A Linear Bandit for Seasonal Environments
This work addresses seasonal non-stationarity in recommendation systems, which is an incremental improvement over existing methods for non-stationary environments.
The paper tackles the problem of non-stationary reward functions in contextual bandit algorithms, specifically addressing seasonal changes like those in music recommendations during holidays, and shows that their method outperforms state-of-the-art algorithms on synthetic and real datasets.
Contextual bandit algorithms are extremely popular and widely used in recommendation systems to provide online personalised recommendations. A recurrent assumption is the stationarity of the reward function, which is rather unrealistic in most of the real-world applications. In the music recommendation scenario for instance, people's music taste can abruptly change during certain events, such as Halloween or Christmas, and revert to the previous music taste soon after. We would therefore need an algorithm which can promptly react to these changes. Moreover, we would like to leverage already observed rewards collected during different stationary periods which can potentially reoccur, without the need of restarting the learning process from scratch. A growing literature has addressed the problem of reward's non-stationarity, providing algorithms that could quickly adapt to the changing environment. However, up to our knowledge, there is no algorithm which deals with seasonal changes of the reward function. Here we present a contextual bandit algorithm which detects and adapts to abrupt changes of the reward function and leverages previous estimations whenever the environment falls back to a previously observed state. We show that the proposed method can outperform state-of-the-art algorithms for non-stationary environments. We ran our experiment on both synthetic and real datasets.