Hasil untuk "Commerce"

Renqi Chen, Zeyin Tao, Jianming Guo et al.

Graphical User Interface (GUI) agents show strong capabilities for automating web tasks, but existing interactive benchmarks primarily target benign, predictable consumer environments. Their effectiveness in high-stakes, investigative domains such as authentic e-commerce risk management remains underexplored. To bridge this gap, we present RiskWebWorld, the first highly realistic interactive benchmark for evaluating GUI agents in e-commerce risk management. RiskWebWorld features 1,513 tasks sourced from production risk-control pipelines across 8 core domains, and captures the authentic challenges of risk operations on uncooperative websites, partially environmental hijackments. To support scalable evaluation and agentic reinforcement learning (RL), we further build a Gymnasium-compliant infrastructure that decouples policy planning from environment mechanics. Our evaluation across diverse models reveals a dramatic capability gap: top-tier generalist models achieve 49.1% success, while specialized open-weights GUI models lag at near-total failure. This highlights that foundation model scale currently matters more than zero-shot interface grounding in long-horizon professional tasks. We also demonstrate the viability of our infrastructure through agentic RL, which improves open-source models by 16.2%. These results position RiskWebWorld as a practical testbed for developing robust digital workers.

Chenghan Fu, Daoze Zhang, Yukang Lin et al.

We introduce MOON, our comprehensive set of sustainable iterative practices for multimodal representation learning for e-commerce applications. MOON has already been fully deployed across all stages of Taobao search advertising system, including retrieval, relevance, ranking, and so on. The performance gains are particularly significant on click-through rate (CTR) prediction task, which achieves an overall +20.00% online CTR improvement. Over the past three years, this project has delivered the largest improvement on CTR prediction task and undergone five full-scale iterations. Throughout the exploration and iteration of our MOON, we have accumulated valuable insights and practical experience that we believe will benefit the research community. MOON contains a three-stage training paradigm of "Pretraining, Post-training, and Application", allowing effective integration of multimodal representations with downstream tasks. Notably, to bridge the misalignment between the objectives of multimodal representation learning and downstream training, we define the exchange rate to quantify how effectively improvements in an intermediate metric can translate into downstream gains. Through this analysis, we identify the image-based search recall as a critical intermediate metric guiding the optimization of multimodal models. Over three years and five iterations, MOON has evolved along four critical dimensions: data processing, training strategy, model architecture, and downstream application. The lessons and insights gained through the iterative improvements will also be shared. As part of our exploration into scaling effects in the e-commerce field, we further conduct a systematic study of the scaling laws governing multimodal representation learning, examining multiple factors such as the number of training tokens, negative samples, and the length of user behavior sequences.

Ariful Islam, Md Rifat Hossen, Abir Ahmed et al.

Aspect-Based Sentiment Analysis (ABSA) has emerged as a critical tool for extracting fine-grained sentiment insights from user-generated content, particularly in e-commerce and social media domains. However, research on Bangla ABSA remains significantly underexplored due to the absence of comprehensive datasets and specialized frameworks for triplet extraction in this language. This paper introduces BanglaASTE, a novel framework for Aspect Sentiment Triplet Extraction (ASTE) that simultaneously identifies aspect terms, opinion expressions, and sentiment polarities from Bangla product reviews. Our contributions include: (1) creation of the first annotated Bangla ASTE dataset containing 3,345 product reviews collected from major e-commerce platforms including Daraz, Facebook, and Rokomari; (2) development of a hybrid classification framework that employs graph-based aspect-opinion matching with semantic similarity techniques; and (3) implementation of an ensemble model combining BanglaBERT contextual embeddings with XGBoost boosting algorithms for enhanced triplet extraction performance. Experimental results demonstrate that our ensemble approach achieves superior performance with 89.9% accuracy and 89.1% F1-score, significantly outperforming baseline models across all evaluation metrics. The framework effectively addresses key challenges in Bangla text processing including informal expressions, spelling variations, and data sparsity. This research advances the state-of-the-art in low-resource language sentiment analysis and provides a scalable solution for Bangla e-commerce analytics applications.

Teri Rumble, Zbyněk Gazdík, Javad Zarrin et al.

