What was the last thing you bought online? Why didn't you go to a store to buy it? Was it for the vast number of items you could scroll through before making a choice or the recommendations that the website or app pulled up for you, remembering your choices and interests from a previous visit, or the ease with which you paid for it with a card whose details were already stored with the website? The online shopping experience is leaps and bounds ahead of the traditional experience in terms of using data and technology to provide unique and personalized customer experiences. While brick and mortar stores also have their own upsides, the move towards omni-channel retailing today is key.

The pursuit of data-driven decision-making can make business leaders starry-eyed about data science, believing that artificial intelligence in particular can instantly transform their business. What's needed is a healthy tension between data scientists and business leaders around what's possible and workable for using data to drive key decisions. The ideal scenario is all parties in complete alignment. This can be envisioned as a perfect rectangle, with business leaders' expectations at the top, fully supported by a foundation of data science capabilities -- for example, when data science and AI can achieve management's goal of reducing customer retention costs by automating identification and outreach to at-risk customers. Consider Target, which in the mid-2010s had flat in-store sales and a growing digital presence.

Retail today looks completely different than it did five years ago, and five years from now it will look completely different than it does today. Technology is advancing at a pace that requires retailers to not just keep pace with these changes, but stay ahead of the adoption curve in order to remain competitive and top of mind for consumers. The past five years have focused largely on the sophistication of omnichannel retail. This essentially entailed putting nice wrappers around a number of backend technologies to present a frictionless user experience to the customer. However, the next five years will be defined by unified commerce or bringing all disjointed systems together into one system of record that provides cohesiveness and visibility across systems.

Amazon CodeGuru (Preview) is a service launched at AWS re:Invent 2019 that analyzes the performance characteristics of your application and provides automatic recommendations on ways to improve. It does this by profiling your application's runtime (with CodeGuru Profiler) and by automatically reviewing source code changes (with CodeGuru Reviewer). For more information, see What Is Amazon CodeGuru Profiler? This post gives a high-level overview of how CodeGuru Profiler works, common ways to use it, and how to improve your understanding of your application's performance in production. It assumes a basic knowledge of the JVM (Java Virtual Machine) and related concepts such as threads and call stacks. CodeGuru Profiler provides insights into your application's runtime performance with a continuous, always-running production profiler.

Supermarkets need to ensure clean and safe environments for both shoppers and employees. Slips, trips, and falls can result in injuries that have a physical as well as financial cost. Timely detection of hazardous conditions such as spilled liquids or fallen items on supermarket floors can reduce the chances of serious injuries. This paper presents EdgeLite, a novel, lightweight deep learning model for easy deployment and inference on resource-constrained devices. We describe the use of EdgeLite on two edge devices for detecting supermarket floor hazards. On a hazard detection dataset that we developed, EdgeLite, when deployed on edge devices, outperformed six state-of-the-art object detection models in terms of accuracy while having comparable memory usage and inference time.

Recent advancements in artificial intelligence and machine learning have hugely contributed to the growth of Image Recognition and Object Detection in retail. While Image Recognition and Object Detection are used interchangeably, these are two different techniques. Image Recognition is the process of analyzing an input image and predicting its category (also called as a class label) from a set of categories. For instance, consider an automatic store checkout scenario. The user displays an SKU in front of a camera that is powered by an Image Recognition software. The software, when trained on all the SKUs present in the store, can predict the SKU shown by the user as one among all the SKUs.

Time-series forecasting is an important task in both academic and industry, which can be applied to solve many real forecasting problems like stock, water-supply, and sales predictions. In this paper, we study the case of retailers' sales forecasting on Tmall--the world's leading online B2C platform. By analyzing the data, we have two main observations, i.e., sales seasonality after we group different groups of retails and a Tweedie distribution after we transform the sales (target to forecast). Based on our observations, we design two mechanisms for sales forecasting, i.e., seasonality extraction and distribution transformation. First, we adopt Fourier decomposition to automatically extract the seasonalities for different categories of retailers, which can further be used as additional features for any established regression algorithms. Second, we propose to optimize the Tweedie loss of sales after logarithmic transformations. We apply these two mechanisms to classic regression models, i.e., neural network and Gradient Boosting Decision Tree, and the experimental results on Tmall dataset show that both mechanisms can significantly improve the forecasting results.

Most of the retail robots have just enough human qualities to make them appear benign, but not too many to suggest they are replacing humans entirely. "It's like Mary Poppins," said Peter Hancock, a professor at the University of Central Florida, who has studied the history of automation. "A spoonful of sugar makes the robots go down." Perhaps no other retailer is dealing as intensely with the sensitivities around automation as Walmart, the nation's largest private employer, with about 1.5 million workers. The company spent many months working with the firm Bossa Nova and researchers at Carnegie Mellon University to design a shelf-scanning robot that they hope both employees and customers will feel comfortable with.

Might AI help improve customer service for the millions of people who shop on Amazon.com? Amazon intends to find out. In a blog post, the Seattle tech giant revealed that it's testing two AI-based systems to handle incoming shopper inquiries. One fields requests from customers automatically and without human intervention, while the other helps human service agents respond more quickly and easily. "It is difficult to determine what types of conversational models other customer service systems are running, but we are unaware of any announced deployments of end-to-end, neural-network-based dialogue models like ours," wrote Kramer.

Amazon's radical new approach to buying foods and speeding up the checkout process goes the next mile today, with a full-size grocery store here. The Amazon Go Grocery opens Tuesday, with more than four times the space of the original, 7-Eleven-style, on-the-go type stores first opened in 2018. The e-tailer, which also owns Whole Foods, launched the Go stores as a way for local workers to get in and out, with a just basics menu that bypassed essentials like fruit and frozen foods. "We believe'Just walk out' technology," makes shopping a better experience, says Cameron Janes, vice-president of Amazon's physical stores division. He gave USA TODAY a sneak-peek tour of the new concept Monday.