Recommender systems are transforming from novelty tools used by a few e-commerce sites into essential business tools that are reshaping e-commerce. Many large e-commerce sites already use recommender systems to help customers find products to purchase. These systems learn from customers and recommend products they are likely to find valuable. This paper explains how recommender systems help e-commerce sites increase sales and analyzes six e-commerce sites that use recommender systems, including those that use multiple systems. Based on these examples, the authors create a taxonomy of recommender systems, including their interfaces, technologies, and customer inputs. They conclude with ideas for new applications of recommender systems in e-commerce. Recommender systems enhance e-commerce sales in three ways: converting browsers into buyers, improving cross-selling, and increasing customer loyalty. They help customers find products they want to buy, suggest additional products for purchase, and create value-added relationships with customers. The more a customer uses the system, the more loyal they become. The paper presents six e-commerce examples, including Amazon.com, CDNOW, eBay, Levis, Moviefinder.com, and Reel.com. Each example illustrates different recommendation technologies, interfaces, and user inputs. The authors describe a taxonomy of recommender systems based on the degree of automation and persistence. They also discuss how users find recommendations and the different methods for accessing them. The paper highlights the importance of recommender systems in e-commerce, noting that they can be used to increase sales, improve customer loyalty, and provide personalized experiences. The authors suggest that future applications of recommender systems could include more personalized recommendations, better integration of data, and more effective marketing strategies. They also discuss the ethical challenges of using customer data to maximize profits. Recommender systems are a key way to automate mass customization for e-commerce sites. They will become increasingly important as businesses focus on long-term customer value. E-commerce sites will work to maximize the value of their customers by providing the right pricing and service. While some systems are fully automatic and ephemeral, most are persistent and partially automatic, requiring some customer input to increase "stickiness." The authors conclude that recommender systems are creating value for both e-commerce sites and their customers, and their taxonomy helps stimulate the creativity needed to develop future systems.Recommender systems are transforming from novelty tools used by a few e-commerce sites into essential business tools that are reshaping e-commerce. Many large e-commerce sites already use recommender systems to help customers find products to purchase. These systems learn from customers and recommend products they are likely to find valuable. This paper explains how recommender systems help e-commerce sites increase sales and analyzes six e-commerce sites that use recommender systems, including those that use multiple systems. Based on these examples, the authors create a taxonomy of recommender systems, including their interfaces, technologies, and customer inputs. They conclude with ideas for new applications of recommender systems in e-commerce. Recommender systems enhance e-commerce sales in three ways: converting browsers into buyers, improving cross-selling, and increasing customer loyalty. They help customers find products they want to buy, suggest additional products for purchase, and create value-added relationships with customers. The more a customer uses the system, the more loyal they become. The paper presents six e-commerce examples, including Amazon.com, CDNOW, eBay, Levis, Moviefinder.com, and Reel.com. Each example illustrates different recommendation technologies, interfaces, and user inputs. The authors describe a taxonomy of recommender systems based on the degree of automation and persistence. They also discuss how users find recommendations and the different methods for accessing them. The paper highlights the importance of recommender systems in e-commerce, noting that they can be used to increase sales, improve customer loyalty, and provide personalized experiences. The authors suggest that future applications of recommender systems could include more personalized recommendations, better integration of data, and more effective marketing strategies. They also discuss the ethical challenges of using customer data to maximize profits. Recommender systems are a key way to automate mass customization for e-commerce sites. They will become increasingly important as businesses focus on long-term customer value. E-commerce sites will work to maximize the value of their customers by providing the right pricing and service. While some systems are fully automatic and ephemeral, most are persistent and partially automatic, requiring some customer input to increase "stickiness." The authors conclude that recommender systems are creating value for both e-commerce sites and their customers, and their taxonomy helps stimulate the creativity needed to develop future systems.