Nasim Sonboli, Toshihiro Kamishima, Amifa Raj, Luca Belli, R. Burke
The 5th Workshop on Responsible Recommendation (FAccTRec 2022) was held in conjunction with the 16th ACM Conference on Recommender Systems on September, 2022 at Seattle, USA, in a hybrid format. This workshop brought together researchers and practitioners to discuss several topics under the banner of social responsibility in recommender systems: fairness, accountability, transparency, privacy, and other ethical and social concerns. It served to advance research and discussion of these topics in the recommender systems space, and incubate ideas for future development and refinement.
{"title":"FAccTRec 2022: The 5th Workshop on Responsible Recommendation","authors":"Nasim Sonboli, Toshihiro Kamishima, Amifa Raj, Luca Belli, R. Burke","doi":"10.1145/3523227.3547419","DOIUrl":"https://doi.org/10.1145/3523227.3547419","url":null,"abstract":"The 5th Workshop on Responsible Recommendation (FAccTRec 2022) was held in conjunction with the 16th ACM Conference on Recommender Systems on September, 2022 at Seattle, USA, in a hybrid format. This workshop brought together researchers and practitioners to discuss several topics under the banner of social responsibility in recommender systems: fairness, accountability, transparency, privacy, and other ethical and social concerns. It served to advance research and discussion of these topics in the recommender systems space, and incubate ideas for future development and refinement.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125665847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cheng-hsin Luo, William P. Headden, Neela Avudaiappan, Haoming Jiang, Tianyu Cao, Qingyu Yin, Yifan Gao, Zheng Li, R. Goutam, Haiyang Zhang, Bing Yin
Query understanding models extract attributes from search queries, like color, product type, brand, etc. Search engines rely on these attributes for ranking, advertising, and recommendation, etc. However, product search queries are usually short, three or four words on average. This information shortage limits the search engine’s power to provide high-quality services. In this talk, we would like to share our year-long journey in solving the information shortage problem and introduce an end-to-end system for attribute recommendation at Amazon Search. We showcase how the system works and how the system contributes to the long-term user experience through offline and online experiments at Amazon Search. We hope this talk can inspire more follow-up works in understanding and improving attribute recommendations in product search.
{"title":"Query Attribute Recommendation at Amazon Search","authors":"Cheng-hsin Luo, William P. Headden, Neela Avudaiappan, Haoming Jiang, Tianyu Cao, Qingyu Yin, Yifan Gao, Zheng Li, R. Goutam, Haiyang Zhang, Bing Yin","doi":"10.1145/3523227.3547395","DOIUrl":"https://doi.org/10.1145/3523227.3547395","url":null,"abstract":"Query understanding models extract attributes from search queries, like color, product type, brand, etc. Search engines rely on these attributes for ranking, advertising, and recommendation, etc. However, product search queries are usually short, three or four words on average. This information shortage limits the search engine’s power to provide high-quality services. In this talk, we would like to share our year-long journey in solving the information shortage problem and introduce an end-to-end system for attribute recommendation at Amazon Search. We showcase how the system works and how the system contributes to the long-term user experience through offline and online experiments at Amazon Search. We hope this talk can inspire more follow-up works in understanding and improving attribute recommendations in product search.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"320 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133545880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maryam Aziz, J. Anderton, Kevin G. Jamieson, Alice Wang, Hugues Bouchard, J. Aslam
Podcasting is an increasingly popular medium for entertainment and discourse around the world, with tens of thousands of new podcasts released on a monthly basis. We consider the problem of identifying from these newly-released podcasts those with the largest potential audiences so they can be considered for personalized recommendation to users. We first study and then discard a supervised approach due to the inadequacy of either content or consumption features for this task, and instead propose a novel non-contextual bandit algorithm in the fixed-budget infinitely-armed pure-exploration setting. We demonstrate that our algorithm is well-suited to the best-arm identification task for a broad class of arm reservoir distributions, out-competing a large number of state-of-the-art algorithms. We then apply the algorithm to identifying podcasts with broad appeal in a simulated study, and show that it efficiently sorts podcasts into groups by increasing appeal while avoiding the popularity bias inherent in supervised approaches.
