Electronic Commerce Research and Applications最新文献

We propose a comprehensive profit-sensitive approach for credit risk modeling in P2P lending for small businesses, one of the most financially complex segments. We go beyond traditional and cost-sensitive approaches by including the financial costs and incomes through profits and introducing the profit information at three points of the modeling process: the estimation of the learning function of the classification algorithm (XGBoost in our case), the hyperparameter optimization, and the decision function. The profit-sensitive approaches achieve a higher level of profitability than the profit-insensitive approach in the small business case analyzed by granting mostly lower-risk, lower-amount loans. Explainability tools help us to discover the key features of such loans. Our proposal can be extended to other loan markets or other classification problems as long as the cells of the misclassification matrix have an economic value.

Consumer loyalty plays a significant role in the sustainable marketing of classic large-scale online social promotions (CLOSPs). However, existing research mainly focuses on the single consumption behavior of consumers, overlooking the exploration of consumer CLOSPs loyalty from both cognitive and behavioral perspectives. This study aims to bridge this gap in the literature by exploring the impact mechanism of environmental factors on consumer loyalty in CLOSPs based on signaling theory and social cognitive theory. We apply a mixed-methods design containing both qualitative and quantitative stages. The research results show that perceived promotional incentives are influenced by three types of environmental signals: social-, product-, and platform-related signals. Subjective norms, relationship benefits, product involvement, and path dependence form consumer loyalty by influencing consumer cognition (including flow experience and satisfaction). Subjective norms and relationship benefits correspond to the passive and active dimensions of social-related signals, respectively. Further, three configurations can lead to high levels of consumer loyalty to CLOSPs. Our findings propose that e-commerce practitioners should leverage environmental signals to stimulate perceived promotional incentives and foster high loyalty to CLOSPs.

Artificial intelligence (AI) chatbot have become increasingly popular as a tool for improving employee productivity over the last few years. In the early stages of AI chatbot development, exploring the impact of AI chatbot service failures on user reusage intention is useful for coordinating human–computer interaction and optimizing AI chatbot service mechanisms. The extant literature on AI service failures focuses on service recovery and anthropomorphism. There is less literature comparing different types of service failures and their effects. The article includes three studies. First, a randomized group experiment was conducted with 120 respondents. The results showed significant differences in the impact of different AI chatbot service failures on user reusage intentions. Second, an online questionnaire was completed by 386 respondents, the results found specific impact mechanisms of service failures on user reusage intentions. Third, an interview survey was conducted with 15 customers using AI chatbots to verify the findings of Study 1 and Study 2. Furthermore determine the boundary conditions for the unsupported hypotheses through meta-inference. The research enriches the literature on relationship marketing and expands the attribution theory of service failures. In addition, which provides theoretical basis and practical support for companies to reduce adverse effects of service failures.

This paper analyzes the manufacturer and retailer’s advertising and pricing strategies within three typical modes of advertising under manufacturer encroachment and derives the optimal advertising mode. We find that if the supply chain members choose to advertise, compared to the scenario without manufacturer encroachment, the manufacturer gets more profit attributed to the expanded demand and advertising efforts, but the retailer gets more profit only if the advertising effectiveness is high. Then, we summarize that when the unit advertising cost is low, the supply chain members do not advertise under manufacturer encroachment. Thirdly, we find that retailer advertising cannot be the optimal advertising mode for the manufacturer. When the unit advertising cost is high and the substitutability level is low, joint advertising is optimal; otherwise, manufacturer advertising is optimal. Finally, we delve into the cost-sharing joint advertising strategy of the supply chain members, and find that within the scenario of cost-sharing joint advertising, the manufacturer can get more profit at the retailer’s expense compared to other advertising modes.

This study proposes a heterogeneous recommendation model that does not rely on data sharing. Previous studies have predominantly focused on nested homogeneous domains that share data. However, this approach encounters issues as it could lead to diminished recommendation performance when there is a scarcity of redundant data within these domains. To overcome these challenges, we propose the HeteLFX model, which extracts and bridges the latent features (LF) of each domain. This model resolves the problems by leveraging the metainformation of domain items to generate an LF. LF is extracted for each domain, and bridges are established based on the relevance of the latent knowledge, thereby enabling heterogeneous recommendations. The efficacy of the HeteLFX model was assessed by comparing it with four other heterogeneous recommendation systems, which are variants of X-Map and NX-Map. The results revealed that the HeteLFX model improved performance by reducing the mean absolute error (MAE) by approximately 0.3, thereby underscoring the superiority of the model. Additionally, HeteLFX reduced the MAE by up to approximately 0.45, depending on the relevance of the data within the domain.

