Effective query reformulation is pivotal in narrowing the gap between a user's exploratory search behavior and the identification of relevant products in e-commerce environments. While traditional approaches predominantly model query rewrites as isolated pairs, they often fail to capture the sequential and transitional dynamics inherent in real-world user behavior. In this work, we propose a novel framework that explicitly models transitional queries--intermediate reformulations occurring during the user's journey toward their final purchase intent. By mining structured query trajectories from eBay's large-scale user interaction logs, we reconstruct query sequences that reflect shifts in intent while preserving semantic coherence. This approach allows us to model a user's shopping funnel, where mid-journey transitions reflect exploratory behavior and intent refinement. Furthermore, we incorporate generative Large Language Models (LLMs) to produce semantically diverse and intent-preserving alternative queries, extending beyond what can be derived through collaborative filtering alone. These reformulations can be leveraged to populate Related Searches or to power intent-clustered carousels on the search results page, enhancing both discovery and engagement. Our contributions include (i) the formal identification and modeling of transitional queries, (ii) the introduction of a structured query sequence mining pipeline for intent flow understanding, and (iii) the application of LLMs for scalable, intent-aware query expansion. Empirical evaluation demonstrates measurable gains in conversion and engagement metrics compared to the existing Related Searches module, validating the effectiveness of our approach in real-world e-commerce settings.

Online sellers and advertisers are recommended keyphrases for their listed products, which they bid on to enhance their sales. One popular paradigm that generates such recommendations is Extreme Multi-Label Classification (XMC), which involves tagging/mapping keyphrases to items. We outline the limitations of using traditional item-query based tagging or mapping techniques for keyphrase recommendations on E-Commerce platforms. We introduce GraphEx, an innovative graph-based approach that recommends keyphrases to sellers using extraction of token permutations from item titles. Additionally, we demonstrate that relying on traditional metrics such as precision/recall can be misleading in practical applications, thereby necessitating a combination of metrics to evaluate performance in real-world scenarios. These metrics are designed to assess the relevance of keyphrases to items and the potential for buyer outreach. GraphEx outperforms production models at eBay, achieving the objectives mentioned above. It supports near real-time inferencing in resource-constrained production environments and scales effectively for billions of items.

Vacuuming is one of those daily tasks that never really goes away. But as technology has advanced, new vacuums can handle cleaning your floors for you -- and with so many robot vacuum deals out there, you don't have to spend an arm and a leg to cross vacuuming off your to-do list. Right now at eBay, you can take an extra 20% off (up to $100) new and refurbished iRobot devices and accessories when you use promo code IROBOT20 at checkout. There's no minimum order requirements and you can use the promo code up to two times now through May 14. There are a ton of options available that can save you a little time and effort when tidying up, including the Roomba S9 Plus robot vacuum with a self-emptying base, which earned a spot on our list of the best robot vacuums for 2023.

Nvidia's most-advanced graphics cards are selling for more than $40,000 on eBay, as demand soars for chips needed to train and deploy artificial intelligence software. The prices for Nvidia's H100 processors were noted by 3D gaming pioneer and former Meta consulting technology chief John Carmack on Twitter. On Friday, at least eight H100s were listed on eBay at prices ranging from $39,995 to just under $46,000. Some retailers have offered it in the past for around $36,000. The H100, announced last year, is Nvidia's latest flagship AI chip, succeeding the A100, a roughly $10,000 chip that's been called the "workhorse" for AI applications.

Transforming Business: Disruptive Innovation Join Andrew Mize, VP of Business Strategy and Initiatives at Bank of America as he explores how providing automation tools in business creates a self-serve data-based thinking environment. He will also explain how this environment fosters curiosity and inspiration and leads to disruptive innovation. From Laggard to Leader – Winning the AI Race Leading organizations have achieved over 60% more analytical value compared to laggards. Bharath Thota and Stuart Klein, Partners at Kearney Analytics, will explain why only 8% of companies extract significant value from analytics investments, and how to overcome the challenge of building a case for change and knowing where to start. Upskilling and Experimentation with AI/ML Presented by Jacqui Van Der Leij–Greyling, the Global Head of Tax Technology at eBay, this session will explain how eBay initiated an AI / ML Launch plan and trained 50 non-data scientists on building AI / ML use cases across the organization.

More than 280 workers at TCGplayer, a marketplace for trading card games like Magic: The Gathering and Pokémon, are trying to unionize. A supermajority of the workers have filed for a union representation election with the National Labor Relations Board. If their efforts are successful, they'll form the first union at eBay, which bought TCGplayer in 2022 in a deal worth up to $295 million. Employees of several card and tabletop companies have unionized, including Card Kingdom, Bellevue Mox Boarding House, Noble Knight Games and Paizo. The TCGplayer workers are similarly trying to organize with the Communications Workers of America ( CWA), which has also worked with several video game studios in their unionization attempts.

Two extremely rare "unreleased, one-of-a-kind, never-digitized" Nintendo NES games have appeared on eBay, according to a tweet from the Video Game History Foundation's Frank Cifaldi, seen by Kotaku. One of those, called Battlefields of Napoleon, was only ever released in Japan. The other is a cartridge from Rare, and appears to be the demo of one of the few games ever developed for the Nintendo Power Glove. According to the eBay listing for Battlefields of Napoleon, the game was "rescued from a dumpster after The Learning Company acquired Brøderbund in 1998 and subsequently discarded most of the historical assets." The items in the lot include a WATA certified prototype on a development board and two additional CHR ROMs.

The board will consist of independent advisors with specific skills and contacts in areas of importance for the ongoing development of the mPower suite of mobility services. AI and ML News: Why SMBs Shouldn't Be Afraid of Artificial Intelligence (AI) Charles Martin is considered a leading figure across multiple technology disciplines, with an established track record in machine learning, deep learning, data science, and AI software development, complemented by extensive domain experience in Natural Language Processing (NLP) for Search Relevance (as well as Text Generation and Quantitative Finance). Highly sought after in the software development field, he has personally developed and implemented machine learning (ML) systems at companies including Roche, France Telecom, GoDaddy, Aardvark (Google), eBay, eHow, Walmart, Barclays/BGI, and Blackrock. Much of his recent project work has been done under his advisory firm, Calculation Consulting, which he founded in 2010 to provide data science, machine learning, and deep learning solutions. He has also served as both a consultant and FTE distinguished engineer at GLG, a prestigious international consulting firm, where he developed AI methods for the search and recommendations platform.

The board will consist of independent advisors with specific skills and contacts in areas of importance for the ongoing development of the mPower suite of mobility services. Charles Martin is considered a leading figure across multiple technology disciplines, with an established track record in machine learning, deep learning, data science, and AI software development, complemented by extensive domain experience in Natural Language Processing (NLP) for Search Relevance (as well as Text Generation and Quantitative Finance). Highly sought after in the software development field, he has personally developed and implemented machine learning (ML) systems at companies including Roche, France Telecom, GoDaddy, Aardvark (Google), eBay, eHow, Walmart, Barclays/BGI, and Blackrock. Much of his recent project work has been done under his advisory firm, Calculation Consulting, which he founded in 2010 to provide data science, machine learning, and deep learning solutions. He has also served as both a consultant and FTE distinguished engineer at GLG, a prestigious international consulting firm, where he developed AI methods for the search and recommendations platform.

For the past few years, Pokémon surged in value on the auction site due to gaming influencers and content makers popularizing the unboxing trend, where creators record themselves opening decks in hopes of finding rare and valuable cards. In June, the company even established a temperature controlled, 31,000 square foot facility called the eBay vault to store particularly precious cards which have been purchased for $750 or more.