Last Updated on 09/07/2019 by TDH Publishing (A)
Like something out of the movie “Minority Report”, where killers are apprehended before they murder based on a pre-sentiment, practitioners of machine learning are trying to gauge the likelihood you will return a piece of apparel even before you purchase it.
Myntra, the Bangalore-based online shopping website, owned by e-commerce start-up Flipkart, has published a new report this week giving details about the experiments that assess a user’s online shopping cart before they even click to buy. This is based on the observed patterns of what a user has looked at online, but also a guess about the size and fit that even the user may not have been aware of.
All this is meant to enable a computer to think within 70 milliseconds, and the purpose is to decide whether to treat oneself differently as a return risk via punishment and reward, along with a variety of measures. This includes an increment in one’s shipping charges or offering a coupon as an incentive in return for making the purchase.
Myntra’s researchers conducted some tests with genuine customers and found out that the neural network’s predictions, rewards, punishments in measurable ways.
The paper, “Early Bird Catches the Worm: Predicting Returns Even Before Purchase in Fashion E-commerce,” is authored by Sajan Kedia, Manchit Madan, and Sumit Borar of Myntra, and posted on the arXiv preprint server. The paper is noteworthy as well-being for being released last week along with two other papers by Myntra researchers. In one paper, “One Embedding To Do Them All,” the authors create a new kind of product listing for retail by combining several sources of information. The third paper, “Fashion Retail: Forecasting Demand for New Items,” predicts which new apparel items will do well based on past trends but also based on a model of styles and types and rating, a model that can anticipate how brand-new items will do before they go on sale. But it’s the “Early Bird” paper that looks to supply the foremost hanging example of the way to flip retail into a form of a game.
The lesson for consumers is clear, too: When you shop online, you’re participating in a game, a game whose rules the merchant knows much better than you do.