Recommender Systems in Industry: Applications, Challenges, and the Academia-Industry Gap

Personalized recommendations are a ubiquitous part of online experiences, and recommender systems have become a major driver of business value across many digital platforms. Numerous success stories across a range of application domains highlight their broad impact, yet significant practical challenges remain unresolved. At the same time, although academic research in this field is thriving and has historically contributed valuable solutions, a concerning gap between academia and industry is emerging. In particular, the increasing emphasis on ever more complex machine learning models and use-case-agnostic evaluation methods raises the question of whether academic efforts are aligned with the most pressing real-world needs. In this paper, we first survey successful recommender system applications from the literature, illustrating their wide applicability and the ways in which they generate business value. We then examine the contributions of academic research in relation to the practical challenges faced in industry. Finally, we issue a call to action for stronger collaboration between academia and industry. We argue that academia should focus more often on problems of practical relevance. In parallel, industry partners should more actively share open challenges and provide access to real-world datasets, enabling researchers to better address practical problems and close the existing gap.