Search

As a result of the extensive variety of products available in e-commerce settings during the last decade, recommender systems have been highlighted as a means of mitigating the problem of information overload. Collaborative filtering (CF) is the most widely used algorithm to build such systems, and improving the predictive accuracy of CF-based recommender systems has been a major research challenge. This research aims to improve the prediction accuracy of CF by incorporating social network analysis (SNA) and clustering techniques. Our proposed model identifies the most influential people in an online social network by SNA and then conducts clustering analysis using these people as initial centroids (cluster centres). Finally, the model makes recommendations using cluster-indexing CF based on the clustering outcomes. In this step, our model adjusts the effect of neighbours in the same cluster as the target user to improve prediction accuracy by reflecting hidden information about his or her social community. The experimental results indicate that the proposed model outperforms other comparison models, including conventional CF, with statistical significance. [ABSTRACT FROM AUTHOR]

Compared with layup techniques, thermo-hydroforming is shown to be a viable process for mass production of thermoplastic composite structures due to its relatively rapid cycle time and low impact on the microstructure of the material. However, unlike layup technique, thermo-hydroforming can produce wrinkles in the formed part. A research was conducted wherein ABAQUS/CAE (6.14-1) was employed to numerically study the impact of thermo-hydroforming process parameters on the formation of wrinkles in a thermoplastic helmet. The optimized properties of the fiber-reinforced polymer composite was previously determined by the authors using the preferred fiber orientation model implemented as a user material subroutine (VUMAT). To account for the interaction between different layers of the laminated composite, the cohesive zone model was employed. The objective of the study was to use the simulation tool to minimize the overall wrinkle density and wrinkle height in the formed helmet as a function of the fluid pressure, boundary conditions, and especially the blank shape and the relief cuts made in the blank. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANNs) have been popularly applied for stock market prediction, since they offer superlative learning ability. However, they often result in inconsistent and unpredictable performance in the prediction of noisy financial data due to the problems of determining factors involved in design. Prior studies have suggested genetic algorithm (GA) to mitigate the problems, but most of them are designed to optimize only one or two architectural factors of ANN. With this background, the paper presents a global optimization approach of ANN to predict the stock price index. In this study, GA optimizes multiple architectural factors and feature transformations of ANN to relieve the limitations of the conventional backpropagation algorithm synergistically. Experiments show our proposed model outperforms conventional approaches in the prediction of the stock price index. [ABSTRACT FROM AUTHOR]

E-commerce has dramatically expanded its sales, with people being increasingly customed to online shopping. This study aimed to examine changes in the distribution of retail stores that provide fashion and beauty products and services in terms of the number of online shopping transactions and their spatial characteristics in Seoul. For this purpose, we analyzed location data concerning relevant newly opened and closed offline stores from four subgroups between 2015 and 2019. Though more offline stores were newly opened than closed in that period, the number of stores had overall significantly decreased apart from stores providing beauty services, with significant differences in subgroup spatial distribution patterns. We identified local geographic factors affecting retail stores by applying spatial regression models, and we found that the growth of e-commerce was associated with the related to the survival and closure of fashion and beauty stores. While retail store locations are not immediately responsive to changes due to COVID-19, we expect the prolonged COVID-19 outbreak will further facilitate the spatial transformation that has been stimulated by rise of online retailing. Our findings provide important basic data for establishing location plans and management strategies for future fashion and beauty stores, as well as timely evidence-based data to help direct subsequent academic research. [ABSTRACT FROM AUTHOR]

The main purpose of this research is to study the predictive power of behavioural life profile models for mortgages using machine learning techniques and emerging languages from the same data sets. Based on the results, banks can determine whether the predictive power of the model can be improved regarding estimates of probability of redemption, and probability of internal transfer beyond traditional techniques. Model training will take place using algorithms based on machine learning such as: random forests, extreme gradient, boosting, light gradient boosting, Adaboost, and ExtraTrees. To perform simulations on fast learning and permit testing of hypotheses, the IBM cloud environment and the Watson proven analytical environment will be used, in order to maximize the value derived from the investment and determine the decision on the implementation and modelling strategy for business disciplines. Therefore, these factors could provide a solid basis for the sustainable development of the mortgage market, and the approach in this research is a starting point for identifying the best decisions taken by banking institutions to contribute to the sustainable development of mortgage lending. [ABSTRACT FROM AUTHOR]

