Hasil untuk "Commerce"

Lawrence Lessig

F. Bélanger, J. Hiller, W. Smith

Abdelsalam H. Busalim, Ab Razak Che Hussin

Yupeng Li, Ben Chen, Mingyue Cheng et al.

E-commerce search serves as a central interface, connecting user demands with massive product inventories and plays a vital role in our daily lives. However, in real-world applications, it faces challenges, including highly ambiguous queries, noisy product texts with weak semantic order, and diverse user preferences, all of which make it difficult to accurately capture user intent and fine-grained product semantics. In recent years, significant advances in large language models (LLMs) for semantic representation and contextual reasoning have created new opportunities to address these challenges. Nevertheless, existing e-commerce search datasets still suffer from notable limitations: queries are often heuristically constructed, cold-start users and long-tail products are filtered out, query and product texts are anonymized, and most datasets cover only a single stage of the search pipeline. Collectively, these issues constrain research on LLM-based e-commerce search. To address these challenges, we construct and release KuaiSearch. To the best of our knowledge, it is the largest e-commerce search dataset currently available. KuaiSearch is built upon real user search interactions from the Kuaishou platform, preserving authentic user queries and natural-language product texts, covering cold-start users and long-tail products, and systematically spanning three key stages of the search pipeline: recall, ranking, and relevance judgment. We conduct a comprehensive analysis of KuaiSearch from multiple perspectives, including products, users, and queries, and establish benchmark experiments across several representative search tasks. Experimental results demonstrate that KuaiSearch provides a valuable foundation for research on real-world e-commerce search.

Xianjie Liu, Yiman Hu, Liang Wu et al.

E-commerce short videos represent a high-revenue segment of the online video industry characterized by a goal-driven format and dense multi-modal signals. Current models often struggle with these videos because existing benchmarks focus primarily on general-purpose tasks and neglect the reasoning of commercial intent. In this work, we first propose a multi-modal information density assessment framework to quantify the complexity of this domain. Our evaluation reveals that e-commerce content exhibits substantially higher density across visual, audio, and textual modalities compared to mainstream datasets, establishing a more challenging frontier for video understanding. To address this gap, we introduce E-commerce Video Ads Benchmark (E-VAds), which is the first benchmark specifically designed for e-commerce short video understanding. We curated 3,961 high-quality videos from Taobao covering a wide range of product categories and used a multi-agent system to generate 19,785 open-ended Q&A pairs. These questions are organized into two primary dimensions, namely Perception and Cognition and Reasoning, which consist of five distinct tasks. Finally, we develop E-VAds-R1, an RL-based reasoning model featuring a multi-grained reward design called MG-GRPO. This strategy provides smooth guidance for early exploration while creating a non-linear incentive for expert-level precision. Experimental results demonstrate that E-VAds-R1 achieves a 109.2% performance gain in commercial intent reasoning with only a few hundred training samples.

Alice Oleto, Rafael Alcadipani, José Vitor Palhares

Objective: this study aims to understand the consequences and reactions of women victims of sexual harassment in organizations. Methods: a qualitative research design was adopted, based on the principles of grounded theory. Data were collected through 43 interviews with women working in Brazilian organizations who reported experiences of sexual harassment. Results: the findings reveal that sexual harassment in the workplace has severe consequences for women’s physical and mental health, often subjecting them to degrading and traumatizing situations. Common reactions include self-blame and the silencing of the violence due to fear of dismissal or feelings of shame. Conclusions: the study highlights the urgent need for further research on sexual harassment in the workplace within the field of business administration. It also calls for the development of organizational practices aimed at preventing and addressing such violence, regardless of the victim’s position within the company.

Tao Wen, Ziwei Wang, Shuang Wang

The study aims to explore the impact mechanism of brand ritual on online word-of-mouth communication, introducing the mediating variable—flow experience—and the moderating variable—consumer–brand relationship norms. The study uses the approach of the experimental research. In Experiment 1, with the watch as the experimental product and the advertisement as the online scene, 62 subjects in the pre-experiment and 132 subjects in the formal experiment are recruited to verify the main effect of brand ritual on online word-of-mouth communication. In Experiment 2, with the tea bag as the experimental product and the online press conference as the online scene, 73 subjects in the pre-experiment and 185 subjects in the formal experiment are recruited to verify the mediating role of flow experience in the impact of brand ritual on online word-of-mouth communication. In Experiment 3, with the scented candle as the experimental product and the promotional video of the e-commerce store as the online scene, 81 subjects in the pre-experiment and 269 subjects in the formal experiment are recruited to verify the moderating role of consumer–brand relationship norms in the impact of brand ritual on online word-of-mouth communication/flow experience. The results show that brand ritual is more effective in promoting online word-of-mouth communication than random action, flow experience plays a completely mediating role in the impact of brand ritual on online word-of-mouth communication, and consumer–brand relationship norms play a moderating role in the impact of brand ritual on online word-of-mouth communication/flow experience. The study not only reveals the impact mechanism of brand ritual on online word-of-mouth communication, but also provides strong guidance for companies to utilize brand ritual, flow experience, and consumer–brand relationship norms to promote online word-of-mouth communication.

