OpenAI.
Further reading
AHRQ: weighted decision matrices ↗
Background reading; this does not imply endorsement or independent review of SumFizz.