Think about the challenge faced by large e-commerce websites like Amazon or Netflix. Brick-and-mortar retailers can capture people’s attention in the store with eye-catching point-of-purchase displays or suggestive selling by store employees. However, these are not options for retail websites. They need an effective way of recommending their vast array of products to customers. Most e-commerce sites provide website search tools based on the technologies previously discussed in this chapter. Relying on customers to find products through an active search, however, assumes customers know what they want and how to describe it when forming their search query. For these reasons, many e-commerce sites rely on recommendation engines (sometimes called recommender systems). Recommendation engines proactively identify products that have a high probability of being something the consumer might want to buy. Amazon has long been recognized as having one of the best recommendation engines. Each time customers log into the site, they are presented with an assortment of products based on their purchase history, browsing history, product reviews, ratings, and many other factors. In effect, Amazon customizes their e-commerce site for each individual, leading to increased sales. According to Amazon employees, click-through and conversion rates “vastly exceed those of untargeted content such as banner advertisements and top-seller lists”
There are three widely used approaches to creating useful recommendations: content-based filtering, collaborative filtering, and hybrid strategies
QUESTION:
Pick a website that you like, in this case choose Amazon
Analyze How it recommends products and services
Identify 2 or 3 points that you like from their recommendation
Identify 1 or 2 areas that they could improve.