The rise of the sharing economy has transformed traditional housing rental practices, with short-term rental (STR) emerging as a successful model in the accommodation sector. However, information asymmetry and trust issues pose significant challenges within STR platforms, emphasizing the importance of improving user stickiness. This study utilizes a two-stage, multi-method approach to validate the dimensions of perceived justice among guests in STR settings and their impact on user stickiness. The results demonstrate that guests’ perceptions of justice are primarily influenced by dimensions such as distributive, interpersonal, informational, and procedural justice, which in turn positively affect platform stickiness through the mediation of trust and relationship commitment. These findings offer valuable insights for addressing justice concerns and enhancing user stickiness in the STR landscape.

Objective

The problem of low model performance caused by the lack of negative samples in the recommendation method based on implicit feedback information can be solved.

Methods

The implicit feedback recommendation model DAEGAN is constructed based on the conditional generative adversarial network framework. The Denoising Auto-Encoder is used as a generator to capture nonlinear potential factors in the interaction and improve the robustness of model. In this paper, a strong and weak negative sampling strategy is proposed, which combines the visibility of user in time points to mine uninteresting items and acquire strong negative samples, and injects these information into the model by modifying the masking mechanism to solve the problem of missing negative samples.

Results

Experiments on MovieLens 100 K, Amazon Movie and TV, MovieLens 1 M datasets show that the recommendation accuracy of CFGAN based on strong and weak negative sampling and DAEGAN proposed in this paper has been improved.

Limitations

The generation of strong negative samples is based on user interaction records, which cannot solve effectively cold start problems in extremely sparse data.

Conclusions

After DAEGAN application, the strong and weak negative sampling method proposed in this paper has generally higher recommendation accuracy than those mainstream recommendation algorithms. The code is available at https://github.com/nanjingzhuyuxuan/DAEGAN.

In the evolving landscape of food e-commerce live streaming, the profusion of textual data, marked by an excess of promotional vernacular and unstructured formats, presents a formidable challenge for event extraction. Addressing these hurdles, we introduce a tailored ontology-based method alongside FMLEE (Food Marketing Live Event Extraction), a joint event extraction algorithm. This approach simplifies the event identification process through meticulous segmentation and the development of an ontology comprising 5 event categories and 19 argument roles. By integrating context-aware embeddings derived from pre-trained language models and applying an adversarial learning tactic, our methodology not only bolsters the robustness of our model but also significantly refines its accuracy in discerning relevant events within the scarce-resource milieu of food live streaming promotions. The effectiveness of the FMLEE model is validated by its achievement of an F1 score of 73.05%, with the inclusion of adversarial learning contributing to a 2.61% enhancement in performance. This evidences our novel contribution to the domain, offering robust technical support for the optimal exploitation of information within the sphere of food live streaming promotions. Simultaneously, this aids in the investigation of innovative applications for consumer engagement within marketing strategies and the smart regulation of marketing activities.

In this paper, we introduce the optimization of hybrid delivery by vehicle and drones. Hybrid delivery by vehicle and drones is advantageous for improving O2O last-mile delivery efficiency. However, vehicle stop selection and drone delivery sortie arrangement are challenging in the optimization of hybrid delivery by vehicle and drones because cyclic sorties and forward sorties jointly influence the total makespan of the delivery. To minimize the delivery makespan, an MILP model for hybrid delivery is formulated considering both the cyclic sorties and forward sorties of drones. In the proposed model, the intertwined influences of the flight times of cyclic and forward sorties and their further effects on total delivery makespan are depicted. Additionally, we introduce an ACO based on set covering for the selection of vehicle stops and a customized HGSADC for the arrangement of drone sorties. A study based on a simulated case and experiments based on 40 generated instances at different scales are explored to assess the optimization of hybrid delivery by vehicle and drones.

A signaling game model is constructed in the framework of a supply chain system consisting of a financially constrained supplier and an e-commerce platform acting as marketplace and a creditor simultaneously. The primary concern of this work is to investigate how the e-commerce platform, which has superior information about market demand, indirectly communicates this information to the financially constrained supplier through its marketing efforts. Under both separating and pooling equilibria, the decisions and profits of each member of the supply chain are firstly considered. Furthermore, using an “intuitive criterion”, the e-commerce platform’s dominant strategy and its influencing factors are analyzed. The results show that when there is a significant difference in the marginal marketing costs, the platform tends to choose the separating equilibrium. When the difference in marginal marketing costs is relatively slight, the e-commerce platform’s dominant strategy depends on the capital of the supplier and the level of market demand fluctuations. Specifically, the e-commerce platform will select the pooling equilibrium when market demand fluctuations are minimal, but the platform will select the separating equilibrium when market demand fluctuations are substantially large. If the supplier’s capital is increased within a certain range, the e-commerce platform is more motivated to select the pooling equilibrium. In addition, the platform usage fee ratio, the platform loan interest rate and the supplier’s prior beliefs are important factors influencing the platform’s decision.