Filters








4,409 Hits in 6.4 sec

Item Popularity Prediction in E-commerce Using Image Quality Feature Vectors [article]

Stephen Zakrewsky, Kamelia Aryafar, Ali Shokoufandeh
2016 arXiv   pre-print
In this paper we use a set of image features that indicate quality to predict product listing popularity on a major e-commerce website, Etsy.  ...  Online retail is a visual experience- Shoppers often use images as first order information to decide if an item matches their personal style.  ...  In this paper we examine the role of image quality in listing popularity on a major e-commerce website, Etsy 1 .  ... 
arXiv:1605.03663v1 fatcat:6ugsmrwnabbgrmsqqatgj2zr2i

Classification of the User's Intent Detection in Ecommerce systems – Survey and Recommendations

Marek Koniew, Institute of Informatics, Silesian University of Technology, Gliwice, Poland
2020 International Journal of Information Engineering and Electronic Business  
In this work, we review existing works from different domains that can be re-used for customer intent detection in the e-commerce.  ...  Intent detection is a new and challenging approach in modern e-commerce to understand the customer.  ...  They embed a sequence of new items into an "image" in the time and latent spaces and learn sequential patterns as local features of the image using convolutional filters.  ... 
doi:10.5815/ijieeb.2020.06.01 fatcat:zcooazhm2jcqfmmegq7syyj7oq

Research and Implementation of Digital Media Recommendation System Based on Semantic Classification

Xiaoguang Li, Qiangyi Li
2022 Advances in Multimedia  
In order to study the recommendation system of digital media based on semantic classification, the CF-LFMC algorithm based on semantic classification is proposed.  ...  CF-LFMC shows better accuracy, and the CF-LFMC algorithm improved by the time function has improved the accuracy, which is better than the traditional algorithm in accuracy.  ...  Semantic-based image classification methods start from the image data itself and use specific feature extraction methods to extract semantic features in the image; on this basis, the semantic hierarchical  ... 
doi:10.1155/2022/4070827 fatcat:i5343hvoebcwfcjp2qefsuxy4q

Learning to Describe E-Commerce Images from Noisy Online Data [chapter]

Takuya Yashima, Naoaki Okazaki, Kentaro Inui, Kota Yamaguchi, Takayuki Okatani
2017 Lecture Notes in Computer Science  
We learn a generation model from product images with associated title descriptions, and examine how e-commerce specific meta-data and fine-tuning improve the generated expression.  ...  We start by collecting a large amount of product images from the online market site Etsy, and consider learning a language generation model using a popular combination of a convolutional neural network  ...  [30] reports an attempt of popularity prediction of products offered in Etsy. The results suggest the potential usefulness of image feature for selling strategies, such as advertisement.  ... 
doi:10.1007/978-3-319-54193-8_6 fatcat:va3v7k3n55cwrmnot4w4n6n3xm

Deep Neural Network and Boosting Based Hybrid Quality Ranking for e-Commerce Product Search

Mourad Jbene, Smail Tigani, Saadane Rachid, Abdellah Chehri
2021 Big Data and Cognitive Computing  
In this work, we involve the power of embeddings to solve the challenging task of optimizing product search engines in e-commerce.  ...  This work proposes an e-commerce product search engine based on a similarity metric that works on top of query and product embeddings.  ...  Special thanks to those who improved the language quality and made this paper more readable.  ... 
doi:10.3390/bdcc5030035 fatcat:balznb36jbhcdl2oofcsptzjmq

Atlas: A Dataset and Benchmark for E-commerce Clothing Product Categorization [article]

Venkatesh Umaashankar, Girish Shanmugam S, Aditi Prakash
2019 arXiv   pre-print
In E-commerce, it is a common practice to organize the product catalog using product taxonomy.  ...  In this paper, we introduce a high-quality product taxonomy dataset focusing on clothing products which contain 186,150 images under clothing category with 3 levels and 52 leaf nodes in the taxonomy.  ...  of e-commerce sites.  ... 
arXiv:1908.08984v1 fatcat:n2hbzhbynnexjov7jxqxbnhhzq

Mining Fashion Outfit Composition Using an End-to-End Deep Learning Approach on Set Data

Yuncheng Li, Liangliang Cao, Jiang Zhu, Jiebo Luo
2017 IEEE transactions on multimedia  
In fashion websites, popular or high-quality fashion outfits are usually designed by fashion experts and followed by large audiences.  ...  In order to train and evaluate the proposed composition system, we have collected a large scale fashion outfit dataset with 195K outfits and 368K fashion items from Polyvore.  ...  Given the encoded feature vectors {E k (x k g )} for a fashion item x g , (1) using a single layer perceptron, reduce the dimension of the feature vector E k (x k g ) ∈ R d k to the same size d: E k (x  ... 
doi:10.1109/tmm.2017.2690144 fatcat:ad77crljmnazvj3rflppyntcp4

Visual Encoding and Debiasing for CTR Prediction [article]

