Information overload is a well-known phenomenon of the information age, since due to the progress in computer power and storage capacity over the last decades, data is produced at an incredible rate, and our ability to collect and store this data is increasing at a faster rate than our ability to analyze it. This gap leads to new challenges in the analysis process since analysts and decision-makers rely on the information hidden within the data. In this context this thesis provides novel scalable analysis techniques that follow the Visual Analytics Mantra in terms of handling massive, heterogeneous volumes of information by integrating human judgment by means of visual representations and interaction techniques in the analysis process. Novel analysis techniques for a number of analysis tasks are presented, that take the special properties of hierarchical-, time-related and geo-related datasets into account. Application examples from a number of scenarios are presented that show how these techniques are successfully applied in business scenarios, including business, process- and financial analysis. Furthermore, the concept of relevance-driven Visual Analytics is introduced, and based on this concept a visualization process model is provided and evaluated that combines automated analysis and image analysis techniques in order to support the user in creating insightful visualizations. Experimental results are presented, that show that this concept can improve the visualization process in terms of scalability and is therefore expected to be useful in many application domains.