I'm marrying the Revlon One-Step Hair Dryer and Volumizer and I don't care what the town clerk has to say. This whole relationship began when Reviewed's social media manager, Kate McCarthy, told me about a magical brush that dries your hair and styles it perfectly at the same time. Much like someone who is single and sick of being set up on fruitless blind dates, I was curious but didn't immediately make plans to try it out. Then the internet blew up with testimonials of the Revlon dryer and I couldn't ignore it anymore. Our first date was a Saturday and I had dinner plans with friends after, so I was prepared to either talk crap or profess my infatuation, as one does after that first IRL rendezvous.
Bundling, the practice of jointly selling two or more products at a discount, is a widely used strategy in industry and a well examined concept in academia. Historically, the focus has been on theoretical studies in the context of monopolistic firms and assumed product relationships, e.g., complementarity in usage. We develop a new machine-learning-driven methodology for designing bundles in a large-scale, cross-category retail setting. We leverage historical purchases and consideration sets created from clickstream data to generate dense continuous representations of products called embeddings. We then put minimal structure on these embeddings and develop heuristics for complementarity and substitutability among products. Subsequently, we use the heuristics to create multiple bundles for each product and test their performance using a field experiment with a large retailer. We combine the results from the experiment with product embeddings using a hierarchical model that maps bundle features to their purchase likelihood, as measured by the add-to-cart rate. We find that our embeddings-based heuristics are strong predictors of bundle success, robust across product categories, and generalize well to the retailer's entire assortment.
The next time you call room service for extra towels, your order may be delivered by a robot. It might not be able to change your sheets, but Savioke's Relay hospitality robot can bring everything from toothpaste to Starbucks, and it uses Wi-Fi and 3D cameras to navigate. The robot is already being used by some hotels in the US, and with recent funding of $15 million, autonomous butlers could soon become a lot more popular. The next time you call room service for a new tube of toothpaste, your order may be delivered by a robot. It might not be able to change your sheets, but Savioke's Relay hospitality robot can bring everything from clean towels to Starbucks, and it uses Wi-Fi and 3D cameras to navigate Each of the Relay robots stands roughly three feet tall.
A UK-wide ban on the manufacture of cosmetics and care products containing tiny pieces of plastic known as "microbeads" has come into force. The move is aimed at protecting the marine environment from one source of plastic pollution, as microbeads are washed down the drain and can enter the seas and be swallowed by fish and crustaceans with potentially harmful effects. Manufacturers of cosmetics and personal care products will no longer be able to add the tiny plastic pieces to rinse-off toiletries such as face scrubs, toothpastes and shower gels. The ban on the manufacture of products containing microbeads will be followed by a ban on the sale of such products in July. A report in 2016 found that more than a third of fish in the English Channel are contaminated with microscopic plastic debris from exfoliating skin scrubs, synthetic fabrics and other everyday products.