PROMOTING STUDENTS SUCCESS WITH A BUSINESS

INTELLIGENCE SYSTEM

Maria Beatriz Piedade

School of Technology and Management, Polytechnic Institute of Leiria, 2411-901, Leiria, Portugal

Maribel Yasmina Santos

Information Systems Department, Algoritmi Research Centre, University of Minho, 4800-058, Guimarães, Portugal

Keywords: Business Intelligence, Customer Relationship Management, Data Mining, Data Warehouse, on-Line

Analytical Processing, Student Relationship Management.

Abstract: The promotion of the students’ success is usually associated to the closely monitoring of the students’

activities. This requires the implementation of mechanisms that, in the scope of the teaching/learning

process, allow the students’ academic activities monitoring, the students’ academic success/failure

evaluation and the teacher/tutor approximation to the students’ day-by-day academic activities. Although

important, the activities involved in these processes do not take place in many higher education institutions,

due to the lack of an appropriate support. To sustain these complex processes and activities, a conceptual

framework and a technological infrastructure was proposed and integrated in a Student Relationship

Management (SRM) System. The SRM System supports the SRM concept and practice and it has been

implemented using concepts and technologies associated with the Business Intelligence systems. To validate

the SRM System, several application cases were implemented in real contexts. They demonstrated the

system relevance in the process of acquisition of knowledge about the students and their academic

behaviours. The system supports the decision making process in the teaching/learning scope and facilitates

the automatic interaction with the students. The impact of the several undertaken actions are presented and

analysed in this paper.

1 INTRODUCTION

In the generality of the Portuguese Higher Education

Institutions there still exists a high rate of failure and

abandon, mainly in the first year of the graduation

courses. Some statistical result can be seen in the

official web page http://www.gpeari.mctes.pt.

Several actions have been undertaken by the

institutions to identify and to analyse the reasons of

failure, and to propose actions to invert this trend

(Nóvoa, Curado and Machado, 2005, 2006). One of

the actions largely accepted as a way to promote the

students’ success is by implementing mechanisms

that allow the students closely monitoring, the

evaluation of their success/failure and the day-by-

day academic activities approximation by the

teacher/tutor (Pile and Gonçalves, 2007) (Pereira,

Motta and Vaz, 2006). However, the implementation

of all these tasks does not take place in many

institutions. Among the reasons, we point out the

huge number of students with failure in the first

graduation year, the huge number of new students in

some courses and the work overload of the teaching

staff, once they are involved in lecturing,

researching and management tasks. It is required the

definition of institutional practices and an adequate

technological support to these practices. To

overcome these conceptual and technological

limitations, in this work it is developed a conceptual

framework which includes a concept, a practice and

the technological infrastructure that supports the

concept and the practice. The conceptual framework

and the technological infrastructure are in this work

integrated in a Student Relationship Management

(SRM) System. To validate the SRM concept and

practice it was adopted a methodology based on the

Grounded Theory principles. To validate the SRM

system it was adopted a methodology which includes

Piedade M. and Santos M. (2010).

PROMOTING STUDENTS SUCCESS WITH A BUSINESS INTELLIGENCE SYSTEM.

In Proceedings of the 2nd International Conference on Computer Supported Education, pages 46-52

DOI: 10.5220/0002793300460052

 SciTePress

the prototype implementation and the development

of a set of application cases in real contexts. The

concretization of the application cases demonstrates

the SRM system relevance and usability in the

students’ knowledge acquisition process, in the early

identification of failure situations, in the decision-

making support in the scope of teaching/learning

processes and in the automatic interaction with the

students. The results of the implemented actions and

their impact are also presented and analysed in this

paper.

This paper is organized as follows: Section 1

summarizes the motivation for the SRM system

proposal; Section 2 includes an overview of the SRM

principles and presents the SRM concept and

practice (as it was understood in this work) and the

adopted methodology to their validation; Section 3

describes the SRM system architecture and gives

some details about the SRM system implementation.

It also describes the methodology adopted for the

SRM system validation; Section 4 describes the

application cases, analysing the impact, on the

students’ behaviour, of the several actions that were

carried out under the principles of the SRM practice;

Section 5 concludes mentioning the advantages of

the SRM system and summarizing some upcoming

tasks for future work.

