Recommendation systems or recommendation engines form or work from a specific type of information filtering system technique that attempts to recommend information items (films, television, video on demand, music, books, news, images, web pages, etc) that are likely to be of interest to the user. Initially, recommendation technology was relatively crude. It basically just recommended products like other items the buyer had purchased. However, the technology has become considerably more sophisticated and is now an essential part of many online retailers’ economic models. The approach uses complex algorithms to analyze large volumes of data and determine what products that potential customers might want to buy based on their stated preferences, online shopping choices, and the purchases of people with similar tastes or demographics. We in our project will setup a site with a recommendation system utilizing user based user based, item based and pattern matching techniques. It basically just recommended products like other items the buyer had purchased. However, the technology has become considerably more sophisticated and is now an essential part of many online retailers economic models. So we innovated a system that recommends products based on usage history, user profile and product schema.
Different modules of Product Recommendation Engines are
- User Registration – This is done to avoid legal issues, users need to register with the website to give their preferences.
- User Permission – System requires explicit permission to gather user data and to communicate with the user for advanced feedback.
- Methods for data acquisition – Direct interactions with customers.
Different Recommendations made by Engine are
- Behavioral - Track complete user activities in the websites, and analyze the time spent of each product category. By analyzing past user behavior, recommendations can be made.
- Social - This can be achieved if eCommerce system have a social plugin. Users should be allowed to sign in using Facebook, Twitter, Google+, Gmail or Yahoo account. System will make recommendations based on the products purchased by peers in user's network.
- Cart Abandonment - Some studies show 67 % of the users abandon carts. If the system can analyze the causes and work on minimizing cart Abandonment, sales can improve drastically
Various benefits of recommendation engines are
- Increase in sales
- Increase in orders
- Repeated customers
- High level of customization
Also provide a customer feedback page in your website. Customer feedback about usability and features they wish to have to can help your website tremendously. Some suggestions can even help websites to start a new business or a new module.