1. An introduction to Recommender Systems - The Goal(s)
This article is written by Riccardo Saccomandi, Co-founder and CTO of Kickdynamic.
Recommender systems started to gain a lot of importance in the nineties, as the Web became an important medium for business and e-commerce transactions. The Web provided unprecedented opportunities for personalization, which were not possible with other channels. Since then, the increasing importance of the Web as a medium for electronic and business transactions has served as a driving force for the development of recommender systems technology.
The basic idea behind recommender systems is to utilize various sources of data to infer (predict) customer interests. The recommendation analysis is often based on the previous interaction between users and items, because past interests and propensities are often good indicators of future choices.
What is the primary goal for a recommender system?
Well... increasing product sales. Recommender systems are, after all, used by merchants to increase their profit. By recommending carefully selected items, recommender systems bring the most relevant items to the attention of users. This increases the sales volume and profits for the merchant.
Although the primary goal of a recommendation system is to increase revenue for the merchant, this is often achieved in ways that are less obvious than might seem at first sight. In order to achieve the broader business goal of increasing sales volumes and therefore increase revenue, the common operational and technical goals of recommender systems are:
The most obvious operational goal of a recommender system is to recommend items that are relevant to the user at hand. Users are more likely to consume items they find interesting.
Although relevance is the primary goal of a recommender system, it is not sufficient in isolation. There are other secondary goals, which may not seem quite as important as relevance but are nevertheless important enough to have a significant impact.
Recommender systems are truly helpful when the recommended item is something that the user has not seen in the past. For example, popular movies of a preferred genre would rarely be novel to the user. Repeated recommendation of popular items can also lead to reduction in sales diversity.
A related notion is that of serendipity, wherein the items recommended are somewhat unexpected. Serendipity is different from novelty in that the recommendations are really surprising to the user, rather than simply something they did not know about before. It may often be the case that a particular user may only be consuming items of a specific type, although a latent interest in items of other types may exist which the user might themselves find surprising. Unlike novelty, serendipitous methods focus on discovering such recommendations. For example, if a new Indian restaurant opens in a neighbourhood, then the recommendation of that restaurant to a user who normally eats Indian food is novel but not necessarily serendipitous. But when the same user is recommended Ethiopian food, and it was unknown to the user that such food might appeal to him, then the recommendation is likely to be serendipitous. Serendipity comes with the beneficial side effect of increasing sales diversity starting new trends of interest in the user.
4. Increasing recommendation diversity.
Recommender systems typically suggest a list of top-k items. When the recommended items are very similar, this increases the risk that the user might not like any of them. On the other hand, when the recommended list contains items of different types, there is a greater chance that the user might like at least one of these items. Diversity has the benefit of ensuring that the user does not get bored by repeated recommendation of similar items.
Apart from these four main goals, the recommendation process can meet other goals both from the perspective of the user and the merchant. From the user's perspective, recommendations can help improve overall user satisfaction with the website. A user who frequently receives relevant recommendations from a merchant's website and emails will be more satisfied with the experience and is more likely to use the website and open emails again. This can improve the user's loyalty and further increase the sales at the site. At the merchant end, the recommendation process can provide insights into the needs of the user and help customize and improve the user experience.
So that is pretty much it about the goals of a recommender system. In the next article we will take a look at the basic models of recommender systems. Stay tuned.