Recent advancements in Large Language Models (LLMs) have transformed Natural Language Processing (NLP), enabling complex information retrieval and generation tasks. Retrieval-Augmented Generation (RAG) has emerged as a key innovation, enhancing factual accuracy and contextual grounding by integrating external knowledge sources with generative models. Although RAG demonstrates strong performance on unstructured text, its application to structured knowledge graphs presents challenges: scaling retrieval across connected graphs and preserving contextual relationships during response generation. Cross-encoders refine retrieval precision, yet their integration with structured data remains underexplored. Addressing these challenges is crucial for developing domain-specific assistants that operate in production environments. This study presents the design and comparative evaluation of multiple Retriever-Reranker pipelines for knowledge graph natural language queries in e-Commerce contexts. Using the STaRK Semi-structured Knowledge Base (SKB), a production-scale e-Commerce dataset, we evaluate multiple RAG pipeline configurations optimized for language queries. Experimental results demonstrate substantial improvements over published benchmarks, achieving 20.4% higher Hit@1 and 14.5% higher Mean Reciprocal Rank (MRR). These findings establish a practical framework for integrating domain-specific SKBs into generative systems. Our contributions provide actionable insights for the deployment of production-ready RAG systems, with implications that extend beyond e-Commerce to other domains that require information retrieval from structured knowledge bases.

Xianren Zhang, Shreyas Prasad, Di Wang et al.

Web agents have shown great promise in performing many tasks on ecommerce website. To assess their capabilities, several benchmarks have been introduced. However, current benchmarks in the e-commerce domain face two major problems. First, they primarily focus on product search tasks (e.g., Find an Apple Watch), failing to capture the broader range of functionalities offered by real-world e-commerce platforms such as Amazon, including account management and gift card operations. Second, existing benchmarks typically evaluate whether the agent completes the user query, but ignore the potential risks involved. In practice, web agents can make unintended changes that negatively impact the user account or status. For instance, an agent might purchase the wrong item, delete a saved address, or incorrectly configure an auto-reload setting. To address these gaps, we propose a new benchmark called Amazon-Bench. To generate user queries that cover a broad range of tasks, we propose a data generation pipeline that leverages webpage content and interactive elements (e.g., buttons, check boxes) to create diverse, functionality-grounded user queries covering tasks such as address management, wish list management, and brand store following. To improve the agent evaluation, we propose an automated evaluation framework that assesses both the performance and the safety of web agents. We systematically evaluate different agents, finding that current agents struggle with complex queries and pose safety risks. These results highlight the need for developing more robust and reliable web agents.

Jiahao Zhu, Jipeng Qiang, Ran Bai et al.

E-commerce live streaming in China, particularly on platforms like Douyin, has become a major sales channel, but hosts often use morphs to evade scrutiny and engage in false advertising. This study introduces the Live Auditory Morph Resolution (LiveAMR) task to detect such violations. Unlike previous morph research focused on text-based evasion in social media and underground industries, LiveAMR targets pronunciation-based evasion in health and medical live streams. We constructed the first LiveAMR dataset with 86,790 samples and developed a method to transform the task into a text-to-text generation problem. By leveraging large language models (LLMs) to generate additional training data, we improved performance and demonstrated that morph resolution significantly enhances live streaming regulation.

Yogesh Gajula

E-commerce platforms generate vast volumes of user feedback, such as star ratings, written reviews, and comments. However, most recommendation engines rely primarily on numerical scores, often overlooking the nuanced opinions embedded in free text. This paper comprehensively reviews sentiment-aware recommendation systems from a natural language processing perspective, covering advancements from 2023 to early 2025. It highlights the benefits of integrating sentiment analysis into e-commerce recommenders to enhance prediction accuracy and explainability through detailed opinion extraction. Our survey categorizes recent work into four main approaches: deep learning classifiers that combine sentiment embeddings with user item interactions, transformer based methods for nuanced feature extraction, graph neural networks that propagate sentiment signals, and conversational recommenders that adapt in real time to user feedback. We summarize model architectures and demonstrate how sentiment flows through recommendation pipelines, impacting dialogue-based suggestions. Key challenges include handling noisy or sarcastic text, dynamic user preferences, and bias mitigation. Finally, we outline research gaps and provide a roadmap for developing smarter, fairer, and more user-centric recommendation tools.

