We introduce ECSEL, an explainable classification method that learns formal expressions in the form of signomial equations, motivated by the observation that many symbolic regression benchmarks admit compact signomial structure. ECSEL directly constructs a structural, closed-form expression that serves as both a classifier and an explanation. On standard symbolic regression benchmarks, our method recovers a larger fraction of target equations than competing state-of-the-art approaches while requiring substantially less computation. Leveraging this efficiency, ECSEL achieves classification accuracy competitive with established machine learning models without sacrificing interpretability. Further, we show that ECSEL satisfies some desirable properties regarding global feature behavior, decision-boundary analysis, and local feature attributions. Experiments on benchmark datasets and two real-world case studies i.e., e-commerce and fraud detection, demonstrate that the learned equations expose dataset biases, support counterfactual reasoning, and yield actionable insights.

Recommender systems have become ubiquitous across a wide range of fields, such as ecommerce, media consumption (including movies, books, music, news, etc.), social networks, finance, and many others, due to their effectiveness in identifying relevant items or content among numerous choices [1, 2]. Traditionally, recommender systems, largely based on collaborative filtering techniques, have focused on recommending individual (or "atomic") items, such as movies or books, by understanding users' preferences for these individual items. However, in certain application domains, recommending "composite" items (i.e., combinations of atomic items) represents a very important capability. For illustration, consider a clothing/fashion recommender system, where we want to recommend "outfits" - combinations of tops (t-shirts, shirts, sweaters) and bottoms (pants, skirts, shorts) - to users. In such a case, multiple fashion items in a recommended outfit ideally have to match both functionally and stylistically, which may require domain expertise (e.g., on things like style compatibility) beyond individual preferences. Another key challenge for such recommender systems is that a given user's personal preference for a composite item may not directly translate to the user's personal preferences for the underlying atomic items and vice versa.

Google introduces a new'Checkout' feature in Gemini and Search AI Mode, allowing US users to make direct purchases through conversations with AI. PCWorld reports that Google launched the Universal Commerce Protocol alongside major retailers like Shopify, Etsy, Walmart, and Target for seamless integration. Users can complete transactions using Google Pay or PayPal, streamlining online shopping by eliminating the need to navigate to separate websites. Google is launching a "Checkout" feature in its Gemini AI chatbot as well as in Google Search's AI Mode, according to a recent blog post . The feature allows users to purchase products without leaving the chat or search interface. Purchases can be completed with Google Pay or PayPal. At the same time, Google is also unveiling its Universal Commerce Protocol (UCP). This is an open standard that enables different AI agents, payment systems, and shops to work seamlessly together.

The Universal Commerce Protocol introduces three new major AI features meant to reduce friction when online shopping. To further push the limits of consumerism, Google has launched a new open standard for agentic commerce that's called Universal Commerce Protocol (UCP). In brief, it's a framework that combines the power of AI agents and online shopping platforms to help customers buy more things. Thanks to the introduction of UCP, Google is offering three new online shopping features. To start, Google's AI mode will have a new checkout feature that allows customers to buy eligible products from certain US retailers within Google Search.

Most existing benchmarks for grounding language in interactive environments either lack realistic linguistic elements, or prove difficult to scale up due to substantial human involvement in the collection of data or feedback signals. We develop WebShop - a simulated e-commerce website environment with 1.18 million real-world products and 12,087 crowd-sourced text instructions. In this environment, an agent needs to navigate multiple types of webpages and issue diverse actions to find, customize, and purchase a product given an instruction. WebShop provides several challenges including understanding compositional instructions, query (re-)formulation, dealing with noisy text in webpages, and performing strategic exploration. We collect over 1,600 human trajectories to first validate the benchmark, then train and evaluate a diverse range of agents using reinforcement learning, imitation learning, and pre-trained image and language models. Our best model achieves a task success rate of 29%, which significantly outperforms rule heuristics but is far lower than expert human performance (59%). We also analyze agent and human trajectories and ablate various model components to provide insights for developing future agents with stronger language understanding and decision making abilities. Finally, we show our agent trained on WebShop exhibits non-trivial sim-to-real transfer when evaluated on amazon.com

Click-through rate (CTR) prediction is one of the fundamental tasks for e-commerce search engines. As search becomes more personalized, it is necessary to capture the user interest from rich behavior data. Existing user behavior modeling algorithms develop different attention mechanisms to emphasize query-relevant behaviors and suppress irrelevant ones. Despite being extensively studied, these attentions still suffer from two limitations. First, conventional attentions mostly limit the attention field only to a single user's behaviors, which is not suitable in e-commerce where users often hunt for new demands that are irrelevant to any historical behaviors.

Ting Cai, head of Rakuten Group's artificial intelligence team, has the task of creating AI systems that would augment the company's many businesses at a minimal cost. Rakuten Group is expanding its AI team under the stewardship of a Google veteran and building models with a focus on cost efficiency. Ting Cai, now three years into his tenure at the head of the e-commerce pioneer's artificial intelligence team, has the task of creating AI systems that would augment the company's many businesses and support the handling of commercial transactions at a minimal cost. He oversees a team that's grown to 1,000 this year and has a battery of "thousands" of Nvidia chips to work with. Tokyo-based Rakuten is wrestling with a struggling mobile business and constant competition in online shopping, both of which could get a significant boost from effective deployment of new AI tools.

From dead crabs to shredded bed sheets, fraudsters are using fake photos and videos to get their money back from ecommerce sites. I don't want to admit it, but I did spend a lot of money online this holiday shopping season. And unsurprisingly, some of those purchases didn't meet my expectations. A photobook I bought was damaged in transit, so I snapped a few pictures, emailed them to the merchant, and got a refund. Online shopping platforms have long depended on photos submitted by customers to confirm that refund requests are legitimate.

With the wide and cross-domain adoption of Large Language Models, it becomes crucial to assess to which extent the statistical correlations in training data, which underlie their impressive performance, hide subtle and potentially troubling biases. Gender bias in LLMs has been widely investigated from the perspectives of works, hobbies, and emotions typically associated with a specific gender. In this study, we introduce a novel perspective. We investigate whether LLMs can predict an individual's gender based solely on online shopping histories and whether these predictions are influenced by gender biases and stereotypes. Using a dataset of historical online purchases from users in the United States, we evaluate the ability of six LLMs to classify gender and we then analyze their reasoning and products-gender co-occurrences. Results indicate that while models can infer gender with moderate accuracy, their decisions are often rooted in stereotypical associations between product categories and gender. Furthermore, explicit instructions to avoid bias reduce the certainty of model predictions, but do not eliminate stereotypical patterns. Our findings highlight the persistent nature of gender biases in LLMs and emphasize the need for robust bias-mitigation strategies.

Automatic question-answering (QA) systems have boomed during last few years, and commonly used techniques can be roughly categorized into Information Retrieval (IR)-based and generation-based. A key solution to the IR based models is to retrieve the most similar knowledge entries of a given query from a QA knowledge base, and then rerank those knowledge entries with semantic matching models. In this paper, we aim to improve an IR based e-commerce QA system-AliMe with proposed text matching models, including a basic Triple Convolutional Neural Network (TCNN) model and two Attention-based TCNN (ATCNN) models. Experimental results show their effect.