Modern e-commerce platforms offer vast product selections, making it difficult for customers to find items that they like and that are relevant to their current session intent. This is why it is key for e-commerce platforms to have near real-time scalable and adaptable personalized ranking and search systems. While numerous methods exist in the scientific literature for building such systems, many are unsuitable for large-scale industrial use due to complexity and performance limitations. Consequently, industrial ranking systems often resort to computationally efficient yet simplistic retrieval or candidate generation approaches, which overlook near real-time and heterogeneous customer signals, which results in a less personalized and relevant experience. Moreover, related customer experiences are served by completely different systems, which increases complexity, maintenance, and inconsistent experiences. In this paper, we present a personalized, adaptable near real-time ranking platform that is reusable across various use cases, such as browsing and search, and that is able to cater to millions of items and customers under heavy load (thousands of requests per second). We employ transformer-based models through different ranking layers which can learn complex behavior patterns directly from customer action sequences while being able to incorporate temporal (e.g. in-session) and contextual information. We validate our system through a series of comprehensive offline and online real-world experiments at a large online e-commerce platform, and we demonstrate its superiority when compared to existing systems, both in terms of customer experience as well as in net revenue. Finally, we share the lessons learned from building a comprehensive, modern ranking platform for use in a large-scale e-commerce environment.

Demand forecasting in the online fashion industry is particularly amendable to global, data-driven forecasting models because of the industry's set of particular challenges. These include the volume of data, the irregularity, the high amount of turn-over in the catalog and the fixed inventory assumption. While standard deep learning forecasting approaches cater for many of these, the fixed inventory assumption requires a special treatment via controlling the relationship between price and demand closely. In this case study, we describe the data and our modelling approach for this forecasting problem in detail and present empirical results that highlight the effectiveness of our approach.

Ensuring safety of the products offered to the customers is of paramount importance to any e- commerce platform. Despite stringent quality and safety checking of products listed on these platforms, occasionally customers might receive a product that can pose a safety issue arising out of its use. In this paper, we present an innovative mechanism of how a large scale multinational e-commerce platform, Zalando, uses Natural Language Processing techniques to assist timely investigation of the potentially unsafe products mined directly from customer written claims in unstructured plain text. We systematically describe the types of safety issues that concern Zalando customers. We demonstrate how we map this core business problem into a supervised text classification problem with highly imbalanced, noisy, multilingual data in a AI-in-the-loop setup with a focus on Key Performance Indicator (KPI) driven evaluation. Finally, we present detailed ablation studies to show a comprehensive comparison between different classification techniques. We conclude the work with how this NLP model was deployed.

B2B interaction is the situation where one business makes a commercial transaction with another business. The nature of such transactions is usually one business sourcing inputs from another. Companies take advantage of B2B chatbots to answer general questions, provide customer service support, mine data and nurture leads. In this article, we will explore what B2B chatbots are, how they can streamline B2B relationships, and showcase some use cases at the end. Chatbots are software applications used to conduct online conversations between users and bots, either through speech or text, instead of talking to a live agent. In line with that, a B2B chatbot is no different than a regular or emotional chatbot: Its ultimate goal is for the user to, through a conversation, get the information they are looking for.

Founded in 2008 by business school friends Robert Gentz and David Schneider, German-headquartered "etailer" Zalando is as much of a tech company as it is a retailer. One reason the company can provide a personalized user experience to its 27 million customers is because of the way it uses artificial intelligence (AI) and machine learning just like the other 28 percent of retailers who used artificial intelligence in 2018. Here are only a few of the ways Zalando uses machine learning and artificial intelligence today. One of the ways Zalando uses technology to improve the user experience is through its Algorithmic Fashion Companion (AFC), a digital outfit recommendation tool that can generate outfit recommendations in real-time. The algorithm's recommendations are based on products that the customer has put in their "wish list," expressed interest in or purchased before.

Founded in 2008 by business school friends Robert Gentz and David Schneider, German-headquartered "etailer" Zalando is as much of a tech company as it is a retailer. One reason the company can provide a personalized user experience to its 27 million customers is because of the way it uses artificial intelligence (AI) and machine learning just like the other 28 percent of retailers who used artificial intelligence in 2018. Here are only a few of the ways Zalando uses machine learning and artificial intelligence today. One of the ways Zalando uses technology to improve the user experience is through its Algorithmic Fashion Companion (AFC), a digital outfit recommendation tool that can generate outfit recommendations in real-time. The algorithm's recommendations are based on products that the customer has put in their "wish list," expressed interest in or purchased before.

Pricing & Forecasting is at the core of our commercial operation. Our tools help to determine how much of each product to buy, to recommend the best prices for these products, and to ensure that we have the right level of logistics capacity to fulfill our customers demand. The Pricing and Forecasting team uses cutting edge technology, data science and machine learning to forecast demand and pricing with a focus on business and customer experience. Partnerships happen with the machine learning research team, all key engineering and product teams, business and customer experience teams. As a Research Engineer in the Predictive Buying team, you will be working on some of our key critical business problems and challenges.

Get YouTube without the ads. Want to watch this again later? Sign in to add this video to a playlist. Report Need to report the video? Sign in to report inappropriate content.

We introduce a hierarchical Bayesian approach to tackle the challenging problem of size recommendation in e-commerce fashion. Our approach jointly models a size purchased by a customer, and its possible return event: 1. no return, 2. returned too small 3. returned too big. Those events are drawn following a multinomial distribution parameterized on the joint probability of each event, built following a hierarchy combining priors. Such a model allows us to incorporate extended domain expertise and article characteristics as prior knowledge, which in turn makes it possible for the underlying parameters to emerge thanks to sufficient data. Experiments are presented on real (anonymized) data from millions of customers along with a detailed discussion on the efficiency of such an approach within a large scale production system.

These venture bets on startups that "returned the fund," making firms and careers, were the result of research, strong convictions, and patient follow-through. Here are the stories behind the biggest VC home runs of all time. In venture capital, returns follow the Pareto principle -- 80% of the wins come from 20% of the deals. Great venture capitalists invest knowing they're going to take a lot of losses in order to hit those wins. Chris Dixon of top venture firm Andreessen Horowitz has referred to this as the "Babe Ruth effect," in reference to the legendary 1920s-era baseball player. Babe Ruth would strike out a lot, but also made slugging records. Likewise, VCs swing hard, and occasionally hit a home run. Those wins often make up for all the losses and then some -- they "return the fund." "If you do the math around our goal of returning the fund with our high impact companies, you will notice that we need these companies to exit at a billion dollars or more," he wrote.