International Journal of Information Technology & Decision Making

In recommender systems, Collaborative Filtering (CF) plays an essential role in promoting recommendation services. The conventional CF approach has limitations, namely data sparsity and cold-start. The matrix decomposition approach is demonstrated to be one of the effective approaches used in developing recommendation systems. This paper presents a new approach that uses CF and Singular Value Decomposition (SVD)$++$ for implementing a recommendation system. Therefore, this work is an attempt to extend the existing recommendation systems by (i) finding similarity between user and item from rating matrices using cosine similarity; (ii) predicting missing ratings using a matrix decomposition approach, and (iii) recommending top-N user-preferred items. The recommender system’s performance is evaluated considering Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). Performance evaluation is accomplished by comparing the systems developed using CF in combination with six different algorithms, namely SVD, SVD$++$, Co-Clustering, KNNBasic, KNNBaseline, and KNNWithMeans. We have experimented using MovieLens 100K, MovieLens 1M, and BookCrossing datasets. The results prove that the proposed approach gives a lesser error rate when cross-validation ($\mathrm{\text{CV}}=\{5,10,15\}$) is performed. The experimental results show that the lowest error rate is achieved with MovieLens 100K dataset ($\mathrm{\text{RMSE}}=0.9123$, $\mathrm{\text{MAE}}=0.7149$). The proposed approach also alleviates the sparsity and cold-start problems and recommends the relevant items.

Time, cost, and quality are the three indispensable factors for the realization and success of a project. In this context, we propose a framework composed of a multi-objective approach and multi-criteria decision-making methods (MCDM) to solve time-cost-quality trade-off optimization problems. A multi-objective Simulated Annealing (MOSA) algorithm is used to compute an approximation to the Pareto optimal set. The concept of the exploratory grid is introduced in the MOSA to improve its performance. MCDM are used to assist the decision-making process. The Shannon entropy and AHP methods assign weights to criteria. The first methodology is for the inexperienced decision-makers, and the second concedes a personal and flexible weighting of the criteria weights, based on the project manager’s assessment. The TOPSIS and VIKOR methods are considered to rank the solutions. Although they have the same purpose, the rankings achieved are different. A tool is implemented to solve a time-cost-quality trade-off problem on a project activities network. The computational experiments are analyzed and the results with the exploratory grid in Simulated Annealing (SA) are promising. Despite the framework aims to solve multi-objective trade-off optimization problems, supporting the decisions of the project manager, the methodologies used can also be applied in other areas.

Evaluating sustainable conceptual designs is a crucial part of the development of new products in various sectors because it contributes to the survival and prosperity of companies. Such designs must be compatible with a product’s functional requirements and be sustainable in economic, environmental, and social terms. Various criteria, some qualitative and others quantitative, are considered when evaluating sustainable conceptual designs; some criteria may also have sub-criteria, and these criteria and sub-criteria may differ in importance. How to effectively evaluate various criteria and sub-criteria and weight them are the major research problem. This study developed an analytic hierarchy process (AHP)-based ELECTRE I method to resolve the evaluation problem; the method entails a two-level hierarchical structure to depict the relationships between the major criteria and sub-criteria and their corresponding weights, with weights obtained through an AHP. Furthermore, an extension based on the addition of net concordance value and net adjusted discordance value is proposed for ranking alternative designs; this extension yields more distinguishable results than the method of [Nijkamp and Van Delft Multi-Criteria Analysis and Regional Decision-Making, Vol. 8 (Springer Science & Business Media, 1977)], and the proposed extension in the ELECTRE I method captures more information in the modified summation matrix when aggregating values in the concordance matrix and the modified discordance matrix, representing an advantage over the method of [Zhang et al. Virtual network embedding using node multiple metrics based on simplified ELECTRE method, IEEE Access 6 (2018) 37314–37327]. In addition, to demonstrate the feasibility of the proposed method, the example of the evaluation and selection of sustainable conceptual designs in the furniture manufacturing industry is presented. Finally, a numerical comparison is made to show the advantages of the proposed method.

This paper had developed an effective information technology (IT) vendor selection model for banking & financial services industries (BFSI). For any business, profitability and growth depends on the right vendor selection in their purchase process. This paper identifies ten most influencing and important criteria with 43 sub-criteria to comprehend the vendor selection process. Furthermore, the authors developed a vendor selection score model using Structural Equation Modelling (SEM) and Analytic Hierarchy Process (AHP). This article intends to inform practice and conclude with practical recommendations to BFSI for vendor selection. The proposed composite technique identified the most eligible vendor to meet up with the buyer’s strategies. This article suggests the most desirable vendor for the required benefit. Vendor 1 (Silverlake) with a score of 44% promised to be the most recommended one that also performed consistently in the sensitivity test.