شيماء جاسم خضير

 يحاول البحث تسليط الضوء  على نطاق تأثير ادارة التنوع في تعزيز الانتماء الوظيفي في صفوف موظفي جامعة ذي قار ، وتحليل  العلاقة للمتغيرين (ادارة التنوع ) المتغير المستقل بأبعاده (البعد الداخلي، البعد الخارجي، البعد التنظيمي) (الانتماء الوظيفي) المتغير التابع  بأبعاده (الانتماء المؤثر او العاطفي ،الانتماء المتواصل او الاستمراري، الانتماء المعياري او الادبي)، ولاستكشاف طبيعة هذا التأثير استعمل البحث نموذج ورقة استبيان  وزعت على العينة المبحوثة  المقدر عددهم (50 ) فرداً ضمت الموظفين الجامعيين في جامعة ذي قار ، خضعت البيانات التي تم جمعها للتحليل الاحصائي بواسطة برنامج (SPSS.V.24) .  واسفرت نتائج البحث الى وجود علاقة ارتباط وتأثير بين المتغيّر المستقل ادارة التنوع بأبعاده (البعد الداخلي، البعد الخارجي، البعد التنظيمي) مع المتغير التابع الانتماء الوظيفي بأبعاده (الانتماء المؤثر او العاطفي ،الانتماء المتواصل او الاستمراري، الانتماء المعياري او الادبي) ،  وذلك لما اظهرته النتائج حيث أن 77 % من التغيرات الحاصلة في الانتماء الوظيفي يمكن تفسيرها عبر ادارة التنوع  ، واعتماداً على النتائج التي بينها البحث اقترحت الباحثة ضرورة التقصي في مبررات ترك العاملين للعمل من قبل القيادات الادارية وفهم رغبات العاملين المتعددة لضمان تحقيق الانتماء المنشود في المؤسسة.

Maria Priska Minda, Ni Komang Prasiani, I Made Satrya Ramayu

Tujauan dilakukan penelitian ini adalah untuk menganalisi pengaruh digital marketing, kualitas layanan, dan word of mouth terhadap peningkatan brand awareness di Konek Market. Penelitian ini menggunakan sampel sebanyak 85 responden yang adalah pengguna aktif Konek Market selama 4 bulan (September 2024-Januari 2025). Teknik yang digunakam dalam pengambilan sampel yaitu purposive sampling. Penelitian ini menggunakan metode kuantitatif. Teknik pengumpulan data yaitu dengan menggunakan kuesioner, dan teknik analisis data yang digunakan adalah regresi linear berganda. Hasil penelitian menunjukan  bahwa secara parsial, digital marketing tidak berpengaruh signifikan terhadap peningkatan brand awareness di Konek Market. Sebaliknya, kualitas layanan dan word of mouth berpengaruh positif dan signifikan terhadap peningkatan brand awareness di Konek Market. Word of mouth merupakan variabel yang memiliki pengaruh paling penting dalam membentuk brand awareness pengguna aktif Konek Market. Secara simultan, digital marketing, kualitas layanan, dan word of mouth memiliki pengaruh positif signifikan terhadap brand awareness, dengan nilai Adjusted R Square yaitu 0,339, yang berarti bahwa 33,9% brand awareness dapat dijelaskan oleh ketiga variabel independen tersebut, sedangkan sisanya dipengaruhi oleh faktor lain di luar model penelitian ini.   The purpose of this research is to analyze the effect of digital marketing, service quality, and word of mouth on increasing brand awareness at Konek Market. This study used a sample of 85 respondents who were active users of Konek Market for 4 months (September 2024-January 2025). The technique used in sampling is purposive sampling. This research uses quantitative methods. The data collection technique is by using a questionnaire, and the data analysis technique used is multiple linear regression. The results showed that partially, digital marketing had no significant effect on increasing brand awareness at Konek Market. In contrast, service quality and word of mouth have a positive and significant effect on increasing brand awareness at Konek Market. Word of mouth is the variable that has the most important influence in shaping the brand awareness of active Konek Market users. Simultaneously, digital marketing, service quality, and word of mouth have a significant positive effect on brand awareness, with an Adjusted R Square value of 0.339, which means that 33.9% of brand awareness can be explained by the three independent variables, while the rest is influenced by other factors outside this research model.

