-*- mode: org -*- * 16(<- 10): On learning of weights through preferences We present a method to learn the criteria weights in multi-criteria decision making (MCDM) by applying emerging learning-to-rank machine learning techniques. Given the pairwise preferences by a decision maker (DM), we learn the weights that the DM attaches to the multiple criteria, characterizing each alternative. As the training information, our method requires the pairwise preferences of alternatives, as revealed by the DM. Once, the DM's decision model is learnt in terms of the criteria weights, it can be applied to predict his choices for any new set of alternatives. The empirical validation of the proposed approach is done on a collection of 12 standard datasets. The accuracy values are compared with those obtained for the state-of-the-art methods such as ranking-SVM and TOPSIS. (C) 2015 Elsevier Inc. All rights reserved. 2015 * 17(<- 16): A multi-criteria recommendation system using dimensionality reduction and Neuro-Fuzzy techniques Multi-criteria collaborative filtering (MC-CF) presents a possibility to provide accurate recommendations by considering the user preferences in multiple aspects of items. However, scalability and sparsity are two main problems in MC-CF which this paper attempts to solve them using dimensionality reduction and Neuro-Fuzzy techniques. Considering the user behavior about items' features which is frequently vague, imprecise and subjective, we solve the sparsity problem using Neuro-Fuzzy technique. For the scalability problem, higher order singular value decomposition along with supervised learning (classification) methods is used. Thus, the objective of this paper is to propose a new recommendation model to improve the recommendation quality and predictive accuracy of MC-CF and solve the scalability and alleviate the sparsity problems in the MC-CF. The experimental results of applying these approaches on Yahoo!Movies and TripAdvisor datasets with several comparisons are presented to show the enhancement of MC-CF recommendation quality and predictive accuracy. The experimental results demonstrate that SVM dominates the K-NN and FBNN in improving the MC-CF predictive accuracy evaluated by most broadly popular measurement metrics, F1 and mean absolute error. In addition, the experimental results also demonstrate that the combination of Neuro-Fuzzy and dimensionality reduction techniques remarkably improves the recommendation quality and predictive accuracy of MC-CF in relation to the previous recommendation techniques based on multi-criteria ratings. 2015 * 24(<-482): A confidence voting process for ranking problems based on support vector machines In this paper, we deal with ranking problems arising from various data mining applications where the major task is to train a rank-prediction model to assign every instance a rank. We first discuss the merits and potential disadvantages of two existing popular approaches for ranking problems: the 'Max-Wins' voting process based on multi-class support vector machines (SVMs) and the model based on multi-criteria decision making. We then propose a confidence voting process for ranking problems based on SVMs, which can be viewed as a combination of the SVM approach and the multi-criteria decision making model. Promising numerical experiments based on the new model are reported. 2009 * 27(<-439): MULTIOBJECTIVE MULTICLASS SUPPORT VECTOR MACHINES MAXIMIZING GEOMETRIC MARGINS In this paper, we focus on the all together model of the support vector machine (SVM) for multiclass classification, which constructs a piece-wise linear discriminant function It is formulated as a single-objective optimization problem maximizing the sum of margins between all pairs of classes. which is defined as the distance between two normalized support hyperplanes parallel to the corresponding discriminant. hyperplane where any sample is not contained However, it is not necessarily equal to the geometric margin defined as the minimal distance of Patterns in a pair of classes to the corresponding discriminant, hyperplanes Then, we formulate the proposed model as a multiobjective problem which maximizes all of the, margins simultaneously Moreover, we derive two kinds of single-objective second order cone programming (SOCP) problems based on scalarization approaches, Benson's method and e-constraint method to solve the proposed multiobjective model, and show that the methods can find Pareto optimal solutions of the model Furthermore, through numerical experiments we verify the generalization ability of discriminant, functions obtained by the proposed SOCP problems 2010 * 132(<- 6): CF-Rank: Learning to rank by classifier fusion on click-through data Ranking as a key functionality of Web search engines, is a user-centric process. However, click-through data, which is the source of implicit feedback of users, are not included in almost all of datasets published for the task of ranking. This limitation is also observable in the majority of benchmark datasets prepared for the learning to rank which is a new and promising trend in the information retrieval literature. In this paper, inspiring from the click-through data concept, the