2 CONCEPTUAL FRAMEWORK

The SRM system was inspired in principles

associated to the Customer Relationship

Management (CRM) systems. In short, a CRM

system is used in a business environment to support

and manage the relationship between the

organization and their customers. These systems

help to translate customer information into customer

knowledge. This customer knowledge is obtained

using the information and business transactions

available in the organizational databases. Supported

in this customer knowledge, the organization defines

strategies/activities/actions able to maintain a

stronger relationship with clients. Values like

reliance, fidelity, loyalty and durability are present

in this relationship (Payne, 2006).

The SRM system is based on the principles

described above, but supports mainly activities

related with the students and associated with the

teaching-learning processes. Underlying to the SRM

concept is the scholar success promotion, as it is

widely accepted that there exists a high correlation

between the closely monitoring of the students and

their academic success.

To exemplify the similarity between the

CRM/SRM actions, it is possible to compare the

actions developed by the customer’s manager, that

on the scope of the banking activity alerts the

customer when he/she exceeds his/her credit

account, and the actions developed by the student’s

tutor/teacher, that on the scope of the monitoring

processes sends an alert message to the student when

detects that he/she misses several lessons.

The “Student Relationship Management or SRM

or CRM in Higher Education” terms were already

used in technological/commercial environments to

refer solutions mainly dedicated to support processes

related with the students in academic areas

(students’ management information, courses and

lessons management, admissions management,

enrolment and registration management) and areas

related with available services (communications,

marketing, financial aids, accommodation) among

others (Fayerman, 2002). Moreover, these solutions

do not make possible trailing the academic path of

the students in activities concerned with the

teaching-learning processes.

In the scope of this work, it was proposed a

concept, the SRM concept, focused on the students’

academic success promotion. The SRM concept is

understood as a process based on the students’

acquired knowledge, whose main purpose is to keep

an effective student-institution relationship through

the closely monitoring of the students and their

academic activities. This concept, as already stated,

was based on the premise that there exists a strong

correlation between the closely monitoring of the

students’ academic activities and their academic

success promotion. The SRM practice is defined as a

set of activities or actions that should guarantee the

student individual contact, and an effective,

adequate and closely monitoring of his/her academic

performance. To validate the SRM concept and the

set of activities included in the SRM practice, a

research methodology based on the Grounded

Theory principles was adopted. It included the

concretization of a set of interviews (Hansen and

Kautz, 2005). The selected interviewers were

teachers with institutional responsibilities (courses

directors, institution directors, council members).

Each interview was recorded, transcribed and

analysed. The interviews analysis process was done

following the Grounded Theory principles and

supported by the NVivo software (a Computer

Assisted Qualitative Data Analysis Software)

(Budding and Cools, 2007). Each interview was

guided by a script, prepared beforehand, including

also open questions (semi-structured interviews).

PROMOTING STUDENTS SUCCESS WITH A BUSINESS INTELLIGENCE SYSTEM

The interview questions included topics like:

academic success/failure, activities to promote the

success, student-institution relationship, practices to

maintain an effective student-institution relationship,

monitoring indicators, behaviour patterns,

identification of activities that can be automatically

supported, among others (Piedade and Santos,

2008).

3 SRM SYSTEM

The SRM system is the technological infrastructure

that supports the SRM concept and the set of

activities integrating the SRM practice. To undertake

an SRM practice it is necessary: (i) to have

adequate, consistent and complete information about

the students. This information must be stored in an

appropriate data repository, maintaining a single

view of the students’ data; (ii) the analysis of such

data in order to obtain knowledge about the students

and their academic behaviour; (iii) the trigger of

automatic actions over the students whenever

specific situations or behaviours are detected; and

(iv) the assessment of the impact of the undertaken

actions over the students.

The structural topics related with i) and ii)

require the implementation of a data warehouse

system and its exploration using data analysis tools.

Based on this, the SRM system is implemented using

the technological infrastructure that traditionally

supports the Business Intelligence systems, once

these systems combine data gathering, data storage

and knowledge management with analytical tools to

present integrated and useful information to support

the decision making process (Negash and Gray,

2003).