Nofi Tri Wijayanti, Rifda Nabila

This research adopts a quantitative research type in analyzing the influence of integrated marketing communication, Islamic service quality and complaint handling on customer loyalty with customer satisfaction as an intervening variable. The population in this study were all customers of the State Savings Bank (BTN) Syariah KCP Ungaran. In determining the sample, the researcher used purposive sampling techniques and the Lemeshow formula to determine the sample size so that 100 respondents were obtained.  In testing the hypothesis, this research applies multiple linear regression analysis and path analysis using SPSS 23 software. Based on the results of the hypothesis test, integrated marketing communication has a negative effect on customer loyalty. Islamic service quality has no effect on customer loyalty. Complaint handling has a positive effect on customer loyalty. Integrated marketing communication has no effect on customer satisfaction. Islamic service quality has a positive effect on customer satisfaction. Complaint handling has a positive and significant effect on customer satisfaction. Customer satisfaction has a positive effect on customer loyalty. Customer satisfaction is unable to mediate the influence of integrated marketing communication on customer loyalty. Customer satisfaction is able to mediate the influence of Islamic service quality on customer loyalty. Customer satisfaction is unable to mediate the influence of integrated marketing communication on customer loyalty.

Marco Antonio Burgos Flórez, Luis Hernando Portillo Riascos, Edinson Ortiz Benavides

El propósito central del estudio es analizar los factores determinantes de la demanda de microcrédito formal e informal en las plazas de mercado de la ciudad de Pasto, año 2021. La investigación tiene un enfoque mixto, con un alcance, inicialmente, descriptivo y, luego, correlacional. Se aplicó una encuesta a una muestra representativa de 344 comerciantes de las cuatro plazas de mercado de la ciudad. Los resultados muestran que el 33% los comerciantes accedieron a microcrédito formal, el 33% a microcrédito informal y el 15% combinaron ambos microcréditos. Las variables determinantes en la demanda de microcrédito formal fueron ingresos, antigüedad, sexo, confianza en las instituciones financieras formales y el acceso a préstamos informales. En el modelo de demanda de préstamo informal se identificaron como factores explicativos, además del ingreso, la antigüedad y el sexo, el tener vivienda propia y acceder a microcrédito formal. Dentro de las conclusiones más relevantes que se obtuvieron a partir de esta investigación se destaca que el microcrédito formal y el informal son productos rivales, pero no excluyentes. Asimismo, las características y el destino que se le da a los recursos difieren entre microcréditos; el ingreso es una variable importante en el acceso al microcrédito formal y reduce la probabilidad del acceso al informal, al igual que la antigüedad del negocio y tener vivienda propia. Por otro lado, la propensión de las mujeres de adquirir financiamiento informal es mayor que la de los hombres.

Amayo Meshack Otieno, Jackline Akoth Odero, Ben Oseno

Purpose: The study examined influence of Professionalism of Project Management Team on the Implementation of National Government-Constituency Development Funded Projects in Kenya. Design/Methodology/Approach: Descriptive survey research design was adopted. The study targeted 1680 project management committee members out of which a sample size of 323 was drawn using Yamane’s formula. Primary data was obtained by use of structured questionnaires and later analyzed by use of descriptive statistics which entailed mean as well as standard deviation and for inferential statistics the study used Pearson’s correlation and simple linear regression. Findings: The findings established that professionalism of project management team positively and significantly influenced implementation. Implications/Originality/Value: This study lays emphasis on the importance of professionalism of project management team members while implementing projects. The conclusion may be of significance for the nation's development, particularly in terms providing the necessary workforce for the efficient governance and achievement of NG-CDF project objectives. The study findings may provide valuable literature for future research on professionalism of project management team and implementation.

Chang Liu, Peng Hou, Anxiang Zeng et al.

Over the past decade, significant advances have been made in the field of image search for e-commerce applications. Traditional image-to-image retrieval models, which focus solely on image details such as texture, tend to overlook useful semantic information contained within the images. As a result, the retrieved products might possess similar image details, but fail to fulfil the user's search goals. Moreover, the use of image-to-image retrieval models for products containing multiple images results in significant online product feature storage overhead and complex mapping implementations. In this paper, we report the design and deployment of the proposed Multi-modal Item Embedding Model (MIEM) to address these limitations. It is capable of utilizing both textual information and multiple images about a product to construct meaningful product features. By leveraging semantic information from images, MIEM effectively supplements the image search process, improving the overall accuracy of retrieval results. MIEM has become an integral part of the Shopee image search platform. Since its deployment in March 2023, it has achieved a remarkable 9.90% increase in terms of clicks per user and a 4.23% boost in terms of orders per user for the image search feature on the Shopee e-commerce platform.

