Traditional data warehouses are manually designed starting from specific requirements and anticipated data analysis needs. As a result there is frequently a disconnect between business process models, business definition of data artifacts and the data stored in the data warehouses as they are often designed manually and in isolation. Hence it has always been a challenge to keep the data warehouse in sync with the continuously changing business process models, resulting in both high maintenance costs and lost opportunities. In this paper we present our Model Driven Data Warehousing (MDDW) approach in the area of Business Performance Management (BPM). The purpose of MDDW is to bridge the gap between the business process models and the data warehouse models, thus enable the rapid adaptation to changes in the business environment. We describe our modeling framework comprising the various modeling elements and meta-models that capture both business and IT data artifacts.