Clustering ensemble is a new problem where it is aimed to extract a clustering out of a pool of base clusterings. The pool of base clusterings is sometimes referred to as ensemble. An ensemble is to be considered to be a suitable one, if its members are diverse and any of them has a minimum quality. The method that maps an ensemble into an output partition (called also as consensus partition) is named consensus function. The consensus function should find a consensus partition that all of the ensemble members agree on it as much as possible. In this paper, a novel clustering ensemble framework that guarantees generation of a pool of the base clusterings with the both conditions (diversity among ensemble members and high-quality members) is introduced. According to its limitations, a novel consensus function is also introduced. We experimentally show that the proposed clustering ensemble framework is scalable, efficient and general. Using different base clustering algorithms, we show that our improved base clustering algorithm is better. Also, among different consensus functions, we show the effectiveness of our consensus function. Finally, comparing with the state of the art, we find that the clustering ensemble framework is comparable or even better in terms of scalability and efficacy.

Failure Mode and Effects Analysis (FMEA) is an effective tool for prioritization of the failures by identifying and eliminating potential risks, free double hierarchy hesitant fuzzy linguistic term set (FDHHFLTS) can describe the hesitation more accurately and reasonably by adding the free second hierarchy hesitant fuzzy linguistic terms, and multiattribute decision-making (MADM) methods have advantages in ranking and selecting different alternatives. By considering the advantages of MADM methods and FMEA model, in this paper, we propose a novel model to evaluate the risk failure modes (FMs) under FDHHFLTS context. First, an extended Complex Proportional Assessment (COPRAS) method is proposed to address the risk assessment problems. The proposed risk assessment model is utilized to assess and rank the FMs to address the limitations of the traditional FMEA. Second, a weight determination model is constructed based on the Kemeny Median (KEM) method and Stepwise Weight Assessment Ratio Analysis (SWARA) method, which can make the weight more practical and effective under the situation of completely unknown weights. Finally, the proposed model is used to the case of logistics enterprises’ risk assessment. The application of the case shows the feasibility of the proposed model, and the comparisons with some existing methods illustrate the advantages of the proposed risk assessment model.

Analyzing and gathering the people’s reactions on product trading, public services, etc. are crucial. Sentiment analysis (also termed as opinion mining) is a usual dialogue preparing act that plans on discovering the sentiments after opinions in texts on changing subjects. This research work adopts a novel sentiment analysis approach that comprises six phases like (i) Pre-processing, (ii) Keyword extraction and its sentiment categorization, (iii) Semantic word extraction, (iv) Semantic similarity checking, (v) Feature extraction, and (vi) Classification. Accordingly, the Mongodb documented tweets initially underwent pre-processing with stop word removal, stemming, and blank space removal. Regarding the extracted keywords, the existing semantic words are derived after categorizing the sentiment of keywords. Additionally, the semantic similarity score is evaluated along with their keywords. The subsequent step is feature extraction, where the Holoentropy features such as cross Holoentropy and joint Holoentropy are formulated. Along with this, the extraction of weighted holoentropy features is the major work, where weight is multiplied with the holoentropy features. Moreover, in order to enhance the performance of classification results, the constant term utilized in evaluating the weight function is optimized. For this optimal tuning, a new, improved algorithm termed as Self Adaptive Moth Flame Optimization (SA-MFO) is introduced, which is the adaptive version of MFO algorithm. For classification, this paper aims to use the Deep Convolutional Neural network (DCNN), where the batch size is fine-tuned using the same SA-MFO algorithm. Finally, the performance of the proposed work is compared over other conventional models with respect to different performance measures.

The bankruptcy prediction research domain continues to evolve with the main aim of developing a model suitable for real-world application in order to detect early stages of financial distress of a company. The recent developments in computing, combined with the potential applications of big data technologies and artificial intelligence solutions have already made possible the integration of timely and recent information about business activities in order to monitor the financial health of companies. Therefore, this paper focuses on the predictions made a few months prior to the potential default of a company with the aim of identifying the determinants that signal about the insolvency. The experiments include in-depth analysis of model performances using different dataset configurations.