Biliqees Ayoola ABDULMUMIN, Hafsat Olatanwa AFOLABI, Bashirat Oluwafunke OLOYIN-ABDULHAKEEM et al.

The objective of our paper is to examine the nexus between firms' characteristics and debt maturity structure in Nigeria. The financial statements of all oil and gas listed firms in Nigeria between 2012 and 2023 provided the secondary data used in the study. The study was examined using panel fixed effect data analysis and Generalized Method of Moments (GMM) estimator. The study's findings showed that, at the 5% level of significance, debt maturity structure is positively impacted by liquidity, asset structure, size and profitability. However, debt maturity structure is negatively significantly impacted by non-debt tax shields. The study shows that firms' characteristics have significant impact on debt maturity structure. Therefore, it was recommended that management of oil & gas companies should pursue efficiency in order to minimize the usage of debt in the capital structure option. Unlike previous empirical work in this area, the study addresses potential variable bias. Also it examines the direction of casualty between the firm characteristics and debt structure. This provides a more robust and accurate understanding of the subject matter.

Mariya Hendriksen, Svitlana Vakulenko, Jordan Massiah et al.

Large Language Models (LLMs) are transforming personalized search, recommendations, and customer interaction in e-commerce. Customers increasingly shop across multiple devices, from voice-only assistants to multimodal displays, each offering different input and output capabilities. A proactive suggestion to switch devices can greatly improve the user experience, but it must be offered with high precision to avoid unnecessary friction. We address the challenge of predicting when a query requires visual augmentation and a cross-device switch to improve product discovery. We introduce Image-Seeking Intent Prediction, a novel task for LLM-driven e-commerce assistants that anticipates when a spoken product query should proactively trigger a visual on a screen-enabled device. Using large-scale production data from a multi-device retail assistant, including 900K voice queries, associated product retrievals, and behavioral signals such as image carousel engagement, we train IRP (Image Request Predictor), a model that leverages user input query and corresponding retrieved product metadata to anticipate visual intent. Our experiments show that combining query semantics with product data, particularly when improved through lightweight summarization, consistently improves prediction accuracy. Incorporating a differentiable precision-oriented loss further reduces false positives. These results highlight the potential of LLMs to power intelligent, cross-device shopping assistants that anticipate and adapt to user needs, enabling more seamless and personalized e-commerce experiences.

Sumaiya Tabassum

Sentiment analysis is an essential part of text analysis, which is a larger field that includes determining and evaluating the author's emotional state. This method is essential since it makes it easier to comprehend consumers' feelings, viewpoints, and preferences holistically. The introduction of large language models (LLMs), such as Llama, has greatly increased the availability of cutting-edge model applications, such as sentiment analysis. However, accurate sentiment analysis is hampered by the intricacy of written language and the diversity of languages used in evaluations. The viability of using transformer-based BERT models and other LLMs for sentiment analysis from Bangladesh e commerce reviews is investigated in this paper. A subset of 4000 samples from the original dataset of Bangla and English customer reviews was utilized to fine-tune the model. The fine tuned Llama-3.1-8B model outperformed other fine-tuned models, including Phi-3.5-mini-instruct, Mistral-7B-v0.1, DistilBERT-multilingual, mBERT, and XLM-R-base, with an overall accuracy, precision, recall, and F1 score of 95.5%, 93%, 88%, 90%. The study emphasizes how parameter efficient fine-tuning methods (LoRA and PEFT) can lower computational overhead and make it appropriate for contexts with limited resources. The results show how LLMs can

Aysenur Kulunk, Berk Taskin, M. Furkan Eseoglu et al.

