Renza Campagni

Data mining models for student careers

We presents a data mining methodology to analyze the careers of University graduated students.We present different approaches based on clustering and sequential patterns techniques.We introduce the concept of ideal career.We compare the career of a generic student with the ideal one.We apply the methodology to a real case study and interpret the results. This paper presents a data mining methodology to analyze the careers of University graduated students. We present different approaches based on clustering and sequential patterns techniques in order to identify strategies for improving the performance of students and the scheduling of exams. We introduce an ideal career as the career of an ideal student which has taken each examination just after the end of the corresponding course, without delays. We then compare the career of a generic student with the ideal one by using the different techniques just introduced. Finally, we apply the methodology to a real case study and interpret the results which underline that the more students follow the order given by the ideal career the more they get good performance in terms of graduation time and final grade.

Finding Regularities in Courses Evaluation with K-means Clustering

This paper presents an analysis about the courses evaluation made by university students together with their results in the corresponding exams. The analysis concerns students and courses of a Computer Science program of an Italian University from 2001/2002 to 2007/2008 academic years. Before the end of each course, students evaluate different aspects of the course, such as the organization and the teaching. Evaluation data and the results obtained by students in terms of grades and delays with which they take their exams can be collected and reorganized in an appropriate way. Then we can use clustering techniques to analyze these data thus show possible correlation between the evaluation of a course and the corresponding average results as well as regularities among groups of courses over the years. The results of this type of analysis can possibly suggest improvements in the teaching organization.

University Student Progressions and First Year Behaviour.

Advanced mining techniques are used on educational data concerning university students. In particular, cluster analysis is used to predict the university careers of students starting from their first year performance and the results of the self assessment test. The analysis of the entire careers highlights three groups of students strongly affected by the results of the first year: high achieving students who start medium-high and increase their performance over the time, medium achieving students who maintain their performance throughout the entire course of study, low achieving students unable to improve their performance who often abandon their studies. This kind of knowledge can have practical implications on the involved laurea degree.

The Influence of First Year Behaviour in the Progressions of University Students

Advanced clustering techniques are used on educational data concerning various cohorts of university students. First, K-means analysis is used to classify students according to the results of the self assessment test and the first year performance. Then, the analysis concentrates on the subset of the data involving the cohorts of students for which the behavior during the first, second and third year of University is known. The results of the second and third year are analyzed and the students are re-assigned to the clusters obtained during the analysis of the first year. In this way, for each student we are able to obtain the sequence of traversed clusters during three years, based on the results achieved during the first. For the data set under analysis, this analysis highlights three groups of students strongly affected by the results of the first year: high achieving students who start high and maintain their performance over the time, medium-high achieving students throughout the entire course of study and, low achieving students unable to improve their performance who often abandon their studies. This kind of study can be used by the involved laurea degree to detect critical issues and undertake improvement strategies.

A Preprocessing Design Scheme for Sequential Pattern Analysis of a Student Database

In a data mining project evolved on a relational database often a significant effort needs to be done to construct the data set for the analysis. In fact, usually the database contains a series of normalized tables that need to be joined, aggregated and processed in an appropriate way to build the data set. This process generates various SQL queries that are written independently of each other, in a disordered manner. In this way, the database grows with tables and views which are not present at the conceptual level and this can yield problems for the development of the database. In this paper we consider a typical database containing data about students, courses and exams and illustrate some SQL transformations to build a data set to perform a sequential pattern analysis eventually combined with clustering and classification. In particular, we introduce in the student database some interesting patterns representing relationship between the exams given by students in various periods and the career of each student. This is achieved by introducing a particular encoding of a the career of a student. The resulting table can be analyzed with clustering and classification algorithms. We present a case study following this organization.

An Analysis of Courses Evaluation Through Clustering

Students of the University of Florence (Italy), before taking an exam, are required to assess different aspects related to the course organization and to the teaching. The data concerning the evaluation of the courses of the Computer Science Program from 2001/2002 to 2007/2008 academic years were collected and linked to the results of students: the grades obtained in the corresponding exams and the delays, with respect to the end of the courses, with which exams were taken. After this preprocessing phase, we used clustering techniques to analyze data and we highlighted a correlation between courses evaluation and the corresponding average student results, as well as regularities among groups of courses over the years. Our analysis can be used to detect possible improvements in the organization and teaching of the degree program and applied to any university context collecting similar data.