E-grocery is becoming more and more popular, involving both pure e-commerce players and physical stores in its development and sales. As a consequence, the last mile delivery model has been heavily modified, with ambiguous final impact on the environment. This paper identifies the key elements germane to e-grocery (demand and supply), discusses e-grocery development and investigates the challenges ahead. In more detail, it presents the results of a stated preference survey on consumers' channel choices for the grocery market. The survey was carried out in Shanghai (China) in order to investigate different purchase attributes, such as product and delivery service price, product range, lead time, time window and travel time. The paper identifies heterogeneous reactions to alternative service configurations, which allows to estimate market shares for e-grocery, with the in-store option as a reference. Policy implications and operational solutions to improve the sustainability of this renewed last mile delivery model are thus proposed. [ABSTRACT FROM AUTHOR]

Measuring and managing the financial sustainability of the borrowers is crucial to financial institutions for their risk management. As a result, building an effective corporate financial distress prediction model has been an important research topic for a long time. Recently, researchers are exerting themselves to improve the accuracy of financial distress prediction models by applying various business analytics approaches including statistical and artificial intelligence methods. Among them, support vector machines (SVMs) are becoming popular. SVMs require only small training samples and have little possibility of overfitting if model parameters are properly tuned. Nonetheless, SVMs generally show high prediction accuracy since it can deal with complex nonlinear patterns. Despite of these advantages, SVMs are often criticized because their architectural factors are determined by heuristics, such as the parameters of a kernel function and the subsets of appropriate features and instances. In this study, we propose globally optimized SVMs, denoted by GOSVM, a novel hybrid SVM model designed to optimize feature selection, instance selection, and kernel parameters altogether. This study introduces genetic algorithm (GA) in order to simultaneously optimize multiple heterogeneous design factors of SVMs. Our study applies the proposed model to the real-world case for predicting financial distress. Experiments show that the proposed model significantly improves the prediction accuracy of conventional SVMs. [ABSTRACT FROM AUTHOR]

After a disability occurs, vocational rehabilitation is essential for promoting return to society and improving quality of life. To facilitate vocational rehabilitation, an effective counseling by human expert is essential. However, the number of the experts is not many. Thus, people with disabilities (PWD) have had difficulty in having proper vocational consultation service. To mitigate this problem, this study aims at developing a decision support system (DSS) to recommend appropriate jobs to PWD based on their characteristics. For doing this, the experts in disabilities, occupational research, and information systems participated in building the logic of the system. The DSS for scientific and quantitative vocational counseling enables job counselors to recommend appropriate occupations considering PWDs' characteristics. [ABSTRACT FROM AUTHOR]

This study introduces a thermally responsive smart hydrogel with enhanced electrical properties achieved through volume switching. This advancement was realized by incorporating multiscale liquid metal particles (LMPs) into the PNIPAM hydrogel during polymerization, using their inherent elasticity and conductivity when deswelled. Unlike traditional conductive additives, LMPs endow the PNIPAM hydrogel with a remarkably consistent volume switching ratio, significantly enhancing electrical switching. This is attributed to the minimal nucleation effect of LMPs during polymerization and their liquid-like behavior, like vacancies in the polymeric hydrogel under compression. The PNIPAM/LMP hydrogel exhibits the highest electrical switching, with an unprecedented switch of 6.1 orders of magnitude. Even after repeated swelling/deswelling cycles that merge some LMPs and increase the conductivity when swelled, the hydrogel consistently maintains an electrical switch exceeding 4.5 orders of magnitude, which is still the highest record to date. Comprehensive measurements reveal that the hydrogel possesses robust mechanical properties, a tissue-like compression modulus, biocompatibility, and self-healing capabilities. These features make the PNIPAM/LMP hydrogel an ideal candidate for long-term implantable bioelectronics, offering a solution to the mechanical mismatch with dynamic human tissues.