Dynamic Content Recommendation Considering Cache State and Preference Using Reinforcement Learning

In recent years, with the spread of services that handle large amounts of content, the importance of content recommendation systems has increased. At the same time, many content providers utilize CDNs (Content Delivery Networks) because delays in content delivery and low throughput lead to an increase in service churn rates. However, when using CDNs in combination, issues arise because the content that should be recommended differs from the user's perspective and the network's perspective. Therefore, if content recommendation does not simultaneously consider both of these factors, there is a risk of degraded delivery quality. While previous studies have considered both factors, most of them assumed static environments. In this paper, we propose a recommendation method that aims to improve both user satisfaction and cache hit rate by utilizing reinforcement learning in an environment where user content preferences change dynamically.