ERP systems contain huge amounts of data related to the actual execution of business processes. These systems have a particular way of recording activities which results in an unclear display of business processes in event logs. Several works have been conducted on ERP systems, most of them focusing on the development of new algorithms for the automatic discovery of business processes. We focused on addressing issues like, how can organizations with ERP systems apply process mining for analyzing their business processes in order to improve them. The data handling aspect of ERP systems contrasts with those of BPMS or workflow based systems, whose systematical storage of events facilitates the application of process mining techniques. CRISP-DM has emerged as the de facto standard for developing data mining and knowledge discovery projects. Successful data mining requires three families of analytical capabilities namely reporting, classification and forecasting. A data miner uses more than one analytical method to get the best results. The objective of this paper is to improve the usability and understandability of process mining techniques, by implementing CRISP-DM methodology for their application in ERP contexts, detailed in terms of specific implementation tools and step by step coordination. Our study confirms that data discovery from ERP system improves strategic and operational decision making.