Recommender systems using LinUCB - A contextual multi-armed bandit approach

• Metadata
  • Tag: Contextual Bandit, Thompson sampling, LinUCB, Multi-Armed Bandit
  • Link: https://towardsdatascience.com/recommender-systems-using-linucb-a-contextual-multi-armed-bandit-approach-35a6f0eb6c4
  • Related Reference: git_issue_Contextual Bandit 을 활용한 개인화추천 성능 고도화 실험, A Contextual-Bandit Approach to Personalized News Article Recommendation
    • Even though the recorded mean award achieved for Arm 3 is higher, the algorithm selects arm 2 because of the uncertainty of its potential and updates its confidence bound for future trials.