IEEE BYTE VOLUME-3 ISSUE-1 | Page 15

  Recommendations​ ​in  e-Commerce  By​ ​ Bhoomika​ ​ Narwani,​ ​ FE​ ​ IT      “We​ ​ are​ ​ leaving​ ​ the​ ​ age​ ​ of​ ​ information​ ​ and​ ​ entering​ ​ the​ ​ age​ ​ of​ ​ recommendation” -​ Chris​ ​ Anderson Looking at the present scenario the above quote by Mr. Anderson is an apt description of it. In this busy world of ours e-Commerce as emerged as a boon, just a click away and your desired commodity will be there at your doorstep. With such a sudden boost, consumers are provided with enormous number of options to choose from which leads us to think about the importance of recommendations. Recommendations help consumers to buy the required commodity according to his requirements and also in some cases saves the buyer from being cheated. Looking on the other side it seems pretty clear that companies can increase their consumer base with the help of these recommendations. Recommendations can act as value added​ ​ advertisement​ ​ for​ ​ the​ ​ company​ ​ in​ ​ the​ ​ following​ ​ manner: 1. “Conversion”: Turning Browsers into Buyers is what the seller desires. Recommendations incline​ ​ you​ ​ towards​ ​ the​ ​ product​ ​ and​ ​ the​ ​ consumer​ ​ ends​ ​ up​ ​ buying​ ​ it​ ​ even​ ​ if​ ​ it​ ​ wasn’t​ ​ planned. 2. By increasing Cross-sell Recommender systems improve cross selling by suggesting additional products or services to customers. If the recommendations are good, the average order size increases. For instance, a site might recommend additional products in the checkout process,​ ​ based​ ​ on​ ​ those​ ​ products​ ​ already​ ​ in​ ​ the​ ​ shopping​ ​ cart. 3. By building loyalty: Building customer-loyalty becomes an essential aspect of business strategy. Recommender systems can improve loyalty by creating a value-added relationship between the site and the customer. If the product is satisfactory it will catch the eyes of the customer and when he looks for something else next time he will end up buying it from the very same​ ​ seller. Advancing​ ​ on​ ​ this​ ​ line​ ​ of​ ​ thought​ ​ Recommendation​ ​ System​ ​ is​ ​ further​ ​ classified​ ​ in​ ​ two​ ​ categories 1. Content-based recommendations: These are basic recommendations based on the description of an item. In such kind of system there are three crucial aspects of it ‘the matcher’, ‘the item description’ and ‘the user profile’. It is important for the seller to ensure that the buyer receives​ ​ proper​ ​ advice​ ​ to​ ​ fulfil​ ​ his​ ​ requirement. 2. Collaborative filtering systems: Collaborative Filtering systems make recommendations exclusively based on knowledge of users’ relationships to items. These techniques require no knowledge of the properties of the item themselves. This type of system extensively focusses