Novaković-Božić Nataša, Perić Goran, Cogoljević Vladan

Internal communication is a fundamental component of the company's successful development and has a direct impact on the efficiency, commitment, satisfaction and motivation of employees. Internal communication is directly related to the company's goals and represents the basis of strategic management. Companies should strive to establish an optimal system of internal communication, in order to build quality relations among employees, team spirit, commitment, improvement of the motivation system, as well as an incentive for innovation and initiative. The aim of this paper is to analyze the impact of internal business communication on the commitment of employees in tourism companies. Research results show that internal business communication has a positive impact on employee commitment. Managers in companies that deal with tourism must take into account the advantages of internal business communication and the opportunities brought by its adequate use, when it comes to the impact on the commitment of employees. Modern tourism companies in the world pay more and more attention to internal communication and its effects, so Serbian tourism companies also follow the example of positive business practices and thus improve the commitment of employees.

Beatriz Barrios Brito, Igor Lopes Martínez, Tatiana Delgado Fernández et al.

El artículo tiene como objetivo definir las actividades educativas para generar en los estudiantes de Ingeniería Industrial, capacidades en economía circular, que les sean útiles tanto para su vida académica, social y/o profesional. Como método de investigación, se utiliza el análisis documental, a través de bibliografía sobre la economía circular, los principios y estrategias circulares, las competencias y capacidades profesionales actuales, el proceso de enseñanza-aprendizaje y el rol de la educación en la transición de modelos de producción y consumo lineales, a circulares. A partir de un modelo de enseñanza-aprendizaje, se definen las competencias y capacidades necesarias para lograr el tránsito circular y se asocian a estos, los tipos de actividades educativas dinámicas que contribuyen a generarlas. Asimismo, se expone la importancia del aprendizaje activo, para generar un marco completo, coherente y práctico en la experiencia académica.

Abhisek Dash, Abhijnan Chakraborty, Saptarshi Ghosh et al.

In traditional (desktop) e-commerce search, a customer issues a specific query and the system returns a ranked list of products in order of relevance to the query. An increasingly popular alternative in e-commerce search is to issue a voice-query to a smart speaker (e.g., Amazon Echo) powered by a voice assistant (VA, e.g., Alexa). In this situation, the VA usually spells out the details of only one product, an explanation citing the reason for its selection, and a default action of adding the product to the customer's cart. This reduced autonomy of the customer in the choice of a product during voice-search makes it necessary for a VA to be far more responsible and trustworthy in its explanation and default action. In this paper, we ask whether the explanation presented for a product selection by the Alexa VA installed on an Amazon Echo device is consistent with human understanding as well as with the observations on other traditional mediums (e.g., desktop ecommerce search). Through a user survey, we find that in 81% cases the interpretation of 'a top result' by the users is different from that of Alexa. While investigating for the fairness of the default action, we observe that over a set of as many as 1000 queries, in nearly 68% cases, there exist one or more products which are more relevant (as per Amazon's own desktop search results) than the product chosen by Alexa. Finally, we conducted a survey over 30 queries for which the Alexa-selected product was different from the top desktop search result, and observed that in nearly 73% cases, the participants preferred the top desktop search result as opposed to the product chosen by Alexa. Our results raise several concerns and necessitates more discussions around the related fairness and interpretability issues of VAs for e-commerce search.

Taner Cokyasar, Anirudh Subramanyam, Jeffrey Larson et al.

Electric vehicle routing problems can be particularly complex when recharging must be performed mid-route. In some applications such as the e-commerce parcel delivery truck routing, however, mid-route recharging may not be necessary because of constraints on vehicle capacities and maximum allowed time for delivery. In this study, we develop a mixed-integer optimization model that exactly solves such a time-constrained capacitated vehicle routing problem, especially of interest to e-commerce parcel delivery vehicles. We compare our solution method with an existing metaheuristic and carry out exhaustive case studies considering four U.S. cities -- Austin, TX; Bloomington, IL; Chicago, IL; and Detroit, MI -- and two vehicle types: conventional vehicles and battery electric vehicles (BEVs). In these studies we examine the impact of vehicle capacity, maximum allowed travel time, service time (dwelling time to physically deliver the parcel), and BEV range on system-level performance metrics including vehicle miles traveled (VMT). We find that the service time followed by the vehicle capacity plays a key role in the performance of our approach. We assume an 80-mile BEV range as a baseline without mid-route recharging. Our results show that BEV range has a minimal impact on performance metrics because the VMT per vehicle averages around 72 miles. In a case study for shared-economy parcel deliveries, we observe that VMT could be reduced by 38.8\% in Austin if service providers were to operate their distribution centers jointly.

