A differential evolution algorithm for finding the median ranking under the Kemeny axiomatic approach

D’Ambrosio, Antonio; Mazzeo, Giulio; Iorio, Carmela; Siciliano, Roberta

doi:10.1016/j.cor.2017.01.017

Cited by 32 publications

(19 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], the Kemeny's median is computed by the evolutionary algorithm. Genetic algorithm for the economical calculation of the Kemeny-Snell median is shown in paper [17]; it stresses that the algorithm is heuristic.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

The research of possibilities for fast calculation of median consensus rankings

Boltenkov

Kuvaieva

Galchonkov

et al. 2018

EEJET

View full text Add to dashboard Cite

Досліджено можливість швидкого обчислення колек тивних експертних оцінок медіанного типу. Незважаючи на широке застосування для розрахунку колективних екс пертних оцінок медіан КеменіСнелла і КукаСейфорда, недостатньо досліджені можливості скорочення часу обчислення медіанного консенсусного ранжирування шля хом застосуванням задачі про призначення і відомих алгоритмів її рішення. На відміну від більшості відомих методів пропонований в статті метод не є наближеним і зберігає вихідну медіанну аксіоматику Кемені. Досліджено можливість розрахунку медіан Кемені Снелла і КукаСейфорда із застосуванням задачі про призначення методами комп'ютерного експерименту. Оцінено час рахунку медіанних ранжирувань чотирма різними алгоритмами рішення задачі про призначення. Встановлено, що запропонованим методом при помір ній кількості альтернатив (n<50) медіанні ранжируван ня розраховуються в режимі часу, близькому до реально го. Показано також, що на відміну від інших методів час обчислення медіанних ранжирувань за допомогою задачі про призначення не залежить від ступеня узгодженості індивідуальних експертних ранжирувань. Отримані результати корисні для практичного засто сування дослідженої процедури в мережевих експертних системах. У таких системах час обчислення консенсус ного ранжирування має бути близьким до реального. Крім того, в мережевих системах експертизи за рахунок випад кового комплектування колективу експертів можливий низький рівень узгодженості індивідуальних ранжируван ня. Для дослідженої процедури це не впливає на трива лість розрахунку. Це дозволяє рекомендувати розробле ну обчислювальну процедуру швидкого пошуку медіанних консенсусних ранжирувань за КеменіСнеллом і Куком Сейфордом для практичного застосування в системах колективної мережевої експертизи Ключові слова: колективне експертне оцінювання, ме діанні консенсусні ранжирування, задача про призначення UDC 004.9

show abstract

Section: Literature Review and Problem Statementmentioning

confidence: 99%

The research of possibilities for fast calculation of median consensus rankings

Boltenkov

Kuvaieva

Galchonkov

et al. 2018

EEJET

View full text Add to dashboard Cite

show abstract

“…Here, we assume that the cluster center is the so-called consensus ranking, namely that ranking that best represents the consensus opinion of a sample of judges. Finding the consensus ranking is a separate topic and a very old (and a NP hard) problem (de Borda, 1781;Condorcet, 1785;Black et al, 1958;Emond and Mason, 2002;Ali and Meila, 2012;Aledo, Gámez and Molina, 2013;D'Ambrosio et al, 2017). Here we consider the consensus ranking that ordering that Kemeny and Snell (1962) defined as the median ranking, namely that ranking that minimizes the sum of the Kemeny distance between itself and the rankings expressed by a set of judges.…”

Section: K-median Cluster Component Analysismentioning

confidence: 99%

“…In our experience, 10 replications are enough to overcome the local optima problem. Furthermore, the rank aggregation problem can be extremely computationally expensive when the number of objects to be ranked increases (Ali and Meila, 2012;Aledo, Gámez and Molina, 2013;D'Ambrosio et al, 2017). For each trial the number of clusters was varied from 1 to 7.…”