notion of click-through features is introduced. Click-through features could be derived from the given primitive dataset even in the absence of click-through data in the utilized benchmark dataset These features are categorized into three different categories and are either related to the users' queries, results of searches or clicks of users. With the use of click-through features, in this research, a novel learning to rank algorithm is proposed. By taking into account informativeness measures such as MAP, NDCG, InformationGain and OneR, at its first step, the proposed algorithm generates a classifier for each category of click-through features. Thereafter, these classifiers are fused together by using exponential ordered weighted averaging operators. Experimental results obtained from a plenty of investigations on WCL2R and LETOR4.0 benchmark datasets, demonstrate that the proposed method can substantially outperform well-known ranking methods in the presence of explicit click-through data based on MAP and NDCG criteria. Specifically, such an improvement is more noticeable on the top of ranked lists, which usually attract users' attentions more than other parts of these lists. This betterment on WCL2R dataset is about 20.25% for P@1 and 5.68% for P@3 in comparison with SVMRank, which is a well-known learning to rank algorithm. CF-Rank can also obtain higher or comparable performance with baseline methods even in the absence of explicit click-through data in utilized primitive datasets. In this regard, the proposed method on the LETOR4.0 dataset has achieved an improvement of about 2.7% on MAP measure compared to AdaRank-NDCG algorithm. (C) 2015 Elsevier Ltd. All rights reserved. 2015 * 430(<-354): Neural network application for fuzzy multi-criteria decision making problems In this paper, a fuzzy multi-criteria decision making model is presented based on a feed forward artificial neural network. This model is used to capture and represent the decision makers' preferences. The topology of the neural network model is developed to train the model. The proposed model can use historical data and update the database information for alternatives over time for future decisions. Basically, multi-criteria decision making problems are formulated, and neural network is used to learn the relation among criteria and alternatives and rank the alternatives. We do not use any utility function for the modeling; however, a unique method is proposed for eliciting the information from decision makers. The proposed model is applicable for a wide variety of multi-attribute decision making problems and can be used for future ranking or selection without managers' judgment effort. Simulation of the managers' decisions is demonstrated in detail and the design and implementation of the model are illustrated by a case study. (C) 2011 Elsevier B.V. All rights reserved. 2011 * 434(<-684): FEEDFORWARD ARTIFICIAL NEURAL NETWORKS FOR SOLVING DISCRETE MULTIPLE CRITERIA DECISION-MAKING PROBLEMS Decision making involves choosing some course of action among various alternatives. In almost all decision making problems, there are several criteria for judging possible alternatives. The main concern of the Decision Maker (DM) is to fulfill his conflicting goals while satisfying the constraints of the system. In this paper, we present an Adaptive Feedforward Artificial Neural Network (AF-ANN) approach to solve discrete Multiple Criteria Decision Making (MCDM) problems. The AF-ANN is used to capture and represent the DM's preferences and then to select the most desirable alternative. The AF-ANN can adjust and improve its representation as more information from the DM becomes available. We begin with the assumption that an AF-ANN topology is given, i.e., specific numbers of nodes and links are predetermined. To adjust the parameters of the AF-ANN, we present an iterative learning algorithm consisting of two steps: (a) generating a direction, and (b) a one-dimensional search along that direction. We then present a methodology to obtain the most appropriate AF-ANN topology and set its parameters. The procedure starts with a small number of nodes and links and then adaptively increases the number of nodes and links until the proper topology is obtained. Furthermore, when the set of training patterns (alternatives with their associated evaluations by the DM) changes, the AF-ANN model can adapt itself by re-training or expanding the existing model. Some illustrative examples are presented. To solve discrete MCDM problems by an AF-ANN, we show how to incorporate basic properties of efficiency, concavity, and convexity into the AF-ANN. We formulate the MCDM problems and use the AF-ANN to rank the set of discrete alternatives where each alternative is associated with a set of conflicting and noncommensurate criteria. We present a method for solving discrete MCDM problems through AF-ANNs which consists of: (a) formulating and assessing the utility function by eliciting information from the DM and then training the AF-ANN, and (b) ranking and rating alternatives by using the trained AF-ANN model. Some computational experiments are presented to show the effectiveness of the method. 1994