Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 42편

E-commerce

E-commerce 설명 보기

We release E-commerce Dialogue Corpus, comprising a training data set, a development set and a test set for retrieval based chatbot. The statistics of E-commerical Conversation Corpus are shown in the following table. | |Train|Val| Test | | ------------- |:-------------:|:-------------:|:-------------:| | Session-response pairs | 1m|10k| 10k | | Avg. positive response per session|1|1|1| | Min turn per session|3|3|3| | Max ture per session|10|10|10| | Average turn per session|5.51|5.48|5.64 | Average Word per utterance|7.02|6.99|7.11 The full corpus can be downloaded from https://drive.google.com/file/d/154J-neBo20ABtSmJDvm7DK0eTuieAuvw/view?usp=sharing.

관련 논문 13편

E-commerce Product Review Dataset for Sentiment Analysis

EPRSTMT
EPRSTMT 설명 보기

The EPRSTMT dataset, also known as EPR-sentiment, is a binary sentiment analysis dataset based on product reviews on an e-commerce platform. Each sample in the dataset is labeled as either Positive or Negative. It was collected by the ICIP Lab of Beijing Normal University and has been re-organized to make it suitable for sentiment analysis tasks.

관련 논문 1편

Live Stream E-Commerce

LSEC
LSEC 설명 보기

The LSEC (Live Stream E-Commerce) dataset has two subsets: LSEC-Small and LSEC-Large. It is a dataset for studying E-commerce transactions in the context of live streams, where the streames are talking about products while interacting with their audience. The dataset consists of interaction information among streamers, users, and products.

관련 논문 0편

E-commerce Product Image Classification Dataset

E-commerce Product Image Classification Dataset 설명 보기

Description: <a href="https://gts.ai/dataset-download/e-commerce-product-image-classification-dataset/" target="_blank">👉 Download the dataset here</a> This dataset is specifically designed for the classification of e-commerce products based on their images, forming a critical part of an experimental study aimed at improving product categorization using computer vision techniques. Accurate categorization is essential for e-commerce platforms as it directly influences customer satisfaction, enhances user experience, and optimizes sales by ensuring that products are presented in the correct categories. Data Collection and Sources The dataset comprises a comprehensive collection of e-commerce product images gathered from a diverse range of sources, including prominent online marketplaces such as Amazon, Walmart, and Google, as well as additional resources obtained through web scraping. Additionally, the Amazon Berkeley Objects (ABO) project has been utilized to enhance the dataset in certain categories, though its contribution is limited to specific classes. Download Dataset Dataset Composition and Structure The dataset is organized into 9 distinct classes, primarily reflecting major product categories prevalent on Amazon. These categories were chosen based on a balance between representation and practicality, ensuring sufficient diversity and relevance for training and testing computer vision models. The dataset's structure includes: 18,175 images: Resized to 224x224 pixels, suitable for use in various pretrained CNN architectures. 9 Classes: Representing major e-commerce product categories, offering a broad spectrum of items typically found on online retail platforms. Train-Val-Check Sets: The dataset is split into training, validation, and check sets. The training and validation sets are designated for model training and hyperparameter tuning, while a smaller check set is reserved for model deployment, providing a visual evaluation of the model's performance in a real-world scenario. Application and Relevance E-commerce platforms face significant challenges in product categorization due to the vast number of categories, the variety of products, and the need for precise classification. This dataset addresses these challenges by offering a well-balanced collection of images across multiple categories, allowing for robust model training and evaluation. This dataset is sourced from kaggle.

관련 논문 0편

Personalized Marketing in E-commerce

Personalized Marketing in E-commerce 설명 보기

Problem Statement <a href="https://globaltechnosol.com/case_studies/Personalized-Marketing-in-E-commerce/" target="_blank">👉 Download the case studies here</a> An e-commerce platform struggled with low conversion rates and inconsistent customer engagement. The lack of personalized shopping experiences led to missed opportunities in upselling and cross-selling. Customers found it difficult to discover relevant products, resulting in low retention rates and reduced average order values. Challenge Providing tailored product recommendations for a diverse and expanding catalog posed significant challenges: Understanding customer preferences from limited historical data. Generating real-time recommendations while maintaining system performance Integrating the recommendation engine with existing infrastructure without disrupting the user experience. Solution Provided An AI-powered recommendation engine was implemented, leveraging deep learning and natural language processing (NLP) technologies. The system analyzed customer behavior, preferences, and purchase history to deliver highly personalized product suggestions. Development Steps Data Collection Aggregated user data, including browsing history, purchase patterns, and product reviews, while ensuring compliance with data privacy regulations. Preprocessing Cleaned and structured data to identify trends and patterns. NLP was applied to analyze product descriptions and customer reviews. Model Training Developed a deep learning recommendation engine using collaborative filtering and content-based filtering methods. Integrated NLP models to enhance product tagging and categorization. Validation Tested the recommendation system on a subset of user data to ensure accuracy and relevance in suggestions. Deployment Seamlessly integrated the trained recommendation engine into the e-commerce platform, enabling real-time suggestions on product pages, search results, and checkout pages. Continuous Improvement Monitored system performance and user feedback, using the insights to refine algorithms and improve personalization over time. Results Increased Conversion Rates The recommendation engine boosted conversion rates by 15%, as customers were more likely to find products that suited their preferences. Higher Average Order Value Cross-selling and upselling through personalized suggestions increased the average order value significantly. Improved Customer Retention A tailored shopping experience strengthened customer loyalty, resulting in repeat purchases and enhanced brand trust. Enhanced User Experience The AI-driven system provided a seamless and enjoyable shopping journey, receiving positive customer feedback. Real-Time Personalization The platform adapted dynamically to changes in customer preferences, ensuring relevant recommendations at every interaction.

관련 논문 0편

maadaa.ai Fashion & e-Commerce Open Dataset

maadaa-FaEco Dataset
maadaa-FaEco Dataset 설명 보기

The dataset is organized into 24 typical scenarios, showcasing the richness of real-world environments, conditions, and objects. It is carefully curated to reflect diverse and realistic situations, allowing models to be tested and refined under a wide range of conditions. This dataset contains 33 meticulously fine-annotated sub-datasets. Each is labeled and annotated with a high degree of precision. These datasets offer a vast range of potential use cases, from object detection and segmentation to pose estimation and beyond. This dataset provides a unique context in various applications including personalized recommendations, virtual fittings, beauty AI, and product recognition. This extensive, versatile dataset is a significant resource that we believe will inspire a myriad of innovative solutions in the field. Source: https://maadaa.ai/datasets/open-dataset/fashion-ecommerce/