{"title":"Identifying New Podcasts with High General Appeal Using a Pure Exploration Infinitely-Armed Bandit Strategy","authors":"Maryam Aziz, J. Anderton, Kevin G. Jamieson, Alice Wang, Hugues Bouchard, J. Aslam","doi":"10.1145/3523227.3546766","DOIUrl":"https://doi.org/10.1145/3523227.3546766","url":null,"abstract":"Podcasting is an increasingly popular medium for entertainment and discourse around the world, with tens of thousands of new podcasts released on a monthly basis. We consider the problem of identifying from these newly-released podcasts those with the largest potential audiences so they can be considered for personalized recommendation to users. We first study and then discard a supervised approach due to the inadequacy of either content or consumption features for this task, and instead propose a novel non-contextual bandit algorithm in the fixed-budget infinitely-armed pure-exploration setting. We demonstrate that our algorithm is well-suited to the best-arm identification task for a broad class of arm reservoir distributions, out-competing a large number of state-of-the-art algorithms. We then apply the algorithm to identifying podcasts with broad appeal in a simulated study, and show that it efficiently sorts podcasts into groups by increasing appeal while avoiding the popularity bias inherent in supervised approaches.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130517465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Online Fashion retailers have significantly increased in popularity over the last decade, making it possible for customers to explore hundreds of thousands of products without the need to visit multiple stores or stand in long queues for checkout. Recommender Systems are often used to solve different complex problems in this domain, such as social fashion-aware recommendations (outfits inspired by influencers), product recommendations, or size and fit recommendations. Moreover, the research interest on this area is increasing, demonstrated by the success of the past three editions of the fashionXrecsys Workshops 2019-21. The Fourth edition of the workshop aims at providing an avenue for continuing the discussion of novel approaches and applications of recommendation systems in fashion and e-commerce with a particular focus on pandemic era events and their short and long lasting effects on e-commerce and Fashion.
{"title":"Fourth Workshop on Recommender Systems in Fashion and Retail – fashionXrecsys2022","authors":"Reza Shirvany, Humberto Jesús Corona Pampín","doi":"10.1145/3523227.3547417","DOIUrl":"https://doi.org/10.1145/3523227.3547417","url":null,"abstract":"Online Fashion retailers have significantly increased in popularity over the last decade, making it possible for customers to explore hundreds of thousands of products without the need to visit multiple stores or stand in long queues for checkout. Recommender Systems are often used to solve different complex problems in this domain, such as social fashion-aware recommendations (outfits inspired by influencers), product recommendations, or size and fit recommendations. Moreover, the research interest on this area is increasing, demonstrated by the success of the past three editions of the fashionXrecsys Workshops 2019-21. The Fourth edition of the workshop aims at providing an avenue for continuing the discussion of novel approaches and applications of recommendation systems in fashion and e-commerce with a particular focus on pandemic era events and their short and long lasting effects on e-commerce and Fashion.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127518486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recommender systems, cold-start issues are situations where no previous events (e.g., ratings), are known for certain users or items. Mitigating cold-start situations is a fundamental problem in almost any recommender system [3, 5]. In real-life, large-scale production systems, the challenge of optimizing the cold-start strategy is even greater. We present an end-to-end framework for evaluating and comparing different cold-start strategies. By applying this framework in Outbrain’s recommender system, we were able to reduce our cold-start costs by half, while supporting both offline and online settings. Our framework solves the pain of benchmarking numerous cold-start techniques using surrogate accuracy metrics on offline datasets - coupled with an extensive, cost-controlled online A/B test. In this abstract, We’ll start with a short introduction to the cold-start challenge in recommender systems. Next, we will explain the motivation for a framework for cold-start techniques. Lastly, we will then describe - step by step - how we used the framework to reduce our exploration by more than 50%.
