With recent rapid growth in online shopping, AI-powered Engagement Surfaces (ES) have become ubiquitous across retail services. These engagement surfaces perform an increasing range of functions, including recommending new products for purchase, reminding customers of their orders and providing delivery notifications. Understanding the causal effect of engagement surfaces on value driven for customers and businesses remains an open scientific question. In this paper, we develop a dynamic causal model at scale to disentangle value attributable to an ES, and to assess its effectiveness. We demonstrate the application of this model to inform business decision-making by understanding returns on investment in the ES, and identifying product lines and features where the ES adds the most value.

While the classic Prospect Theory has highlighted the reference-dependent and comparative nature of consumers' product evaluation processes, few models have successfully integrated this theoretical hypothesis into data-driven preference quantification, particularly in the realm of recommender systems development. To bridge this gap, we propose a new research problem of modeling reference-dependent preferences from a data-driven perspective, and design a novel deep learning-based framework named Attributed Reference-dependent Choice Model for Recommendation (ArcRec) to tackle the inherent challenges associated with this problem. ArcRec features in building a reference network from aggregated historical purchase records for instantiating theoretical reference points, which is then decomposed into product attribute specific sub-networks and represented through Graph Neural Networks. In this way, the reference points of a consumer can be encoded at the attribute-level individually from her past experiences but also reflect the crowd influences. ArcRec also makes novel contributions to quantifying consumers' reference-dependent preferences using a deep neural network-based utility function that integrates both interest-inspired and price-inspired preferences, with their complex interaction effects captured by an attribute-aware price sensitivity mechanism. Most importantly, ArcRec introduces a novel Attribute-level Willingness-To-Pay measure to the reference-dependent utility function, which captures a consumer's heterogeneous salience of product attributes via observing her attribute-level price tolerance to a product. Empirical evaluations on both synthetic and real-world online shopping datasets demonstrate ArcRec's superior performances over fourteen state-of-the-art baselines.

Large Language Models (LLMs), especially following the release of OpenAI's GPT series, have significantly disrupted textual human-machine interaction. They have enabled the development of chat assistants--also known as chatbots--that engage in more natural conversations and better understand users' needs. When combined with Retrieval-Augmented Generation (RAG) [1] techniques, these models can interact with other software systems and expand the information encoded in their parameters with data retrieved from external sources. Some examples described in the literature include FACTS [2], NVIDIA's framework for building assistants that leverage enterprise data for enhancing employee productivity and Abbasian et al. [3] health agents, focused on assisting users with healthcare-related tasks. Another possible domain for such systems is online shopping and delivery services. With estimated global retail e-commerce sales surpassing 6.3 trillion US dollars in 2024 [4], developing alternatives to enhance the customer experience in online purchases holds significant commercial value. In this context, this work describes Retail-GPT, an original open-source RAG-based chatbot designed to guide users through product recommendations and assist with cart operations, aiming to enhance user engagement with retail e-commerce and serve as a virtual sales agent. The goal of this system is to test the viability of such an assistant and provide an adaptable approach for implementing sales chatbots across different retail businesses.

In the rapidly evolving domain of large-scale retail data systems, envisioning and simulating future consumer transactions has become a crucial area of interest. It offers significant potential to fortify demand forecasting and fine-tune inventory management. This paper presents an innovative application of Generative Adversarial Networks (GANs) to generate synthetic retail transaction data, specifically focusing on a novel system architecture that combines consumer behavior modeling with stock-keeping unit (SKU) availability constraints to address real-world assortment optimization challenges. We diverge from conventional methodologies by integrating SKU data into our GAN architecture and using more sophisticated embedding methods (e.g., hyper-graphs). This design choice enables our system to generate not only simulated consumer purchase behaviors but also reflects the dynamic interplay between consumer behavior and SKU availability -- an aspect often overlooked, among others, because of data scarcity in legacy retail simulation models. Our GAN model generates transactions under stock constraints, pioneering a resourceful experimental system with practical implications for real-world retail operation and strategy. Preliminary results demonstrate enhanced realism in simulated transactions measured by comparing generated items with real ones using methods employed earlier in related studies. This underscores the potential for more accurate predictive modeling.

