For the weighted sum algorithm to be valid,
Results Analytics
normalizes the objectives to bring them into the same range; otherwise, the
effect of each objective function is not represented equally.
The weighted sum ranking algorithm does the following to calculate the
overall score for each data point:
- The thresholds for each parameter are evaluated. If the priority of a
parameter is MH (Must Have), but its value falls outside the thresholds, the
data point is given a score of 0.0, regardless of the objective values.
- Results Analytics
calculates the raw object value for each parameter with an objective, using the
"higher" = "better" formulation:
- If the objective is to minimize a parameter,
- If the objective is to maximize a parameter,
- If the objective is a target value of a parameter,
- For each parameter that was chosen as an objective, the raw object
values are scaled to fall between 1 and 100. This is the scaled parameter
objective value.
- The scaled parameter objective values are multiplied by the final
weight factor. This is the scaled and weighted parameter objective value.
- For each data point,
Results Analytics
calculates the sum of the scaled and weighted objective values to get the
weighted sum. This is the raw score for the data point.
- Results Analytics
calculates the score by scaling the raw scores for all the data points to fall
between 1 and 100.
The overall score of each data point also
becomes the score of the top level parameter group.
- For each parameter group other than the top
level parameter group, the score is calculated as the sum of the scores of all
sub-groups and parameters.
Results Analytics
does not scale the group scores; it calculates the score from the sum of all
the child scores.