Collaborative Filtering with Temporal Dynamics

“Modeling time drifting data is a central problem in data mining. Often, data is changing over time, and up to date modeling should be continuously updated to reflect its present nature. The analysis of such data needs to find the right balance between discounting temporary effects that have very low impact on future behavior, while capturing longer-term trends that reflect the inherent nature of the data. This led to many works on the problem, which is also widely known as concept drift; see e.g. [15, 25].

Modeling temporal changes in customer preferences brings unique challenges. One kind of concept drift in this setup is the emergence of new products or services that change the focus of customers. Related to this are seasonal changes, or specific holidays, which lead to characteristic shopping patterns. All those changes influence the whole population, and are within the realm of traditional studies on concept drift. However, many of the changes in user behavior are driven by localized factors. For example, a change in the family structure can drastically change shopping patterns. Likewise, individuals gradually change their taste in movies and music. All those changes cannot be captured by methods that seek a global concept drift. Instead, for each customer we are looking at different types of concept drifts, each occurs at a distinct time frame and is driven towards a different direction.

The need to model time changes at the level of each individual significantly reduces the amount of available data for detecting such changes. Thus we should resort to more accurate techniques than those that suffice for modeling global changes. For example, it would no longer be adequate to abandon or simply underweight far in time user transactions. The signal that can be extracted from those past actions might be invaluable for understanding the customer herself or be indirectly useful to modeling other customers. Yet, we need to distill long term patterns while discounting transient noise. This requires a more sensitive methodology for addressing drifting customer preferences. It would not be adequate to concentrate on identifying and modeling just what is relevant to the present or the near future. Instead, we require an accurate modeling of each point in the past, which will allow us to distinguish between persistent signal that should be captured and noise that should be isolated from the longer term parts of the model.

Modeling user preferences is relevant to multiple applications ranging from spam filtering to market-basket analysis. Our main focus in the paper is on modeling user preferences for building a recommender system, but we believe that general lessons that we learn would apply to other applications as well. Automated recommendations is a very active research field [12]. Such systems analyze patterns of user interest in items or products to provide personalized recommendations of items that will suit a user’s taste. We expect user preferences to change over time. This may stem from multiple factors, some are fundamental while others are more circumstantial. For example, in a movie recommender system, users may change their preferred genre or adopt a new viewpoint on an actor or director. In addition, they may alter the appearance of their feedback. E.g., in a system where users provide star ratings to products, a user that used to indicate a neutral preference by a “3 stars” input, may now indicate dissatisfaction by the same “3 stars” feedback. Similarly, it is known that user feedback is influenced by anchoring, where current ratings should be taken as relative to other ratings given at the same short period. Finally, in many instances systems cannot separate different household members accessing the same account, even though each member has a different taste and deserves a separate model. This creates a de facto multifaceted meta-user associated with the account. A way to get some distinction between different persons is by assuming that time-adjacent accesses are being done by the same member (sometimes on behalf of other members), which can be naturally captured by a temporal model that assumes a drifting nature of a customer.

All these patterns and the likes should have made temporal modeling a predominant factor in building recommender systems. Nonetheless, with very few exceptions (to be mentioned in Sec. 7), the recommenders literature does not address temporal changes in user behavior. Perhaps, because user behavior is composed of many different concept drifts, all acting in a different timeframe and different directions, thus making common methodologies for dealing with concept drift and temporal data less successful at this setup. We are showing that capturing time drifting patterns in user behavior is essential to improving accuracy of recommenders. This also gives us hope that the insights from successful time modeling for recommenders will be useful in other data mining applications.”