Nada Ghanem, Stephan Leitner, Dietmar Jannach

Automated recommendations can nowadays be found on many e-commerce platforms, and such recommendations can create substantial value for consumers and providers. Often, however, not all recommendable items have the same profit margin, and providers might thus be tempted to promote items that maximize their profit. In the short run, consumers might accept non-optimal recommendations, but they may lose their trust in the long run. Ultimately, this leads to the problem of designing balanced recommendation strategies, which consider both consumer and provider value and lead to sustained business success. This work proposes a simulation framework based on agent-based modeling designed to help providers explore longitudinal dynamics of different recommendation strategies. In our model, consumer agents receive recommendations from providers, and the perceived quality of the recommendations influences the consumers' trust over time. We design several recommendation strategies which either give more weight on provider profit or on consumer utility. Our simulations show that a hybrid strategy that puts more weight on consumer utility but without ignoring profitability considerations leads to the highest cumulative profit in the long run. This hybrid strategy results in a profit increase of about 20 % compared to pure consumer or profit oriented strategies. We also find that social media can reinforce the observed phenomena. In case when consumers heavily rely on social media, the cumulative profit of the best strategy further increases. To ensure reproducibility and foster future research, we publicly share our flexible simulation framework.

Guojie Xie, Lijuan Huang, Hou Bin et al.

The digital divide between urban and rural communities has substantially narrowed as information and communication technology has evolved, enabling increasingly more interactions between urban and rural areas. Rural areas now have the foundation and conditions to take advantage of e-commerce opportunities, which is no longer exclusively a city-centric economic mode. Taking advantage of the Internet’s vast resources, many villagers jumped at the opportunity to launch rural e-commerce businesses. Rural inhabitants, however, face several challenges when it comes to starting their own e-commerce enterprises. Meanwhile, local governments and rural e-commerce platform providers, find it difficult to provide accurate help to practitioners and entrepreneurs. To this end, a system of indicators based on a model of entrepreneurial events was developed to identify e-commerce entrepreneurs. And the main objective of this paper is to explore the factors influencing the abilities and expectations of rural residents to set up their own e-commerce businesses in order to provide them with tailored support. Survey data from 162 rural e-commerce practitioners were analyzed using a deep neural network in R. The results reveal that the index system developed in this paper has a good level of reliability and validity, and the prediction approach has a high degree of precision (over 90%), indicating that it can successfully identify rural e-commerce entrepreneurs. Based on the findings of this study, we recommend that local governments and e-commerce businesses work together to address the practical issues of perceived feasibility and desirability for rural e-commerce practitioners. Residents in rural areas who want to start their own businesses can take advantage of the development opportunities provided by the information and communication technology, while local governments should keep up with the speed of digitization and informatization to better manage rural economic growth.

Xiangyu Liu, Chuan Yu, Zhilin Zhang et al.

In e-commerce advertising, it is crucial to jointly consider various performance metrics, e.g., user experience, advertiser utility, and platform revenue. Traditional auction mechanisms, such as GSP and VCG auctions, can be suboptimal due to their fixed allocation rules to optimize a single performance metric (e.g., revenue or social welfare). Recently, data-driven auctions, learned directly from auction outcomes to optimize multiple performance metrics, have attracted increasing research interests. However, the procedure of auction mechanisms involves various discrete calculation operations, making it challenging to be compatible with continuous optimization pipelines in machine learning. In this paper, we design \underline{D}eep \underline{N}eural \underline{A}uctions (DNAs) to enable end-to-end auction learning by proposing a differentiable model to relax the discrete sorting operation, a key component in auctions. We optimize the performance metrics by developing deep models to efficiently extract contexts from auctions, providing rich features for auction design. We further integrate the game theoretical conditions within the model design, to guarantee the stability of the auctions. DNAs have been successfully deployed in the e-commerce advertising system at Taobao. Experimental evaluation results on both large-scale data set as well as online A/B test demonstrated that DNAs significantly outperformed other mechanisms widely adopted in industry.