Search results

This paper aims to find the best method to predict the friction coefficient of textured 45# steel by comparing different machine learning algorithms and analytical calculations.

Five machine learning algorithms, including K-nearest neighbor, random forest, support vector machine (SVM), gradient boosting decision tree (GBDT) and artificial neural network (ANN), are applied to predict friction coefficient of textured 45# steel surface under oil lubrication. The superiority of machine learning is verified by comparing it with analytical calculations and experimental results.

The results show that machine learning methods can accurately predict friction coefficient between interfaces compared to analytical calculations, in which SVM, GBDT and ANN methods show close prediction performance. When texture and working parameters both change, sliding speed plays the most important role, indicating that working parameters have more significant influence on friction coefficient than texture parameters.

This study can reduce the experimental cost and time of textured 45# steel, and provide a reference for the widespread application of machine learning in the friction field in the future.

This paper considers the brand awareness and anchor influence on consumers' live-streaming purchases, and explores the existence of “free-riding” behavior, the comparison of brand promotion effect and active live-streaming effect and the optimal strategic combination between the brand and the anchor. The authors investigate the evolutionary stabilization strategies of the bounded rational brand and anchor, and explore the conditions for the realization of the optimal strategy. Management suggestions for the development of live streaming commerce can be provided in this paper.

Two significant models are used in this paper. The Stackelberg model is used to study the “free-riding” behavior, the comparison of brand promotion effect and active live-streaming effect and the optimal strategic combination between the brand and the anchor. Using evolutionary game theory to get the evolutionary stable equilibrium strategies and analyze the binary equilibrium strategy of the bounded rational brand and anchor. In addition, relevant simulation analysis is conducted using realistic data to verify the conclusions and for further analysis, making the conclusions of the paper have realistic significance.

The study shows that “free-riding” behavior exists and the positive effect of brand promotion is greater than that of active live-streaming. The brand and the anchor take active actions as the optimal strategy. As the sensitivity coefficient of consumers to live-streaming effort and the sensitivity coefficient of consumers to brand promotion change, various evolutionary stabilization strategies will appear. When the two sensitivity coefficients are below a certain threshold, the game sides will reach the optimal strategic combination to obtain the maximum benefits. When they rise above this threshold, it is counterproductive instead. The system achieves the optimal strategic combination when the difference factor between effort cost and promotion cost must be higher than a certain value, but when it takes the smallest possible value, the game sides tend to take active actions. This study can provide management suggestions for the sustainable development of the live-streaming model.

This paper shows that under certain conditions, the brand and the anchor can evolve into the optimal strategy to maximize the profits of both parties, which has certain practical significance for the prosperous development of live streaming commerce. In future research, the authors will consider the regulatory role of the government and construct a more realistic game model to provide constructive suggestions for the sustainable prosperity of live streaming commerce. Meanwhile, there are also games between multiple brands and multiple anchors, as well as games among brands-anchors-the live streaming platforms, and the authors will conduct more in-depth research in the future.

So far, the co-impact of anchor influence and brand awareness has not been considered simultaneously in published articles. This paper provides theoretical guidance for the behavioral choices of the brand and the anchor under the live streaming commerce, which is conducive to the prosperous development of live streaming commerce.

This study investigates whether the visualization of agricultural products influences consumers’ purchase intentions in the context of farmer-assisted livestreaming in China. Moreover, it explores the moderating effect of packaging functionality and the mediating effect of consumer trust.

Consumers in China from multiple social media platforms participated in this survey, which yielded 333 valid responses for analysis.

The results revealed a positive relationship between the video presentation about the agricultural production process and consumers’ purchase intention, which is mediated by consumers’ trust. Meanwhile, packaging functionality moderates the relationship between agricultural product visualization and consumers’ purchase intentions as well as the indirect effect of consumers’ trust.

