WISP (Simple Weighted Sum Product Method)

WISP is a ranking method for when you hold a decision table filled with numbers and want to place the alternatives in a single order. Its output is a benefit score for each alternative and the ranking that follows from it; it does not sort alternatives into groups, and it does not produce criterion weights, taking them from outside. Stanujkić, Popović, Karabašević, Meidutė-Kavaliauskienė and Ulutaš proposed it in 2023; the method is quite new and its application literature is still limited, but it has already begun to appear in supplier-selection and alternative-evaluation studies.

The idea behind WISP is "do not rely on a single comparison logic." Comparing criteria by adding them (additive logic) and comparing them by multiplying them (multiplicative logic) can give different results for the same table, and which is "correct" is debatable. WISP calculates both, in both difference and ratio form, and averages the results of four distinct viewpoints: additive difference, multiplicative difference, additive ratio, multiplicative ratio. If an alternative performs well across all four viewpoints, the result rests not on a single formula but on the agreement of four distinct logics.

This idea carries a philosophical consequence: WISP is compensatory, allowing a weakness on one criterion to be papered over by strength on another, as TOPSIS and similar methods do. Unlike TOPSIS, though, WISP tests this compensation against four distinct arithmetic logics; if all four favour the same alternative, the result can be said not to depend on a single assumption (adding alone, or multiplying alone). If the four logics diverge, that is a sign the decision is fragile.

The method proceeds in four steps.

First, scale equalisation. Every column is divided by its own largest value; each column is thereby compressed into the 0-to-1 range, and criteria in different units become comparable.

Second, weighting. WISP multiplies each equalised column by its criterion's weight. The weights come from outside WISP itself; they must sum to 1.

Third, four benefit measures. WISP splits the weighted table into benefit criteria (higher is better) and cost criteria (lower is better). For each alternative it calculates four separate measures: the difference between the sum of benefits and the sum of costs, the difference between the product of benefits and the product of costs, the ratio of the sum of benefits to the sum of costs, and the ratio of the product of benefits to the product of costs.

Fourth, averaging. WISP scales each of the four measures, within itself, to a 0-to-1 range relative to the best alternative on that measure, then averages the four. This average is the final score; WISP ranks the alternatives from highest to lowest on it.

The formulas behind the steps are given on the DecisionMind method page; this card carries no formulas.

The final score states an alternative's average standing across four distinct comparison logics; nothing more. A score of 1 does not mean "perfect" but "the alternative all four logics find best in this set." The score is not a percentage and cannot be compared with a score from a different analysis, because the scaling is done relative to each analysis's own best value.

The four components underlying the score (additive difference, multiplicative difference, additive ratio, multiplicative ratio) should also be checked separately: if all four find the same alternative best, the result is reliable; if one points to a different alternative, the final average conceals this disagreement, and the report should state it.

Thus instead of writing:

"WISP found the best alternative"

the report should read:

"With these weights, the average of the four comparison logics favours this alternative; all four logics agree / do not agree on this being the best"

WISP works with crisp data: a single number per cell. DecisionMind holds four WISP family members alongside the base method (classical WISP together with fuzzy, neutrosophic and plithogenic extensions); which fits your data situation is explained on the relevant data-type cards.

You need alternatives in rows, criteria in columns, one number per cell, and no empty cells; direction information for every criterion; and criterion weights that sum to 1. WISP does not produce weights, it asks for them; you can derive them from expert opinion (AHP, BWM, SWARA) or from the data itself (Entropy, CRITIC). A minimum of two alternatives and two criteria is required; three to twelve criteria work comfortably. Take care that no cell in the table is zero: if a multiplicative measure is zeroed out, that logic drops out and the four-logic agreement falls to two.

WISP is a sound choice if your criteria can be measured numerically, your table has no gaps, and you accept compensation, while also not wanting to rely on a single arithmetic logic (adding alone or multiplying alone). Its typical fields are alternative selection and supplier evaluation.

It should not be used in these cases: where you will not compromise on one criterion (WISP is compensatory and does not screen out anything below a threshold); where your table has a zero or negative value (multiplicative measures break down, and the data must be transformed first); and where you need to explain how the method works to a decision-maker in a single simple story (summarising four separate logics is more complex than TOPSIS's single "closeness to the ideal" story).

A numerical table, compensation accepted, not wanting to rely on one logic → WISP

Same goal, but the data is fuzzy / neutrosophic / plithogenic → the relevant WISP extension

A simple, single-story explanation is needed → TOPSIS, SAW

No compromise allowed on one criterion, sub-threshold alternatives must be screened out → screening first, then ranking

Not a ranking but weights are needed → AHP, BWM, SWARA, CIMAS (subjective); Entropy, CRITIC (objective)

WISP's greatest strength is that it does not depend on a single arithmetic assumption: by using additive and multiplicative logics together, in both difference and ratio form, it offers four independent checkpoints. When all four favour the same alternative, this gives the decision-maker a stronger assurance than TOPSIS's or SAW's single formula. Its computational burden is small and its normalisation step is simple (dividing only by the column maximum). Despite being a new method, it has already been extended to neutrosophic, fuzzy and plithogenic settings within a short time, showing that its logic transfers to different data types (Stanujkić et al., 2022).

Its limitations stem largely from its still being a young method. First, classical WISP requires crisp data; it cannot capture uncertainty in expert judgement or disagreement between experts. This gap is the reason a neutrosophic extension was published one year after the method was proposed (Stanujkić, Karabašević, Popović, Smarandache, Stanimirović, Saračević and Katsikis, 2022). Second, when the four logics are averaged, each is given equal weight; where one logic (such as the multiplicative ratio) fits the decision-maker's intuition less well, this equal weighting can be contentious. Third, when the table has a value at or near zero, the multiplicative measures break down and the four-logic agreement effectively drops to two. Fourth, because the method was only proposed in 2023, independent studies of rank reversal or comparative performance have not matured to the level seen for TOPSIS or VIKOR; DecisionMind presents this card while stating openly that the existing literature is limited.

The most common mistake is marking a criterion's direction wrongly; if a cost criterion is marked "higher is better," the benefit and cost sums and products get added on the wrong side, and the ranking becomes meaningless.

A second mistake is reporting only the final average without ever checking the four intermediate measures (additive difference, multiplicative difference, additive ratio, multiplicative ratio); if the four disagree, this information is lost. A third mistake is leaving a zero value in the table; the multiplicative measures give unreliable results in that case. A fourth mistake is reading the final score as a percentage or a probability. A fifth is giving weights equal value without justification and presenting this as "neutrality."

The governing principle is this:

A WISP result is the average of four distinct comparison logics; if the logics disagree, the average alone is not a reliable summary, and the report must show this disagreement.