Actually, a set of ETL software (Extract, Transform and Load) is available to constitute a major investment market. Each ETL uses its own techniques for extracting, transforming and loading data into data warehouse, which makes the task of evaluating ETL software very difficult. However, choosing the right software of ETL is critical to the success or failure of any Business Intelligence project. As there are many impacting factors in the selection of ETL software, the same process is considered as a complex multi-criteria decision making (MCDM) problem. In this study, an application of decision-making methodology that employs the two well-known MCDM techniques, namely Analytic Hierarchy Process (AHP) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) methods is designed. In this respect, the aim of using AHP is to analyze the structure of the ETL software selection problem and obtain weights of the selected criteria. Then, TOPSIS technique is used to calculate the alternatives’ ratings. An example is given to illustrate the proposed methodology. Finally, a software prototype for demonstrating both methods is implemented.

Landfill location selection is a multi-criteria decision problem and has a strategic importance for many regions. The conventional methods for landfill location selection are insufficient in dealing with the vague or imprecise nature of linguistic assessment. To resolve this problem, fuzzy multi-criteria decision-making methods are proposed. The aim of this paper is to use fuzzy TODIM (the acronym for Interactive and Multi-criteria Decision Making in Portuguese) and the fuzzy analytic hierarchy process (AHP) methods for the selection of landfill location. The proposed methods have been applied to a landfill location selection problem in the region of Casablanca, Morocco. After determining the criteria affecting the landfill location decisions, fuzzy TODIM and fuzzy AHP methods are applied to the problem and results are presented. The comparisons of these two methods are also discussed.

Blockchain technology has received wide attention during recent years, and has huge potential to transform and improve supply chain management. However, its implementation in the SSCM (Sustainable Supply Chain Management) strategy is sophisticated, and the challenges are not explored very well, especially in the Moroccan context. To this end, the chief objective of the current endeavor is to investigate the barriers that hinder the adoption of blockchain technology in SSCM from the Moroccan industry and service sectors’ perspective. Based on a comprehensive literature search and the use of experts’ viewpoints, the barriers affecting the successful implementation of blockchain are classified into three categories called TEO: technological and system, environmental, and intra-organizational dimensions. In this context, a fuzzy group decision-making framework is organized by combining DEMATEL (Decision-Making Trial and Evaluation Laboratory) and IFAHP (Intuitionistic Fuzzy Analytic Hierarchy Process). The IFAHP technique helps to determine the importance/priorities of barriers affecting blockchain adoption, while the DEMATEL technique forms the cause–effect interconnections between these barriers and classifies them concerning the degree of importance and relationships. The results reveal that ‘government policy and support’ and ‘challenges in integrating sustainable practices and blockchain technology through SCM’ are significant adoption barriers of blockchain in Moroccan SSCM. The proposed solution can support industrial decision makers to form flexible short- and long-term decision-making strategies to efficiently manage a sustainable supply chain.

In recent years, the classification of class-imbalanced data has obtained increasing attention across different scientific areas such as fraud detection, metabolomics, Cancer diagnosis, etc. This interest comes after proving the negative effect of overlapping on the performance of class-imbalanced learning. Based on augmented R-value, our proposed strategy aims to select features that make data achieve the minimal overlap degree, so improving the performance of classification as well. In this context, we present three feature selection algorithms RONS (Reduce Overlapping with No-sampling), ROS (Reduce Overlapping with SMOTE), and ROA (Reduce Overlapping with ADASYN), which are built through sparse feature selection to minimize the overlapping and perform binary classification. Also, a re-sampling process has been included in both ROS and ROA. Simulation results show that our proposed algorithms as feature selection methods manage the variation of false discovery rate during the selection of main features for the process modeling. For the experiment, four credit card datasets have been selected to test the performance of our algorithms. Using F-measure and Gmean evaluation metrics, the results reveal that our proposed algorithms are considerably recommended compared with classical feature selection methods. Besides, this effective feature selection strategy can be extended as an alternative to deal with class-imbalanced learning problems that involve overlapping.

No abstract