{"title":"Evaluation Framework for Cold-Start Techniques in Large-Scale Production Settings","authors":"moran haham","doi":"10.1145/3523227.3547385","DOIUrl":"https://doi.org/10.1145/3523227.3547385","url":null,"abstract":"In recommender systems, cold-start issues are situations where no previous events (e.g., ratings), are known for certain users or items. Mitigating cold-start situations is a fundamental problem in almost any recommender system [3, 5]. In real-life, large-scale production systems, the challenge of optimizing the cold-start strategy is even greater. We present an end-to-end framework for evaluating and comparing different cold-start strategies. By applying this framework in Outbrain’s recommender system, we were able to reduce our cold-start costs by half, while supporting both offline and online settings. Our framework solves the pain of benchmarking numerous cold-start techniques using surrogate accuracy metrics on offline datasets - coupled with an extensive, cost-controlled online A/B test. In this abstract, We’ll start with a short introduction to the cold-start challenge in recommender systems. Next, we will explain the motivation for a framework for cold-start techniques. Lastly, we will then describe - step by step - how we used the framework to reduce our exploration by more than 50%.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129019596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Frequent updates and model retraining are important in various application areas of recommender systems, e.g., news recommendation. Moreover, in such domains, we may not only face the problem of dealing with a constant stream of new data, but also with anonymous users, leading to the problem of streaming session-based recommendation (SSR). Such problem settings have attracted increased interest in recent years, and different deep learning architectures were proposed that support fast updates of the underlying prediction models when new data arrive. In a recent paper, a method based on Graph Neural Networks (GNN) was proposed as being superior than previous methods for the SSR problem. The baselines in the reported experiments included different machine learning models. However, several earlier studies have shown that often conceptually simpler methods, e.g., based on nearest neighbors, can be highly effective for session-based recommendation problems. In this work, we report a similar phenomenon for the streaming configuration. We first reproduce the results of the mentioned GNN method and then show that simpler methods are able to outperform this complex state-of-the-art neural method on two datasets. Overall, our work points to continued methodological issues in the academic community, e.g., in terms of the choice of baselines and reproducibility.1
频繁的更新和模型再训练在推荐系统的各个应用领域都很重要，例如新闻推荐。此外，在这些领域中，我们可能不仅面临处理持续不断的新数据流的问题，而且还面临匿名用户的问题，从而导致基于流会话的推荐(streaming session based recommendation, SSR)问题。近年来，这样的问题设置引起了越来越多的兴趣，并且提出了不同的深度学习架构，以支持在新数据到达时快速更新底层预测模型。在最近的一篇论文中，提出了一种基于图神经网络(GNN)的方法来解决SSR问题。报告实验中的基线包括不同的机器学习模型。然而，一些早期的研究表明，通常概念上更简单的方法，例如，基于最近邻的方法，可以非常有效地解决基于会话的推荐问题。在这项工作中，我们报告了流配置的类似现象。我们首先重现了上述GNN方法的结果，然后表明更简单的方法能够在两个数据集上优于这种复杂的最先进的神经方法。总的来说，我们的工作指出了学术界持续存在的方法问题，例如，在基线的选择和可重复性方面
{"title":"Streaming Session-Based Recommendation: When Graph Neural Networks meet the Neighborhood","authors":"Sara Latifi, D. Jannach","doi":"10.1145/3523227.3548485","DOIUrl":"https://doi.org/10.1145/3523227.3548485","url":null,"abstract":"Frequent updates and model retraining are important in various application areas of recommender systems, e.g., news recommendation. Moreover, in such domains, we may not only face the problem of dealing with a constant stream of new data, but also with anonymous users, leading to the problem of streaming session-based recommendation (SSR). Such problem settings have attracted increased interest in recent years, and different deep learning architectures were proposed that support fast updates of the underlying prediction models when new data arrive. In a recent paper, a method based on Graph Neural Networks (GNN) was proposed as being superior than previous methods for the SSR problem. The baselines in the reported experiments included different machine learning models. However, several earlier studies have shown that often conceptually simpler methods, e.g., based on nearest neighbors, can be highly effective for session-based recommendation problems. In this work, we report a similar phenomenon for the streaming configuration. We first reproduce the results of the mentioned GNN method and then show that simpler methods are able to outperform this complex state-of-the-art neural method on two datasets. Overall, our work points to continued methodological issues in the academic community, e.g., in terms of the choice of baselines and reproducibility.1","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122845736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Creative design is one of the key components of generating engaging content on the web. E-commerce websites need engaging product descriptions, social networks require user posts to have different types of content such as videos, images and hashtags, and traditional media formats such as blogs require content creators to constantly innovate their writing style, and choice of content they publish to engage with their intended audience. Designing the right content, irrespective of the industry, is a time consuming task, often requires several iterations of content selection and modification. Advertising is one such industry where content is the key to capture user interest and generate revenue. Designing engaging and attention grabbing advertisements requires extensive domain knowledge and market trend awareness. This motivates companies to hire marketing specialists to design specific advertising content, most often tasked to create text, image or video advertisements. This process is tedious and iterative which limits the amount of content that can be produced manually. In this talk, we summarize our work focused on automating ad creative design by leveraging state of the art approaches in text mining, ranking, generation, multimodal (visual-linguistic) representations, multilingual text understanding, and recommendation. We discuss how such approaches can help to reduce the time spent on designing ads, and showcase their impact on real world advertising systems and metrics.