Section: Simulation Studymentioning

confidence: 99%

“…Nevertheless, the searching space of the cluster centers for the CCA algorithm is not limited to the universe of full rankings. In finding the median ranking, the CCA algorithm uses the branch-and-bound algorithm designed by Emond and Mason (2002) if the number of items is less than 15, and the FAST heuristic algorithm or the Differential Evolution algorithm for consensus ranking detection (D'Ambrosio et al, 2017) if the number of items is less than 50 or larger than 50 respectively.…”

Section: Simulation Studymentioning

confidence: 99%

“…In following this approach, according to which the probability of each judge to belong to a given cluster is unequivocally related to the distance between himself and the cluster center, we use the Kemeny distance (Kemeny and Snell, 1962). This choice is due to the consideration that the Kemeny distance is defined in the space of both full and tied rankings, and that it is the unique distance measure defined on the extended permutation polytope, which is generally accepted as the geometrical space of preference rankings (Heiser and D'Ambrosio, 2013;D'Ambrosio et al, 2017). The remainder of the paper is organized as follows: Section 2 briefly introduces rank data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A distribution-free soft-clustering method for preference rankings

D’Ambrosio¹,

Heiser²

2018

Behaviormetrika

Self Cite

View full text Add to dashboard Cite

Typically, ranking data consist of a set of individuals, or judges, who have ordered a set of items-or objects-according to their overall preference or some prespecified criterion. When each judge has expressed his or her preferences according to his own best judgment, such data are characterized by systematic individual differences. In the literature several approaches have been proposed in order to decompose heterogeneous populations of judges into a defined number of homogeneous groups. Often, these approaches work by assuming that the ranking process is governed by some distance-based probability models. We use the flexible class of methods proposed by Ben-Israel and Iyigun, which consists in a probabilistic-distance clustering approach, and define the disparity between a ranking and the center of a cluster as the Kemeny distance. This class of methods allows for probabilistic allocation of cases to classes, thus being a form of soft or fuzzy, clustering. The allocation probability is unequivocally related to the chosen distance measure.

show abstract

An examination of scenarios to increase waterfowl hunting participation

Hinrichs,

Nawrocki,

Gruntorad

et al. 2023

Wildlife Society Bulletin

View full text Add to dashboard Cite

Since the 1970s, waterfowl hunting participation has declined in the United States, which has resulted in socioeconomic consequences for waterfowl conservation and management. Attempts to increase the waterfowl hunter population have been difficult, partly due to social factors (e.g., constraints, motivations, demographics) influencing who participates, frequency of participation, and diversity of desired outcomes from hunting experiences. We examined the preferences of 10 potential management options by hunters and anglers from several states in the central U.S. during 2018. Respondents were grouped into the following activity groups based on responses to survey questions: frequent waterfowl hunters, sporadic waterfowl hunters, previous waterfowl hunters, hunters (never hunted waterfowl), and nonhunters (anglers who have never hunted). All ordinal models indicated that the ability of the scenario to increase participation significantly (P < 0.05) depended on the activity group. Scenarios, including Having someone to take the respondent hunting (probability of increasing participation > 0.35 for all activity groups) and Special areas for new waterfowl hunters, had the greatest indication (probability > 0.40) of increased waterfowl hunting participation across activity groups. Frequent and sporadic waterfowl hunters ranked Special areas to allow for a quality hunt highest, while hunters and non‐hunters ranked Someone to take me hunting as the most preferred scenario. Information for what new/inexperienced hunters need, Classes or materials to teach waterfowl ID, and Ability to rent equipment were scenarios consistently ranked as the lowest for all activity groups. Our research underscores that only some of the scenarios had the same appeal to all activity groups, which implies a need for a greater diversity of experiences in the landscape of public waterfowl hunting access. Also, continued promotion of current waterfowl hunters taking new or inexperienced individuals may increase waterfowl hunting participation.

show abstract

A differential evolution algorithm for finding the median ranking under the Kemeny axiomatic approach

Cited by 32 publications

References 19 publications

The research of possibilities for fast calculation of median consensus rankings

The research of possibilities for fast calculation of median consensus rankings

A distribution-free soft-clustering method for preference rankings

An examination of scenarios to increase waterfowl hunting participation

Contact Info

Product

Resources

About