In large scale e-commerce marketplaces, duplicate product listings frequently cause consumer confusion and operational inefficiencies, degrading trust on the platform and increasing costs. Traditional keyword-based search methodologies falter in accurately identifying duplicates due to their reliance on exact textual matches, neglecting semantic similarities inherent in product titles. To address these challenges, we introduce a scalable, multimodal product deduplication designed specifically for the e-commerce domain. Our approach employs a domain-specific text model grounded in BERT architecture in conjunction with MaskedAutoEncoders for image representations. Both of these architectures are augmented with dimensionality reduction techniques to produce compact 128-dimensional embeddings without significant information loss. Complementing this, we also developed a novel decider model that leverages both text and image vectors. By integrating these feature extraction mechanisms with Milvus, an optimized vector database, our system can facilitate efficient and high-precision similarity searches across extensive product catalogs exceeding 200 million items with just 100GB of system RAM consumption. Empirical evaluations demonstrate that our matching system achieves a macro-average F1 score of 0.90, outperforming third-party solutions which attain an F1 score of 0.83. Our findings show the potential of combining domain-specific adaptations with state-of-the-art machine learning techniques to mitigate duplicate listings in large-scale e-commerce environments.

Zhe Zhang, Young Kwark, Srinivasan Raghunathan et al.

The use of sponsored product listings in prominent positions of consumer search results has made e-commerce platforms, which traditionally serve as marketplaces for third-party sellers to reach consumers, a major medium for those sellers to advertise their products. On the other hand, regulators have expressed anti-trust concerns about an e-commerce platform's integration of marketplace and advertising functions; they argue that such integration benefits the platform and sellers at the expense of consumers and society and have proposed separating the advertising function from those platforms. We show, contrary to regulators' concerns, that separating the advertising function from the e-commerce platform benefits the sellers, hurts the consumers, and does not necessarily benefit the social welfare. A key driver of our findings is that an independent advertising firm, which relies solely on advertising revenue, has same or lesser economic incentive to improve targeting precision than an e-commerce platform that also serves as the advertising medium, even if both have the same ability to target consumers. This is because an improvement in targeting precision enhances the marketplace commission by softening the price competition between sellers, but hurts the advertising revenue by softening the competition for prominent ad positions.

Ravinder Jangra, Etender Singh, Sunil Manglaw et al.

پیشینه: ارزیابی ظرفیت ، جزء مهمی در حفظ پایداری در بخش گردشگری است. تمام نگرانی‌ها در گردشگری به تعداد گردشگرانی که از یک مکان خاص بازدید می‌کنند، مرتبط است. منطقه مورد مطالعه دارای مناظر زیبا در اکوسیستم بیابان سرد و همچنین ویژگی‌های متمایز بودایی است که گردشگری انبوه را جذب می‌کند. امروزه، توسعه گردشگری نگرانی‌هایی را در مورد پایداری و ایجاد استانداردهایی برای قابلیت‌های مقصد گردشگری ایجاد کرده است. اهداف: مطالعه حاضر با هدف تجزیه و تحلیل اهداف زیر انجام می‌شود: 1) ارزیابی ظرفیت برد فیزیکی (PCC)، ظرفیت برد واقعی (RCC) و ظرفیت برد مؤثر (ECC) نقاط گردشگری منتخب در روستای ناکو و 2) محاسبه ظرفیت پارکینگ صومعه. روش شناسی: روش‌های مشخص‌شده در اتحادیه بین‌المللی حفاظت از طبیعت و منابع طبیعی (IUCN) برای اندازه‌گیری ظرفیت برد مقاصد گردشگری خاص در ناکو استفاده شد. تکنیک‌های سه سطحی برای ارزیابی ظرفیت برد فیزیکی (۲۸۱۶۱ نفر)، ظرفیت برد واقعی (۴۱۶۲ نفر) و ظرفیت برد مؤثر (۲۹۶۸ نفر) به کار گرفته شد. نتایج: نتایج نشان می‌دهد که ظرفیت برد مؤثر (ECC) مناسب‌ترین روش برای تخمین است و وضعیت فعلی گردشگری در منطقه مورد مطالعه کمتر از ظرفیت خود بهره‌برداری شده است. نتیجه‌گیری: سیستم‌های بسیار کوچک تا بزرگ در ناکو یافت می‌شوند و این سیستم‌ها از انواع مختلف فعالیت‌ها نیز پشتیبانی می‌کنند. گردشگری یک فعالیت بسیار رایج است و تأثیرات زیست‌محیطی، اجتماعی، فرهنگی و اقتصادی دارد. این تأثیرات به پارامترهای مختلفی وابسته بوده و با تغییر ماهیت تعامل نیز تغییر می‌کنند. مشخص شده است که وضعیت فعلی فعالیت گردشگری در منطقه مورد مطالعه در مقایسه با ظرفیت برد آن، بسیار کمتر از حد بهره‌برداری قرار گرفته است.

