摘要 :
Wolf pack algorithm (WPA) is a relatively new swarm intelligence-based algorithm for solving complex continuous optimisation problems as well as real-world optimisation problems. The basic WPA and its variants are prone to trap in...
展开
Wolf pack algorithm (WPA) is a relatively new swarm intelligence-based algorithm for solving complex continuous optimisation problems as well as real-world optimisation problems. The basic WPA and its variants are prone to trap into local optima and premature convergence when tackling multi-modal functions due to diversity loss problem and imbalance between exploration and exploitation. Inspired by the idea of integrating the heuristic information and stochastic strategies to balance exploration with exploitation, we propose a self-adaptive WPA based on dynamic population updating (SWPA-DU) strategy. First, the self-adaptive chaotic scouting behaviour is designed to develop the global exploration of scout wolves. Second, a novel Cauchy perturbation operator is proposed to generate a few mutation besieging wolves, which not only enhances the capability of jumping out of local optima but also improves local exploitation. Third, a dynamic population updating strategy is invented to improve diversity. Numerical experiments with a suit of benchmark functions and practical applications are performed to verify the effectiveness and advancement of the proposed algorithm. The experimental results indicate that SWPA-DU obtains superior performance on both multi-modal and high-dimensional problems over the compared algorithms.
收起
摘要 :
Purpose This study examines the dynamic relationships of visit behavior in the multiple channels [personal computer (PC) and mobile channels] on online store sales performance. Design/methodology/approach The empirical data were f...
展开
Purpose This study examines the dynamic relationships of visit behavior in the multiple channels [personal computer (PC) and mobile channels] on online store sales performance. Design/methodology/approach The empirical data were from an online store for the period between August 14, 2015 and May 15, 2016. The data consisted of consumer visit behavior and online store sales performance. Vector autoregression with an exogenous variables model was adopted to investigate the dynamic relationships. Findings The empirical results show significant relationships between visit behavior metrics (number of visitors, average number of visits per visitor and average length of each visit) in the two channels and online store sales performance. The number of visitors through the PC and mobile channels strongly and positively affects online store sales performance both in the short term and in the longer term. Moreover, the number of visitors in the PC channel has the strongest influence on sales performance metrics, followed by the number of visitors and the average number of visits in the mobile channel. The PC channel's visit behavior metrics explain a larger proportion of the sales performance variance than that in the mobile channel. Originality/value The previous literature on consumer behavior in multichannel marketing mainly focuses on channel selection or migration, and examines the different factors affecting channel choice behavior. Little is known about the impacts of visit behavior in the multiple channels. This study adopts the heuristic-systematic information processing theory to unveil the impacts of visit behavior metrics in the PC and mobile channels on online store sales performance.
收起
摘要 :
Purpose Online product ratings play an important role in the decision-making process of consumers, which are not only sources of information used by consumers to understand the function and quality of a product or service but also...
展开
Purpose Online product ratings play an important role in the decision-making process of consumers, which are not only sources of information used by consumers to understand the function and quality of a product or service but also sources of information used to find desirable products. The purpose of this paper is to develop a decision-based method for supporting the purchase decisions of consumers based on not only the online product ratings but also the actual product attributes.
收起
摘要 :
Previous studies on financial distress prediction have chiefly used financial indicators which derived from financial statements as explanatory variables, so some potentially useful information that contained in the financial netw...
展开
Previous studies on financial distress prediction have chiefly used financial indicators which derived from financial statements as explanatory variables, so some potentially useful information that contained in the financial network was not considered. The listed companies can be represented as a complex financial network which the firms are regarded as nodes and the links account for stock returns correlation. The purpose of this study is to investigate whether network-based variables can improve the predictive power of financial distress prediction. Therefore, this study proposed a genetic algorithm (GA) approach to parameter selection in gradient boosting decision tree and integrated network-based variables for financial distress prediction. In order to verify the prediction capability of network-based variables and GA-based gradient boosting method in financial distress prediction, empirical study based on Chinese listed firms' real data is employed, and comparative analysis is conducted. The experiment results indicate that the introduction of network-based variables and GA-based gradient boosting method for financial distress prediction can enhance predictive performance in terms of accuracy, recall, precision, F-score, type I error, and type II error.
收起
摘要 :
From the viewpoint of a monopolist who is selling a product in a market where peer communication matters, a social network of consumers is a valuable resource that can elevate a company's revenue if used effectively. In order to u...
展开
From the viewpoint of a monopolist who is selling a product in a market where peer communication matters, a social network of consumers is a valuable resource that can elevate a company's revenue if used effectively. In order to understand and realize the potential value within a social network, this paper focuses on measuring the link value in marketing-oriented scenarios and further adopting the measured value to propose profitable referral strategies. We measure the link value by considering how much a company's revenue changes when a new link is added. Moreover, different market scenarios are considered, including different degrees of price discrimination and different levels of information. More interestingly, we identify the relationship between the measured link value and the (weighted) Bonacich centrality in various market scenarios. Then, we design and propose profitable referral networks based on measured link value, which serves as a new perspective for designing a profitable referral mechanism. From numerical examples, several properties are summarized in order to determine how the measured link value is influenced by the interaction between market scenarios and network structures. Furthermore, a series of simulations have also been conducted to validate the effectiveness of the proposed referral networks as well as to provide insight into managerial practices. (c) 2020 Elsevier B.V. All rights reserved.
收起
摘要 :
This paper investigates the optimal pricing strategies of domestic/imported electric vehicle manufacturer and the government's optimal decisions by developing the game-theoretic models. The results show that the technology spillov...