This study extends the application of the stimulus-organism-response (SOR) model to the field of farmer-assisted livestreaming. By building a more detailed model, this study adds to knowledge on the influencing mechanisms of consumers’ purchase intentions in farmer-assisted livestreaming.

This study aims to understand how different levels of streamer channels influence luxury brand sales in live streaming commerce. This study also seeks to understand the conditions under which luxury brands may benefit more from different level streamer channels.

Panel data were collected from 17 international luxury brands on the Douyin live streaming platform in an 18 week period from August to December 2020 and analyzed by using a two-way fixed effects model.

The authors compared different mega-, macro- and micro-streamer channels within live streaming commerce and found that the densities of mega- and macro-streamer channels had significant positive impacts on luxury brand sales in live streaming commerce. Moreover, the effects of the density of streamer channel on luxury brand sales were moderated by such variables as product line breadth, product line depth, product type (star/non-star) and product price (high/low). The authors found that product line breadth and depth could reduce the positive impact of the densities of mega- and macro-streamer channels on luxury brand sales. For star products and high-priced products, the relationship between the density of mega-streamer channel and luxury brand sales was more likely to be observed than for non-star products and low-priced products. The relationship between the density of macro-streamer channel and luxury brand sales was more likely to be observed in low-priced products than in high-priced products.

The findings make important contributions to the literature in that the authors expand the influencer-brand fit theory by proposing a new model of effects of the densities of mega-, macro- and micro-streamer channels on sales performance across different luxury products to improve our understanding of the fit among influencers, brands and products. This helps luxury brands make basic decisions of “who sells” and “sells what” when engaging in live streaming commerce.

This research paper aims to investigate the critical factors influencing the live commerce industry and their implications for Key Opinion Leaders (KOLs) and brands.

The study comprehensively reviews previous research, develops relevant hypotheses and utilizes personal information from 66 anchors, along with data from 23,000 product links obtained from the backends of live commerce platforms.

The study emphasizes that KOLs with higher traffic significantly influence Gross Merchandise Volume (GMV). Intriguingly, KOLs with lower traffic levels exhibit a more pronounced effect on Return on Investment (ROI), highlighting their significance in driving profitability. Furthermore, the study explores the correlation between KOL hashtags and GMV/ROI and the intricate relationship between product types and KOL hashtags.

The findings significantly enhance the understanding of live shopping behavior and provide valuable insights for business management strategies. Practitioners can leverage this empirical evidence to make informed decisions, utilizing extensive data samples of KOLs and brands.

This research contributes unique insights into the live-streaming commerce industry using backend data from Live Streaming E-commerce platforms. The findings are more accurate based on market data than previous studies that relied on platform reviews or questionnaires. Additionally, this paper investigates the impact of KOLs on the performance of live e-commerce from three perspectives: GMV, ROI and hot-selling products.

Although user stickiness has been studied for several years in the field of live e-commerce, little attention has been paid to the effects of streamer attributes on user stickiness in this field. Rooted in the stimulus-organism-response (S-O-R) theory, this study investigated how streamer attributes influence user stickiness.

The authors obtained 496 valid samples from Chinese live e-commerce users and explored the formation of user stickiness using partial least squares-structural equation modeling (PLS-SEM). Artificial neural network (ANN) was used to capture linear and non-linear relationships and analyze the normalized importance ranking of significant variables, supplementing the PLS-SEM results.

The authors found that attractiveness and similarity positively impacted parasocial interaction (PSI). Expertise and trustworthiness positively impacted perceived information quality. Moreover, streamer-brand preference mediated the relationship between PSI and user stickiness, as well as the relationship between perceived information quality and user stickiness. Compared to PLS-SEM, the predictive ability of ANN was more robust. Further, the results of PLS-SEM and ANN both showed that attractiveness was the strongest predictor of user stickiness.

This study explained how streamer attributes affect user stickiness and provided a reference value for future research on user behavior in live e-commerce. The exploration of the linear and non-linear relationships between variables based on ANN supplements existing research. Moreover, the results of this study have implications for practitioners on how to improve user stickiness and contribute to the development of the livestreaming industry.