Wenxuan Ding, Weiqi Wang, Sze Heng Douglas Kwok et al.

Enhancing Language Models' (LMs) ability to understand purchase intentions in E-commerce scenarios is crucial for their effective assistance in various downstream tasks. However, previous approaches that distill intentions from LMs often fail to generate meaningful and human-centric intentions applicable in real-world E-commerce contexts. This raises concerns about the true comprehension and utilization of purchase intentions by LMs. In this paper, we present IntentionQA, a double-task multiple-choice question answering benchmark to evaluate LMs' comprehension of purchase intentions in E-commerce. Specifically, LMs are tasked to infer intentions based on purchased products and utilize them to predict additional purchases. IntentionQA consists of 4,360 carefully curated problems across three difficulty levels, constructed using an automated pipeline to ensure scalability on large E-commerce platforms. Human evaluations demonstrate the high quality and low false-negative rate of our benchmark. Extensive experiments across 19 language models show that they still struggle with certain scenarios, such as understanding products and intentions accurately, jointly reasoning with products and intentions, and more, in which they fall far behind human performances. Our code and data are publicly available at https://github.com/HKUST-KnowComp/IntentionQA.

Wendi Zhou, Tianyi Li, Pavlos Vougiouklis et al.

Identifying and understanding user intents is a pivotal task for E-Commerce. Despite its essential role in product recommendation and business user profiling analysis, intent understanding has not been consistently defined or accurately benchmarked. In this paper, we focus on predicative user intents as "how a customer uses a product", and pose intent understanding as a natural language reasoning task, independent of product ontologies. We identify two weaknesses of FolkScope, the SOTA E-Commerce Intent Knowledge Graph: category-rigidity and property-ambiguity. They limit its ability to strongly align user intents with products having the most desirable property, and to recommend useful products across diverse categories. Following these observations, we introduce a Product Recovery Benchmark featuring a novel evaluation framework and an example dataset. We further validate the above FolkScope weaknesses on this benchmark. Our code and dataset are available at https://github.com/stayones/Usgae-Centric-Intent-Understanding.

Tim Ellis, Briland Hitaj, Ulf Lindqvist et al.

Space systems enable essential communications, navigation, imaging and sensing for a variety of domains, including agriculture, commerce, transportation, and emergency operations by first responders. Protecting the cybersecurity of these critical infrastructure systems is essential. While the space environment brings unique constraints to managing cybersecurity risks, lessons learned about risks and effective defenses in other critical infrastructure domains can help us to design effective defenses for space systems. In particular, discoveries regarding cybersecurity for industrial control systems (ICS) for energy, manufacturing, transportation, and the consumer and industrial Internet of Things (IoT) offer insights into cybersecurity for the space domain. This paper provides an overview of ICS and space system commonalities, lessons learned about cybersecurity for ICS that can be applied to space systems, and recommendations for future research and development to secure increasingly critical space systems.

Meizi Zhou, Zhuoye Ding, Jiliang Tang et al.

Miao Cui, S. Pan, S. Newell et al.

Hui Han, S. Trimi

Abstract Reverse logistics initiatives with social commerce not only provide opportunities for firms to create new sources of revenue but also demonstrate their corporate social responsibility via social, green, and environmental activities. Thus, a growing number of companies are attempting to streamline their social commerce platforms to effectively handle reverse logistics. The purpose of this study is to identify the criteria that should be used in designing and evaluating social commerce based reverse logistics processes by firms. We tested the effectiveness of the identified criteria by using them to evaluate the reverse logistics practices of three major global firms that use social commerce platforms. First, we identified the criteria from a thorough review of the literature. Then, we invited five experts to provide (linguistic) ratings of these firms on the selected criteria, using a fuzzy Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) technique with FLINTSTONES (a software tool) to generate aggregate scores for the assessment and evaluation of reverse logistics practices in social commerce platforms. Sensitivity analysis was also provided to monitor the robustness of the approach. The results of the study identified that four dominant criteria (reverse logistics performance indicators) in the social commerce platform: Customer relationship, Usage risk, Reviews, and Quality control.

Namil Kim, Wonjoon Kim