展开
This paper investigates the optimal pricing strategies of domestic/imported electric vehicle manufacturer and the government's optimal decisions by developing the game-theoretic models. The results show that the technology spillover caused by introducing IEVs into domestic markets can affect the profits of electric vehicle manufacturers and the government's decisions on sub-sidies and tariffs. In addition, implementing the subsidy and tariff policies can help to improve the profit of the domestic electric vehicle manufacturer and the social welfare. Moreover, when the degree of technology spillover is relatively large, implementing the subsidy and tariff policies can also help to improve the consumer surplus.
收起
摘要 :
As knowledge graphs have attracted enormous attention from researchers, much effort has been invested in recommendation systems to mine user preferences effectively. In particular, knowledge graphs, which convey useful side inform...
展开
As knowledge graphs have attracted enormous attention from researchers, much effort has been invested in recommendation systems to mine user preferences effectively. In particular, knowledge graphs, which convey useful side information about users and items, can provide more accurate and explainable recommendations. When it comes to interactions between entities, however, the majority of existing work fails to incorporate high-order relations that ensure recommendation accuracy. This paper proposes attention-enhanced joint knowledge and user preference propagation (AKUPP), which integrates two types of knowledge propagation. The first is propagating user preferences based on the users' history of interacting items through ripple sets. The second propagation employs an attention mechanism to emphasize the important semantics of relations, and with multiple layers, high-order relations are explored. Therefore, we successfully incorporate both side information and high-order relations in the knowledge graph. We show, via extensive experimentation on real-world datasets, that our approach outperforms numerous state-of-the-art baselines in terms of performance and accuracy.
收起
摘要 :
Purpose Online charitable giving is prevalent, and how to attract individuals' attention to donate is essential for charities. Little is known about the interaction effect of empathy (donor) and vulnerability (receiver) on donate ...
展开
Purpose Online charitable giving is prevalent, and how to attract individuals' attention to donate is essential for charities. Little is known about the interaction effect of empathy (donor) and vulnerability (receiver) on donate intention. To bridge this gap, this study aims to investigate whether the influence of empathy on charitable giving would be moderated by receivers' vulnerability, and if yes, what is the mechanism. Design/methodology/approach Five experiments were conducted in the context of charitable giving with 1,303 participants to test our hypotheses. Findings When empathetic individuals confronted high vulnerable receivers, they were less likely to donate; otherwise, they were more likely to donate when they confronted low vulnerable receivers, and this interaction effect was mediated by concern about self. Originality/value The present research identifies a novel moderator of the effect of empathy on charitable giving and elucidates the underlying mechanism of concern about self. Based on these findings, the authors provide actionable implications for charities by demonstrating the interaction effect of empathy and vulnerability on donate intention.
收起
摘要 :
As orthopedic and dental implants, polyetheretherketone (PEEK) is expected to be a common substitute material of titanium (Ti) and its alloys due to its good biocompatibility, chemical stability, and elastic modulus close to that ...
展开
As orthopedic and dental implants, polyetheretherketone (PEEK) is expected to be a common substitute material of titanium (Ti) and its alloys due to its good biocompatibility, chemical stability, and elastic modulus close to that of bone tissue. It could avoid metal allergy and bone resorption caused by the stress shielding effect of Ti implants, widely studied in the medical field. However, the lack of biological activity is not conducive to the clinical application of PEEK implants. Therefore, the surface modification of PEEK has increasingly become one of the research hotspots. Researchers have explored various biomolecules modification methods to effectively enhance the osteogenic and antibacterial activities of PEEK and its composites. Therefore, this review mainly summarizes the recent research of PEEK modified by biomolecules and discusses the further research directions to promote the clinical transformation of PEEK implants.
收起
摘要 :
Gold and Bi-bearing parageneses are pivotal to understanding gold concentration and deposition processes. The large-scale Laozuoshan gold deposit is located in the Jiamusi Block, northeastern China, and has experienced complex min...
展开
Gold and Bi-bearing parageneses are pivotal to understanding gold concentration and deposition processes. The large-scale Laozuoshan gold deposit is located in the Jiamusi Block, northeastern China, and has experienced complex mineralization processes with abundant gold and Bi-bearing minerals. However, the relationship between Bi-minerals and gold is unclear, preventing our understanding of the gold enrichment and precipitation mechanism in the Laozuoshan gold deposit. Optical microscope and SEM results show three stages of gold mineralization pyrrhotite (Po-1) + arsenopyrite (Apy-1) + Bi-bearing minerals (Bis-1) + Au-1; arsenopyrite (Apy-2) + chlorite + Bi-bearing minerals (Bis-2) + Au-2; and arsenopyrite (Apy-3) + graphite + Bi-bearing minerals (Bis-3) + Au-3. The abundant amount of gold (Au-1~Au-3) is associated with Bi-bearing minerals (Bis-1~Bis-3), which coexist as inclusions and fill in fractures in these minerals. The mineral assemblages of arsenopyrite, Bi-minerals, and gold exhibit a clear As-Bi-Au mineralogy in the ores, and the ternary diagram of the chemical compositions of the Bi-minerals shows that Bi-minerals all fall in reducing regions, indicating that Bi-minerals are precipitated under reducing conditions. The gold compositions demonstrate a positive correlation (R2 = 0.58) between Au and Bi. Consequently, we propose that the gold experienced the ore-forming fluids concentration and further Bi-melts scavenging for the Laozuoshan gold deposit mineralization. The Bi collector model is essential in interpreting the high-grade gold in the Laozuoshan gold deposit, indicating that the geochemical anomalies observed with bismuth may be a critical potential exploration target for the high-grade gold deposits in the Jiamusi Block.
收起