Student dropout rates in distance learning universities are higher than those in conventional universities, therefore reducing the dropout rate is essential in a distance learning system. Many studies have attempted to solve the dropout problem by using various research methodologies. The application of a data warehouse and data mining to the problem of Distance Learning Students’ Dropout is presented. An ETL System was developed to integrate data from the source system into a data warehouse. Then the data warehouse of the students’ dropout in academic years 1999-2006 was developed. Three front-end applications were developed; 1) OLAP 2) reporting and 3) data mining. The OLAP Cube, a multidimensional database, enables users to drill up and drill down the dropout students’ characteristics with several dimensions such as “amount of dropout students in each year by semester, major, school, gender, occupation, income, etc.” The predefined reports were designed and created to support the management planning and decision making via intranet. The data mining techniques; clustering, sequence clustering and time series have been used to mine the information and new knowledge from the data warehouse. Applying the clustering algorithm revealed that the dropout students can be clustered into two groups using the demographic attributes. Sequence clustering revealed the pattern of students’ course registration before they dropped out. Time series equations were calculated precisely to predict the amount of dropout students in each semester and each school.