With the rapid growth in fashion e-commerce and customer-friendly product return policies, the cost to handle returned products has become a significant challenge. E-tailers incur huge losses in terms of reverse logistics costs, liquidation cost due to damaged returns or fraudulent behavior. Accurate prediction of product returns prior to order placement can be critical for companies. It can facilitate e-tailers to take preemptive measures even before the order is placed, hence reducing overall returns. Furthermore, finding return probability for millions of customers at the cart page in real-time can be difficult. To address this problem we propose a novel approach based on Deep Neural Network. Users' taste & products' latent hidden features were captured using product embeddings based on Bayesian Personalized Ranking (BPR). Another set of embeddings was used which captured users' body shape and size by using skip-gram based model. The deep neural network incorporates these embeddings along with the engineered features to predict return probability. Using this return probability, several live experiments were conducted on one of the major fashion e-commerce platform in order to reduce overall returns.

Wednesday is serving up some seriously tasty deals. If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA Today's newsroom and any business incentives. So, we finally know when Prime Day is going to be this year, and we're already tracking what's going on sale, what will be discounted for the big event, and what other retailers are getting up to to complete with the online shopping giant and for July 4th. What that means for you is an onslaught of new sales, deals, and discounts for virtually anything and everything you can think of.

Disclaimer: The challenges discussed in this blog are when the Eye Tracking study is done with the help of glasses. Eye Tracking study is about knowing a person's gaze behavior in regards to the real world environment consumer. The technology is well known in the retail market research, where companies are eager to find out the insights of consumer behavior in accordance with their purchasing attributes. While the study is essential for understanding the market, there are some challenges associated with setting up of Eye Tracking study. Some of them are highlighted in this article.

"When you think about recommending something to someone, there's a real business reason why you might want to do that." Machine learning recommendation systems are not just a trendy feature of online stores. It is a mighty tool that can propel your business to the next level, if used strategically. No wonder Jack Chua suggests always having "a great tie-in to the underlying KPI of what you want to drive". If you're still hesitating on how exactly to use recommendations to invigorate your business, we invite you to learn from the experience of those who already made it work brilliantly! We collected the best examples of machine learning implementation in recommenders (including our own development projects) and explain in plain English how to build a machine learning recommender systems from scratch. Okay, let's start with a short quiz. Try to remember as many types of recommendation systems as you can.

The rise in popularity of major social media platforms have enabled people to share photos and textual information about their daily life. One of the popular topics about which information is shared is food. Since a lot of media about food are attributed to particular locations and restaurants, information like popularity of spatio-temporal popularity of various cuisines can be analysed. Tracking the popularity of food types and retail locations across space and time can also be useful for business owners and restaurant investors. In this work, we present an approach using off-the shelf machine learning techniques to identify trends and popularity of cuisine types in an area using geo-tagged data from social media, Google images and Yelp. After adjusting for time, we use the Kernel Density Estimation to get hot spots across the location and model the dependencies among food cuisines popularity using Bayesian Networks. We consider the Manhattan borough of New York City as the location for our analyses but the approach can be used for any area with social media data and information about retail businesses.

Retailers are getting smarter about artificial intelligence (AI), and the latest example of that innovative effort comes from Walmart. According to a new report, the retail chain, hoping to reduce checkout theft, is turning to cameras powered by AI, with deployments underway in some 1,000 stores. "The retailer began investing in the surveillance program, dubbed Missed Scan Detection, several years ago in an effort to combat shrinkage -- loss due to several causes including theft, scanning errors, waste and fraud," the report stated. "The AI-powered cameras were rolled out to more than 1,000 stores about two years ago and the retail giant has seen positive results since then, according to Jenkins, who said shrinkage has reduced in stores where the cameras have been added." Artificial intelligence is moving from theory to reality, and that holds true for the world of retail as well.

Walmart is using computer vision technology to monitor checkouts and deter potential theft in more than 1,000 stores, the company confirmed to Business Insider. The surveillance program, which Walmart refers to internally as Missed Scan Detection, uses cameras to help identify checkout scanning errors and failures. The cameras track and analyze activities at both self-checkout registers and those manned by Walmart cashiers. When a potential issue arises, such as an item moving past a checkout scanner without getting scanned, the technology notifies checkout attendants so they can intervene. The program is designed to reduce shrinkage, which is the term retailers use to define losses due to theft, scanning errors, fraud, and other causes.

The store chain is using tech from several companies, including Everseen. The technology has been in use for the past two years. If you ask the company, it appears to be working. Spokeswoman LeMia Jenkins told BI that shrinkage rates (that is, the loss of goods to theft and accidents) have dropped at stores where the computer vision is in use. The question is whether or not the system addresses privacy concerns.

If you haven't wasted the last few years searching for evidence on extraterritorial life in the distant corners of the world you'd have surely heard about Artificial Intelligence or AI! Together with Big Data, this is transforming the world. In a world where access to data has become easier, computing power is at historical lows on the cost side and algorithms have been programmed to think and react like a human mind, the power of AI is truly being unleashed. The impact of AI is being majorly felt in the retail industry where it is creating a store like an experience on online platforms and at the same time arming brick and mortar stores with technology that narrows the game between them and online retailers. AI in shopping was first tried in the world of e-commerce and this wasn't surprising as online retailers had been at the forefront of adopting new technology. But the brick and mortar stores have been slowly catching up.

Walmart will begin to deliver groceries inside customers' homes soon. Walmart is working to reduce checkout theft in more than 1,000 U.S. stores with the help of cameras powered by artificial intelligence. The retailer began investing in the surveillance program, dubbed Missed Scan Detection, several years ago in an effort to combat shrinkage -- loss due to several causes including theft, scanning errors, waste and fraud, a Walmart spokeswoman told Business Insider. "Walmart is making a true investment to ensure the safety of our customers and associates," Walmart spokeswoman LeMia Jenkins told the business site. "Over the last three years, the company has invested over half a billion dollars in an effort to prevent, reduce and deter crime in our stores and parking lots."