This study applies parasocial relationship theory to identify the role of broadcaster characteristics in the highly interactive business setting of live streaming commerce.

A total of 401 online questionnaires were distributed to individuals with live streaming showroom shopping experience, and SmartPLS software was used to analyse the data and test the hypotheses.

Broadcasters' characteristics are positively associated with viewers' parasocial relationships, thus further enhancing viewers' attitudinal and behavioural loyalty towards that broadcaster's streams. Parasocial relationships mediate the effects of most broadcaster characteristics (except for expertise) on attitudinal and behavioural loyalty. In addition, parasocial relationships have a stronger positive effect on viewer behaviours for hedonic products and under high match-up.

The broadcaster is a key indicator of the success of live streaming commerce. This study establishes a well-organized framework to understand how broadcaster characteristics influence viewer loyalty towards that broadcasters' streams based on parasocial relationship theory.

This paper critically examines the effectiveness of male anchor in cross-gender endorsements and questions whether it can truly deliver positive outcomes for advertisers in the context of live streaming. It explores the underlying mechanisms of this effect by examining the mediation effect of perceived gender-identity incongruence and the moderation effect of anchor presence.

Three experiments are conducted to examine the effect of cross-gender endorsement on purchase intention.

The findings from three experiments provide empirical evidence that the endorsement of female-gendered products by male anchors leads to a significant decrease in the evaluation of these products among female consumers. This negative effect is mediated by a sense of gender-identity incongruence experienced by female consumers. Furthermore, the study demonstrates that female customers exhibit higher purchase intent for female-gendered products endorsed by male virtual anchors compared to real anchors; however, the same pattern was not observed in the case of female anchors.

This paper empirically examines the possible negative effects of the male anchor endorsement in the live streaming context. It reveals the underlying mechanism of this negative effect, and how the virtual “presence” take a role in this underlying mechanism.

This paper reviews the pros and cons of different parametric modeling methods, which can provide a theoretical reference for parametric reconstruction of 3D human body models for virtual fitting.

In this study, we briefly analyze the mainstream datasets of models of the human body used in the area to provide a foundation for parametric methods of such reconstruction. We then analyze and compare parametric methods of reconstruction based on their use of the following forms of input data: point cloud data, image contours, sizes of features and points representing the joints. Finally, we summarize the advantages and problems of each method as well as the current challenges to the use of parametric modeling in virtual fitting and the opportunities provided by it.

Considering the aspects of integrity and accurate of representations of the shape and posture of the body, and the efficiency of the calculation of the requisite parameters, the reconstruction method of human body by integrating orthogonal image contour morphological features, multifeature size constraints and joint point positioning can better represent human body shape, posture and personalized feature size and has higher research value.

This article obtains a research thinking for reconstructing a 3D model for virtual fitting that is based on three kinds of data, which is helpful for establishing personalized and high-precision human body models.

This study aims to investigate the effect of post-treatment on anti-corrosion performance of Al coating on the surface of Ti-6Al-4V (TC4) fastener.

The Al coatings with different layer structures were prepared on TC4 by middle-frequency and direct-current combined magnetron sputtering. The cross-sectional morphology and surface roughness of coatings were characterized by scanning electron microscope and atomic force microscope. The corrosion resistance was evaluated by electrochemical method. The monolayer coating was post-treated by Alodine chemical conversion, Ar⁺ bombardment and a combination of two methods above.

The results show that the interfaces in bilayer and trilayer coatings reduce the defects. Ar⁺ bombardment reduces the corrosion current density, and Alodine chemical conversion leads to a higher pitting corrosion potential. The combined post-treatment has the highest polarization resistance.

The corrosion resistance of the Al coating is enhanced as the layer quantity increases. The combination of two post-treatments, Ar⁺ bombardment and Alodine chemical conversion, could achieve an overall improvement in corrosion resistance of Al coating.