In this chapter, the potential integration between quantitative systems pharmacology (QSP) and machine learning (ML) is explored. ML models are in their nature “black boxes”, since they make predictions based on data without explicit system definitions, while on the other hand, QSP models are “white boxes” that describe mechanistic biological interactions and investigate the systems properties emerging from such interactions. Despite their differences, both approaches have unique strengths that can be leveraged to form a powerful integrated tool. ML’s ability to handle large datasets and make predictions is complemented by QSP’s detailed mechanistic insights into drug actions and biological systems. The chapter discusses basic ML techniques and their application in drug development, including supervised and unsupervised learning methods. It also illustrates how combining QSP with ML can facilitate the design of combination therapies against cancer resistance to single therapies. The synergy between these two methodologies shows promise to accelerate the drug development process, making it more efficient and tailored to individual patient needs.