This book comprehensively discusses the role of cloud computing in Artificial Intelligence-based data-driven systems, and hybrid cloud computing for large data-driven applications. It further explores new approaches, paradigms, and frameworks to meet societal challenges by providing solutions for critical insights into data. The text provides internet of things-based frameworks and advanced computing techniques to deal with online virtual systems. The resource-constrained nature of IoT devices leads to not only the challenges of privacy and autonomy but also the major challenge of implementing Machine Learning models for IoT devices. The implementation of Machine Learning models on IoT devices in real-time scenarios poses a major challenge that attracts researchers to work in this domain. To make the IoT ecosystems intelligent, these resource-constrained devices need to be analysed locally. As of now, all sensed data are being processed and analysed in clouds. The small IoT devices may not afford Machine Learning algorithms because of their limited computational power and memory requirements. This involves issues like low bandwidth, high latency, privacy, security and others. Also, there are several Machine Learning algorithms that can be applied for IoT data analytics especially for data-driven systems. Therefore, choosing the best model which is application specific is great work of thought.