Reliability of complex equipment and systems and efficient asset management have become major challenges for the economy, sustainability, and safety of today’s advanced societies. Previously, traditional methods relied on static reliability predictions based on scarce data and fixed maintenance plans. These methods suffer limitations in complex and dynamic environments. The digital transformation has now made it possible to evolve towards dynamic methods that exploit increasingly abundant data to update reliability predictions and support maintenance decisions based on asset condition. This evolution is enabled by (i) connectivity and communication (the ‘Internet of Things’), (ii) affordable powerful hardware for parallel computing (such as Graphics Processing Units, GPU) and (iii) advanced algorithms. In this chapter, we shall focus on how artificial intelligence (AI), and more particularly machine learning (ML), can be harnessed to enhance the effectiveness of reliability engineering and to progress towards system operation and maintenance optimization.