{"title":"Recommendation Systems for Ad Creation: A View from the Trenches","authors":"Manisha Verma, Shaunak Mishra","doi":"10.1145/3523227.3547401","DOIUrl":"https://doi.org/10.1145/3523227.3547401","url":null,"abstract":"Creative design is one of the key components of generating engaging content on the web. E-commerce websites need engaging product descriptions, social networks require user posts to have different types of content such as videos, images and hashtags, and traditional media formats such as blogs require content creators to constantly innovate their writing style, and choice of content they publish to engage with their intended audience. Designing the right content, irrespective of the industry, is a time consuming task, often requires several iterations of content selection and modification. Advertising is one such industry where content is the key to capture user interest and generate revenue. Designing engaging and attention grabbing advertisements requires extensive domain knowledge and market trend awareness. This motivates companies to hire marketing specialists to design specific advertising content, most often tasked to create text, image or video advertisements. This process is tedious and iterative which limits the amount of content that can be produced manually. In this talk, we summarize our work focused on automating ad creative design by leveraging state of the art approaches in text mining, ranking, generation, multimodal (visual-linguistic) representations, multilingual text understanding, and recommendation. We discuss how such approaches can help to reduce the time spent on designing ads, and showcase their impact on real world advertising systems and metrics.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122270505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Numerous problems of practical significance such as clickthrough rate (CTR) prediction, forecasting, tagging and so on, involve complex interaction of various user, item and context features. Manual feature engineering has been used in the past to model these combinatorial features but it requires domain expertise and becomes prohibitively expensive as the number of features increases. Feedforward neural networks alleviate the need for manual feature engineering to a large extent and have shown impressive performance across multiple domains due to their ability to learn arbitrary functions. Despite multiple layers of non-linear projections, neural networks are limited in their ability to efficiently model functions with higher order interaction terms. In recent years, Factorization Machines and its variants have been proposed to explicitly capture higher order combinatorial interactions. However not all feature interactions are equally important, and in sparse data settings, without a suitable suppression mechanism, this might result into noisy terms during inference and hurt model generalization. In this work we present Dual Attentional Higher Order Factorization Machine (DA-HoFM), a unified attentional higher order factorization machine which leverages a compositional architecture to compute higher order terms with complexity linear in terms of maximum interaction degree. Equipped with sparse dual attention mechanism, DA-HoFM summarizes interaction terms at each layer, and is able to efficiently select important higher order terms. We empirically demonstrate effectiveness of our proposed models on the task of CTR prediction, where our model exhibits superior performance compared to the recent state-of-the-art models, outperforming them by up to 6.7% on the logloss metric.