We introduce the Robustness of Hierarchically Organized Time Series (RHiOTS) framework, designed to assess the robustness of hierarchical time series forecasting models and algorithms on real-world datasets. Hierarchical time series, where lower-level forecasts must sum to upper-level ones, are prevalent in various contexts, such as retail sales across countries. Current empirical evaluations of forecasting methods are often limited to a small set of benchmark datasets, offering a narrow view of algorithm behavior. RHiOTS addresses this gap by systematically altering existing datasets and modifying the characteristics of individual series and their interrelations. It uses a set of parameterizable transformations to simulate those changes in the data distribution. Additionally, RHiOTS incorporates an innovative visualization component, turning complex, multidimensional robustness evaluation results into intuitive, easily interpretable visuals. This approach allows an in-depth analysis of algorithm and model behavior under diverse conditions. We illustrate the use of RHiOTS by analyzing the predictive performance of several algorithms. Our findings show that traditional statistical methods are more robust than state-of-the-art deep learning algorithms, except when the transformation effect is highly disruptive. Furthermore, we found no significant differences in the robustness of the algorithms when applying specific reconciliation methods, such as MinT. RHiOTS provides researchers with a comprehensive tool for understanding the nuanced behavior of forecasting algorithms, offering a more reliable basis for selecting the most appropriate method for a given problem.

Amazon Prime Day is officially over -- but there are still a few legacy deals hanging on. We had previously pulled together this list of worthy under- 25 deals, and we've just updated it to reflect these affordable bargains that are still available as of Thursday morning. As a reminder (and for the uninitiated): Engadget treats tech deals with the same care as we would "regular" tech news. When we scour the web for deals, we're looking not only for the best prices possible, but also the best products as well. Our goal with our deals coverage, especially surrounding events like Amazon Prime Day, is to surface only the best deals we can find on the gadgets we've tested and rated highly, or that we've used and know to be worth your money.

The Amazon Prime Day sale ends tonight, but don't think that all opportunities to save have come and gone. In typical Amazon fashion, most of the best Prime Day deals on day one of the sale remain the best offers now on day two -- if they didn't sell out already, that is. Thankfully, many of the best tech deals we curated yesterday are still around today. If you didn't get the chance to shop yesterday, Engadget has you covered. We've collected the best Prime Day deals you can still get right now before the shopping event is over tonight.

On the second day of Amazon's Prime Day sale, the deals on smaller gadgets and accessories are still going strong. In fact, as I was checking to make sure these deals were still live, I noted about five on the list that dropped a few dollars cheaper than they were yesterday. As a reminder, this list represents the best of the affordable tech gear that we at Engadget have tested, reviewed and know to be worth your time. Everything here is on sale for 49.99 or under to make up the best possible roundup of the Prime Day tech deals you can get for under 50. As with all Engadget tech deals coverage, we only highlight discounts on gear we've tested or have otherwise used and know to be worthy of your money. We cross-checked our guides and reviews with the Prime Day deals Amazon has put forth to come up with what you see here. The Anker Nano power bank in black is on sale for Prime Day for 16.13. That's a 15 percent discount and a good deal for one of the best power banks we tested. We like the foldable USB-C connector which means you don't have to remember a separate cable and the amount of charge it delivers for such a small package. Plus it's compact enough you can use it while it refills your phone.

In only a few short hours, Amazon Prime Day 2024 will be in the books, but you still have time to shop day-two deals right now. This year's July Prime Day has been, for lack of a better word, typical, but that's a good thing for anyone who missed out on shopping yesterday. The best Prime Day deals we saw on day one are, indeed, the best deals you can get now during day two -- and most of them haven't sold out yet. If you have any electronics on your wishlist, or you're back for day two and want to take advantage of the still-live sales, Engadget has you covered. We've curated the best Prime Day deals on tech that you can still get for the remainder of Amazon Prime Day.

Amazon Prime Day 2024 will be over in a few hours, but there's still time to save on some of our favorite gadgets. As to be expected, the best Prime Day deals from day one of the sale remain the best offers now on day two -- if they didn't sell out already, that is. We haven't seen a ton of sold out items this year, which is a pleasant surprise. While we have seen some products go up and down in price, they've leveled out eventually. So even if you picked up some items yesterday, there's still time to grab anything you might have forgotten today.