Annibal Parracho Sant'Anna

Data envelopment analysis of randomized ranks

Probabilities and odds, derived from vectors of ranks, are here compared as measures of efficiency of decision-making units (DMUs). These measures are computed with the goal of providing preliminary information before starting a Data Envelopment Analysis (DEA) or the application of any other evaluation or composition of preferences methodology. Preferences, quality and productivity evaluations are usually measured with errors or subject to influence of other random disturbances. Reducing evaluations to ranks and treating the ranks as estimates of location parameters of random variables, we are able to compute the probability of each DMU being classified as the best according to the consumption of each input and the production of each output. Employing the probabilities of being the best as efficiency measures, we stretch distances between the most efficient units. We combine these partial probabilities in a global efficiency score determined in terms of proximity to the efficiency frontier.

Probabilistic priority numbers for failure modes and effects analysis

Purpose – The purpose of this paper is to propose a method, derived from numerical evaluations on the criteria of security, frequency and detectability, of Failure Modes and Effects Analysis (FMEA), a probabilistic priority measure for potential failures; and to evaluate the use of this method when combined with subjective evaluations to decide on improvement actions.Design/methodology/approach – The method proposed is based on treating the numerical initial measurements as estimates of location parameters of probability distributions. This allows for objectively taking into account the uncertainty inherent in such measurements and to compute probabilities of each potential failure being the most important according to each criterion. These probabilities are then combined into a global quality measure, which can be interpreted as a joint probability of choice of the potential failure.Findings – The results obtained in the cases studied show the suitability of the changes proposed. Thresholds levels propos...

Scatter Search Applied to the Vehicle Routing Problem with Simultaneous Delivery and Pickup

Though its origins can be traced back to 1977, the development and application of the metaheuristic Scatter Search (SS) has stayed dormant for 20 years. However, in the last 10 years, research interest has positioned SS as one of the recognizable methodologies within the umbrella of evolutionary search. This paper presents an application of SS to the problem of routing vehicles that are required both to deliver and pickup goods (VRPSDP). This specialized version of the vehicle routing problem is particularly relevant to organizations that are concerned with sustainable and environmentally-friendly business practices. In this work, the efficiency of SS is evaluated when applied to this problem. Computational results of the application to instances in the literature are presented.

Statistical modeling and probabilistic composition in the prediction of the customer lifetime value

Purpose – Data mining registers of transactions allows for benchmarking customers evaluation strategies. The purpose of this paper is to provide information on the application of different approaches to explore this kind of data.Design/methodology/approach – Traditionally, heuristics based on variables such as recency, frequency, and monetary (RFM) value of transactions are used to determine the best customers. In this paper, a new form of directly combining the values of these variables is compared to an approach based on fitting a stochastic model. This last model is a mixture of a model for the number of transactions and another for the value spent. The new direct form of evaluation is based on computing the joint probability of maximizing quality indicators.Findings – Good fit of the different models tested to the series of individual data as well as coherent predictions are registered. Patterns found provide empirical confirmation of results that theoretically should be expected.Research limitations...

Aleatorização e composição de medidas de preferência

Models for preferences, established through the ranking of the options according to isolated factors, are developed here. Randomization of ranks allows us to compute the probability of each option be raised to the position of best choice. It is verified that, in horses races, measures of preference built through odds of the options to hold the first position according to some criterion or to a combination of criteria are more correlated with the measure of preference given by the final betting distribution than those given directly by the ranks.

Rough sets analysis with antisymmetric and intransitive attributes: classification of brazilian soccer clubs

Este trabalho visa a desenvolver classificacoes alternativas para times de futebol em um campeonato. Dados do Campeonato Brasileiro de Futebol de 2005 sao analisados. A Teoria dos Conjuntos Aproximativos (TCA) e empregada nesta analise. Por avaliar a qualidade da aproximacao em termos de probabilidades de concordância e de discordância entre a classificacao pelo conjunto de atributos de decisao e pelo conjunto de atributos de condicao de um par de objetos escolhidos aleatoriamente como discerniveis ou indiscerniveis, a modificacao da TCA empregada permite considerar relacoes intransitivas e anti-simetricas. A diferenca entre o numero de gols marcados pelos pares de clubes em confrontos diretos e uma relacao desse tipo.

Classification of the teams in the Brazilian Soccer Championship by probabilistic criteria composition

The essay discusses alternative rules for the classification of the teams in the Brazilian Soccer Championship. Three explanatory variables for the final classification are explored: the total number of goals scored and taken by each team and the results of their matches against each opponent. Two teams are placed in different classes only if their relative ranks according to a combination of these three criteria do not contradict the official ranks. The essay studies the rules for building the joint classification based on the probabilities of dominance according to these three criteria. Finally, it presents the results of the application of different rules to the data of 2006 and 2007.

Probabilistic Preferences Composition in the Classification of Apparel Retail Stores

This paper employs the probabilistic composition of preferences to classify stores by their operational efficiency. Probabilistic composition of preferences is a multicriteria analysis methodology based on the transformation of assessments by multiple attributes into probabilities of choice. The numerical initial measurements provide estimates for location parameters of probability distributions that are compared to measure the preferences. The probabilities of choice according to each attribute separately are aggregated according to probabilistic composition rules. A classification of two sets of stores into five classes is performed. Probabilistic Preferences Composition in the Classification of Apparel Retail Stores

Probabilistic composition of criteria for schedule monitoring

Time is a key factor in management. Along a project execution, keeping the best completion rates, not too slow and not too fast, is a central objective but such a best rate cannot be suitably anticipated in a precise schedule. It must be determined on the job, on a comparative basis. This paper develops an evaluation system involving the measurement of schedule fitting indicators designed to deal with such conditions. This evaluation system is based on a transformation of the data into probabilities of reaching the frontier of best performances that permits precisely composing measurements on correlated attributes. This feature of the system allows for combining criteria evaluated on elementary and on aggregate levels.

Restringindo flexibilidade de pesos em DEA utilizando análise de regressão MSEA

In this paper we present a procedure based on the use of Minimum Sum of Absolute Errors (MSAE) regression for the treatment of factor weights in Data Envelopment Analysis (DEA). It develops and presents alternative method to limit the range within which these factor weights are allowed to vary when models using a single output are analyzed.