Cold start

Cold start is a potential problem in computer-based information systems which involve a degree of automated data modelling. Specifically, it concerns the issue that the system cannot draw any inferences for users or items about which it has not yet gathered sufficient information.

Systems affected

The cold start problem is most prevalent in recommender systems. Recommender systems form a specific type of information filtering (IF) technique that attempts to present information items (movies, music, books, news, images, web pages) that are likely of interest to the user. Typically, a recommender system compares the user's profile to some reference characteristics. These characteristics may be from the information item (the content-based approach) or the user's social environment (the collaborative filtering approach).

In the content-based approach, the system must be capable of matching the characteristics of an item against relevant features in the user's profile. In order to do this, it must first construct a sufficiently-detailed model of the user's tastes and preferences through preference elicitation. This may be done either explicitly (by querying the user) or implicitly (by observing the user's behaviour). In both cases, the cold start problem would imply that the user has to dedicate an amount of effort using the system in its 'dumb' state – contributing to the construction of their user profile – before the system can start providing any intelligent recommendations.

In the collaborative filtering approach, the recommender system would identify users who share the same preferences (e.g. rating patterns) with the active user, and propose items which the like-minded users favoured (and the active user has not yet seen). Due to the cold start problem, this approach would fail to consider items which no-one in the community has rated previously.^[1]

The cold start problem is also exhibited by interface agents. Since such an agent typically learn the user's preferences implicitly by observing patterns in the user's behaviour – "watching over the shoulder" – it would take time before the agent may perform any adaptations personalised to the user. Even then, its assistance would be limited to activities which it has formerly observed the user engaging in.^[2]

Solutions

There are several solutions that have been proposed to tackle the cold start problem. One of the effective solutions is to apply Active learning (machine learning) techniques, i.e., selectively choosing and obtaining more data, that can most improve the performance of the recommender system. This is done by analysing the available data and estimating the usefulness of the data points (e.g., ratings) .^[3] In Collaborative Filtering recommender systems, these techniques are so called rating elicitation Strategies .^[4]

In scenarios involving interface agents, the cold start problem may be overcome by introducing an element of collaboration amongst agents assisting various users. This way, novel situations may be handled by requesting other agents to share what they have already learnt from their respective users.^[2]

In recommender systems, the cold start problem is often reduced by adopting a hybrid approach between content-based matching and collaborative filtering. New items (which have not yet received any ratings from the community) would be assigned a rating automatically, based on the ratings assigned by the community to other similar items. Item similarity would be determined according to the items' content-based characteristics.^[1]

The construction of the user's profile may be automated by integrating information from other user activities, such as browsing histories. If, for example, a user has been reading information about a particular music artist from a media portal, then the associated recommender system would automatically propose that artist's releases when the user visits the music store.^[5]

It is also possible to create initial profile of a user based on the Personality characteristics of the user and use such profile to generate personalized recommendation.^{[6] [7]} Personality characteristics of the user can be identified using a personality model such as Five Factor Model (FFM).

See also

• Collaborative filtering
• Preference elicitation
• Recommender system
• Active learning (machine learning)
• Five Factor Model

References

1. Andrew I. Schein, Alexandrin Popescul, Lyle H. Ungar, David M. Pennock (2002). Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2002). Methods and Metrics for Cold-Start Recommendations. New York City, New York: ACM. pp. 253–260. ISBN 1-58113-561-0.
2. Yezdi Lashkari, Max Metral, Pattie Maes (1994). Proceedings of the Twelfth National Conference on Artificial Intelligence. Collaborative Interface Agents. Seattle, Washington: AAAI Press. pp. 444–449. ISBN 0-262-61102-3.
3. Rubens, Neil; Elahi, Mehdi; Sugiyama, Masashi; Kaplan, Dain (2016). "Active Learning in Recommender Systems". In Ricci, Francesco; Rokach, Lior; Shapira, Bracha. Recommender Systems Handbook (2 ed.). Springer US. ISBN 978-1-4899-7637-6.
4. Elahi, Mehdi; Ricci, Francesco; Rubens, Neil. Active Learning in Collaborative Filtering Recommender Systems. Springer International Publishing. pp. 113–124. ISBN 978-3-319-10491-1.
5. Xiam (2007-06-29). "Vendor attempts to crack ‘cold start’ problem in content recommendations". Mobile Media (PDF) (United Kingdom: Informa Telecoms & Media): 18.
6. Tkalcic, Marko; Chen, Li (2016). "Personality and Recommender Systems". In Ricci, Francesco; Rokach, Lior; Shapira, Bracha. Recommender Systems Handbook (2 ed.). Springer US. ISBN 978-1-4899-7637-6.
7. Fernández-Tobías, Ignacio; Braunhofer, Matthias; Elahi, Mehdi; Ricci, Francesco; Cantador, Iván (2016). "Alleviating the new user problem in collaborative filtering by exploiting personality information". User Modeling and User-Adapted Interaction. doi:10.1007/s11257-016-9172-z.

, .