An introduction to recommender systems for e-commerce and new challenges

Recommender systems (RSs) are computer-based techniques that attempt to present information about products that are likely to be of interest to a user. These techniques are mainly used in electronic commerce (e-commerce) in order to provide suggestions for items that a customer will presumably like.

There are other applications that make use of RSs, including social networks and community-building processes. A recommender system is a specific type of information filtering technique that tries to present users with information about items (movies, music, books, news, web pages, etc.) in which they are interested. The term “item” is used to denote what the system recommends to users. To achieve this goal, the user profile is contrasted with the characteristics of the items. These features may come from the item content (content-based approach) or the user’s social environment (CF).

The use of these systems is becoming increasingly popular on the Internet, because they are very useful for evaluating and filtering the vast amount of information available on the web in order to assist users in their search processes and retrieval. RSs have been highly used and play an important role in various Internet sites that offer products and services on social networks, such as Amazon, YouTube, Netflix, Yahoo!, TripAdvisor, Facebook, and Twitter. Many different companies are developing RSs techniques as an added value to the services they provide for their subscribers.

The European Commission introduced the General Data Protection Regulation (GDPR) to create a single set of data protection rules for all companies operating in the EU, wherever they are based. GDPR includes stronger rules on data protection, with the aim of providing individuals with greater control over their personal data. Businesses also benefit from a level playing field, as unifying the regulations within the EU simplifies the regulatory environment for international business.

In order to comply with the requirements of GDPR, the data controller must first implement measures that comply with the principles of data protection by design and by default (Article 25 GDPR). This article indicates the necessary measures for protecting data for the development of commercial processes for products and services.

When collecting user data, stakeholders should be clearly informed as to the scope of data collection, the legal basis for data processing, the period of time during which the data will be retained, and whether the data will be transferred to a third party and / or outside the EU. In addition, any automated decisions that are made on an exclusively algorithmic basis must be disclosed.

Further development of recommender systems must take into consideration the implementation and enforcement of GDPR. This represents a challenge that needs to be discussed and overcome.

PD Dr Luis Terán is speaking on this subject at Connecta Bern.