Si Chen, Chen Lin, Wanxian Guan, Jiayi Wei, Xingyuan Bu, He Guo, Hui Li, Xubin Li, Jian Xu, Bo Zheng
2022 arXiv   pre-print
Extracting expressive visual features is crucial for accurate Click-Through-Rate (CTR) prediction in visual search advertising systems.  ...  Secondly, we incorporate a debiasing network in the online CTR predictor to adjust the visual features by contrasting high impression items with selected items with lower impressions.We deploy the framework  ...  In E-commerce, each image is clearly labeled by its category (e.g., in the clothing section, an image could be labeled as "dress" or "pants", etc.).  ... 
arXiv:2205.04168v1 fatcat:lx4uwwe2rfb27n7yo5wcsnu464

Differentiated Fashion Recommendation Using Knowledge Graph and Data Augmentation

Cairong Yan, Yizhou Chen, Lingjie Zhou
2019 IEEE Access  
E-commerce recommender systems (RSs) can help users quickly find what they need or new products they might be interested in.  ...  The fashion e-commerce websites can collect the attributes of items and users as well as the user purchase behaviors, but lack the fine-grained classification of the items and the implicit relationship  ...  DESCRIPTION OF THE DATASET There are not many e-commerce datasets available at present. The dataset used in this paper is Amazon dataset, a classic e-commerce dataset.  ... 
doi:10.1109/access.2019.2928848 fatcat:yxjrft74ofd7rpchgpeln4s6ge

Using the Context of User Feedback in Recommender Systems

Ladislav Peska
2016 Electronic Proceedings in Theoretical Computer Science  
In this paper, we present a model of relevant contextual features affecting user feedback, propose methods leveraging those features, publish a dataset of real e-commerce users containing multiple user  ...  Our work is generally focused on recommending for small or medium-sized e-commerce portals, where explicit feedback is absent and thus the usage of implicit feedback is necessary.  ...  The experiments presented in this paper were done while author was a Ph.D. student at Charles University in Prague. The work was supported by the Czech grant P46.  ... 
doi:10.4204/eptcs.233.1 fatcat:4u6sdqsfufc3nb66njc6yfcpqm

Choosing the Right Model: A Comprehensive Analysis of Outfit Recommendation Systems

Gursimran Kaur, Hrithik Malhotra, Tanmaya Gupta
2021 International Journal of Computer Applications  
A presentation of these with examples for representative algorithms of each category, and analysis of their predictive performance and their ability to address the challenges is carried out.  ...  The cloth vectors help calculate the final colour percentage in each input image, using the pixels in the image.  ...  |U j |) |I v ||I u | (9) (2) Item Frequency factor: Decreases the impact of popular items and making the less popular items gain more popularity.  ... 
doi:10.5120/ijca2021921413 fatcat:ze6npdmhzba7zky5jva57cvyse

Product Characterisation towards Personalisation: Learning Attributes from Unstructured Data to Recommend Fashion Products [article]

Ângelo Cardoso, Fabio Daolio, Saúl Vargas
2018 arXiv   pre-print
In this paper, we describe a solution to tackle a common set of challenges in e-commerce, which arise from the fact that new products are continually being added to the catalogue.  ...  We describe in detail the architecture and methodology implemented at ASOS, one of the world's largest fashion e-commerce retailers, to tackle this problem.  ...  [29] solve a closely-related problem, product classification in a large e-commerce; they use an image CNN, a text CNN, Figure 2 : Example instances with their associated (a) product images and (b)  ... 
arXiv:1803.07679v1 fatcat:nsylu3omubbajfyzvvc23v3aui

Recommendation System: A Systematic Overview on Methods, Issues and Solutions

2020 International Journal of Advanced Trends in Computer Science and Engineering  
In an e-business site when the user selects any product, then the recommendation will be provided by considering the relationships of user-user, user-item, item-item.  ...  As the technology evolves, the Recommendation System (RS) is becoming a trending topic and widely applied in many fields such as e-commerce sites, health care, stock market, movie,song recommendation.  ...  Feature extraction on images is done based on the JPEG coefficients which are converted into a feature vector.  ... 
doi:10.30534/ijatcse/2020/280952020 fatcat:hiqemfozzngb3ko7oed6dbn2mi

User Response Prediction in Online Advertising [article]

Zhabiz Gharibshah, Xingquan Zhu
2021 arXiv   pre-print
Recent years have witnessed a significant increase in the number of studies using computational approaches, including machine learning methods, for user response prediction.  ...  We propose a taxonomy to categorize state-of-the-art user response prediction methods, primarily focus on the current progress of machine learning methods used in different online platforms.  ...  Focusing on the first section with the network of users interacting with items in an e-commerce website, they applied DeepWalk [109] to generate embedding vectors of items in the directed graph of items  ... 
arXiv:2101.02342v2 fatcat:clgefamcd5fmbeg5ephizy3zqu

Visually Explainable Recommendation [article]

Xu Chen and Yongfeng Zhang and Hongteng Xu and Yixin Cao and Zheng Qin and Hongyuan Zha
2018 arXiv   pre-print
Images account for a significant part of user decisions in many application scenarios, such as product images in e-commerce, or user image posts in social networks.  ...  However, such vectors are hardly useful in terms of providing visual explanations to users about why a particular item is recommended, and thus weakens the explainability of recommendation systems.  ...  See the example in Figure 3 again, in the review of user B "... Nice quality ... ", the feature quality can hardly be expressed in an image.  ... 
arXiv:1801.10288v1 fatcat:tbcfo73zhbb6dlf7ii3t6x5st4
« Previous Showing results 1 — 15 out of 4,409 results