{"title":"Dual Attentional Higher Order Factorization Machines","authors":"Arindam Sarkar, Dipankar Das, Vivek Sembium, Prakash Mandayam Comar","doi":"10.1145/3523227.3546789","DOIUrl":"https://doi.org/10.1145/3523227.3546789","url":null,"abstract":"Numerous problems of practical significance such as clickthrough rate (CTR) prediction, forecasting, tagging and so on, involve complex interaction of various user, item and context features. Manual feature engineering has been used in the past to model these combinatorial features but it requires domain expertise and becomes prohibitively expensive as the number of features increases. Feedforward neural networks alleviate the need for manual feature engineering to a large extent and have shown impressive performance across multiple domains due to their ability to learn arbitrary functions. Despite multiple layers of non-linear projections, neural networks are limited in their ability to efficiently model functions with higher order interaction terms. In recent years, Factorization Machines and its variants have been proposed to explicitly capture higher order combinatorial interactions. However not all feature interactions are equally important, and in sparse data settings, without a suitable suppression mechanism, this might result into noisy terms during inference and hurt model generalization. In this work we present Dual Attentional Higher Order Factorization Machine (DA-HoFM), a unified attentional higher order factorization machine which leverages a compositional architecture to compute higher order terms with complexity linear in terms of maximum interaction degree. Equipped with sparse dual attention mechanism, DA-HoFM summarizes interaction terms at each layer, and is able to efficiently select important higher order terms. We empirically demonstrate effectiveness of our proposed models on the task of CTR prediction, where our model exhibits superior performance compared to the recent state-of-the-art models, outperforming them by up to 6.7% on the logloss metric.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116768722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Calls to action to implement evaluation of fairness and bias into industry systems are increasing at a rapid rate. The research community has attempted to meet these demands by producing ethical principles and guidelines for AI, but few of these documents provide guidance on how to implement these principles in real world settings. Without readily available standardized and practice-tested approaches for evaluating fairness in recommendation systems, industry practitioners, who are often not experts, may easily run into challenges or implement metrics that are potentially poorly suited to their specific applications. When evaluating recommendations, practitioners are well aware they should evaluate their systems for unintended algorithmic harms, but the most important, and unanswered question, is how? In this talk, we will present practical challenges we encountered in addressing algorithmic responsibility in recommendation systems, which also present research opportunities for the RecSys community. This talk will focus on the steps that need to happen before bias mitigation can even begin.
{"title":"Challenges in Translating Research to Practice for Evaluating Fairness and Bias in Recommendation Systems","authors":"Lex Beattie, D. Taber, H. Cramer","doi":"10.1145/3523227.3547403","DOIUrl":"https://doi.org/10.1145/3523227.3547403","url":null,"abstract":"Calls to action to implement evaluation of fairness and bias into industry systems are increasing at a rapid rate. The research community has attempted to meet these demands by producing ethical principles and guidelines for AI, but few of these documents provide guidance on how to implement these principles in real world settings. Without readily available standardized and practice-tested approaches for evaluating fairness in recommendation systems, industry practitioners, who are often not experts, may easily run into challenges or implement metrics that are potentially poorly suited to their specific applications. When evaluating recommendations, practitioners are well aware they should evaluate their systems for unintended algorithmic harms, but the most important, and unanswered question, is how? In this talk, we will present practical challenges we encountered in addressing algorithmic responsibility in recommendation systems, which also present research opportunities for the RecSys community. This talk will focus on the steps that need to happen before bias mitigation can even begin.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126769575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
At Shopify, we serve product recommendations to customers across millions of merchants’ online stores. It is a challenge to provide optimized recommendations to all of these independent merchants; one model might lead to an overall improvement in our metrics on aggregate, but significantly degrade recommendations for some stores. To ensure we provide high quality recommendations to all merchant segments, we develop several models that work best in different situations as determined in offline evaluation. Learning which strategy best works for a given segment also allows us to start off new stores with good recommendations, without necessarily needing to rely on an individual store amassing large amounts of traffic. In production, the system will start out with the best strategy for a given merchant, and then adjust to the current environment using multi-armed bandits. Collectively, this methodology allows us to optimize the types of recommendations served on each store.
{"title":"Optimizing product recommendations for millions of merchants","authors":"Kim Falk, Chen Karako","doi":"10.1145/3523227.3547393","DOIUrl":"https://doi.org/10.1145/3523227.3547393","url":null,"abstract":"At Shopify, we serve product recommendations to customers across millions of merchants’ online stores. It is a challenge to provide optimized recommendations to all of these independent merchants; one model might lead to an overall improvement in our metrics on aggregate, but significantly degrade recommendations for some stores. To ensure we provide high quality recommendations to all merchant segments, we develop several models that work best in different situations as determined in offline evaluation. Learning which strategy best works for a given segment also allows us to start off new stores with good recommendations, without necessarily needing to rely on an individual store amassing large amounts of traffic. In production, the system will start out with the best strategy for a given merchant, and then adjust to the current environment using multi-armed bandits. Collectively, this methodology allows us to optimize the types of recommendations served on each store.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129657666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：