Recommender systems are one of the most common applications of big data. The most known application is probably Amazons recommendation engine, which allows users to get a personalized webpage when they visit Amazon.com. But e-tailers are not the only companies that use recommendation engines to persuade customers to buy additional products. Recommender systems can also be used in other industries as well as have different application. Lets have a look what recommender systems are and how you can apply them in your organisation.
Recommender systems can be based on two different types of algorithms, but they are often combined. The first is analysing vast amounts of past choices / purchases of your customers and use these to suggest new products. This is called collaborative filtering; a system recommending other products based on what other users with the same profile also bought. For example, a user bought A, B, C and D and another user bought A, B, C, D and E. The system will then automatically recommend product E to the first user, as both users have the same buying profile and will likely be the same. The other approach is content-based filtering, where the system uses a detailed profile of what a users has previously bought, liked, searched for, tweeted about, blogged about, visited etc. Based on that information, a profile is created and products are recommended that best fit that profile based on the attributes of that product.
Most consumers know recommendation engines from online shopping, but recommendation engines can also be used B2B, for example to recommend potential prospects to sales people. Ellis Booker from InformationWeek describes in a post that using public data sets such as credit bureaus, company data information can be combined with a companys own sales and customer database to find new relationships that a sales person might have missed. As such, recommendation systems are becoming common practice in finance and insurance companies to suggest, among others, investment opportunities or sales strategies.
In fact, recommendation engines can be used anywhere users are looking for products / services or people. LinkedIn uses recommendations to recommend people, jobs or groups you might want to connect with. The you may like this functionality on the platform blends content based and collaborative filtering and uses a algorithmic popularity and graph based approach for the recommendations. Building a virtual profile of each group and extracting the most representative features of those group members create Groups you may like. LinkedIn recommends jobs by combining different profile features, behaviour, location and attributes to similar people like you.
Recommendations has become a standard feature for most of the, large, online players. Ranging from retailers to the online travel websites. For any company working with recommendations, the trick is to deliver relevant recommendations. This will improve the buyer experience and increase the conversion rate.
These are just one of the many examples and possibilities for recommendation engines. One thing is for sure; recommendation engines require vast amounts of data from as may different datasets to be useful. If you want to start with a recommendation engine, it is therefore wise to first start to build the required database before activating the recommender system. Otherwise the recommendations will prove not to be correct in the beginning, requiring iterations while limiting the success of the recommendation engine. Hadoop is great tool to deal with the vast amounts of data in a robust, efficient and flexible manner, while combining the different data sources to improve the targeting of the recommendations.
With the ever-increasing amount of data, recommendation engines will only become better in the future. For organisations this will mean better targeting of products to the right person and thereby probably increasing the conversion rate and the user experience. For consumers it will become even easier to find the product that you are looking for. However, this could also have a downside. If the recommendation engines become so good and recommend products / services before you are aware that you would need them, what would this do with the possibility to discover new products / services that are not inline with your profile? Organisations should be aware of this, as otherwise it could backfire.