With respect to the issues related with iii) and

iv), the set of relevant indicators and the behaviour

patterns that characterize the different situations to

supervise were identified, as well as the actions to be

automatically done by the different participants in

the SRM practice (teacher, tutor, course director)

were defined and implemented. After the

implementation of a set of actions, their impact on

the students’ academic behaviour and their final

assessment results were analysed.

3.1 Architecture

The SRM system architecture aggregates four main

components: the Data Acquisition and Storage

component, the Data Analysis component, the

Interaction component, and the Assessment

component (Figure 1). The Data Acquisition and

Storage component is responsible for storing the

students’ data in a data warehouse. Data from

different data sources were gathered and were

submitted to the ETL process (Extraction,

Transformation and Loading). The Data Analysis

component, responsible for obtaining knowledge

about the students, includes appropriate data analysis

tools that allow the patterns identification. The

obtained knowledge was stored in an adequate

knowledge database. The Interaction component is

responsible for maintaining an adequate and

effective relationship with the student, using the

obtained student’s knowledge. A set of actions are

automatically triggered (with the students as target)

when it is verified a specific situation or behaviour.

The Assessment component is responsible for the

assessment of all the carried out actions and their

impact, through the monitoring of the students’

academic behaviour and, also, through the

verification of different rates (assiduity, marks, and

interactions with the e-learning platform).

Assessment

Interaction

Data Analysis

Data Aquisition and

Storage

External sources

Analysis Tools

Marks

ETL(Extraction, Transformation, Loading)

Academic

activities

e-learning

Data Warehouse

Data

Knowledge

Actions

Presences

Data Mining Statistical Visualization Reporting Querying

Technological Tools

Communication

Personalization

Actions Definitions

Interaction

Knowledge

Tutor Teacher

Course Director

Actions Execution

Students Group

Student

Monitoring and assessment

Monitoring Assessment

Knowledge database

...

Technological Tools

Statistical Analysis Visualization Reports

OLAP

Tutor

Teacher

...

Student

Course Director

Student

Figure 1: The SRM system’s architecture.

CSEDU 2010 - 2nd International Conference on Computer Supported Education

3.2 Implementation

The SRM system prototype implementation has been

done using database management tools, Business

Intelligence tools and web development tools.

Considering the context in which this work takes

place, the selected development tools integrate the

Microsoft environment: SQL Server Business

Intelligence Development Studio (MSqlServerBIDS)

and Visual Studio .NET. The first one includes a set

of integrated components, Database Engine,

Integration Services, Analysis Services, Reporting

Services and Notification Services for developing

and managing Business Intelligence solutions

(Mundy, Thornthwaite and Kimball, 2006), and the

second one includes a set of development tools for

building ASP.NET web applications.

3.3 Validation

To validate the SRM system, a prototype was

implemented. This prototype shows the relevance of

the SRM concept and supports the SRM practice.

After the prototype implementation, demonstration

cases were carried out in real higher education

contexts.

4 APPLICATION CASE

An application case implementation includes the

following tasks: (i) scenario identification; (ii) data

acquisition and storage; (iii) data analysis; (iv)

interpretation of the obtained results; (v) actions

definition; (vi) execution of the automatic actions

over the students; and (vii) impact assessment of the

carried out actions.

4.1 Application Case Description

As already mentioned, application cases were

undertaken in real contexts of Portuguese Higher

Education institutions. Due to the huge complexity

and diversity of processes related with the students

and having in attention that the “students’ academic

success promotion” is the main issue underlying this

project, this complexity and diversity was limited to

the teaching-learning process. In this application

case, it was selected a graduate course and one of its

curricular units/signatures. The relevant data were

identified and collected. These data include

information about the unit, the adopted teaching-

learning process, the adopted assessment method,

the developed activities, the students and their

interaction in the developed activities and in the

teaching-learning process. Afterwards, the data

warehouse model was designed, implemented and

loaded. The model follows a constellation schema.

Figure 2 represents the data warehouse model for

this application case.

Figure 2: Data warehouse model example.

The facts and dimension tables implementation

was supported by the Database Engine component.

The loading process followed the ETL process steps,

in which the relevant data were extracted from the

source databases, were cleaned (when errors in data

were detected) and were transformed in order to

accomplish the data warehouse format. The loading

process was supported by the Integration Services

component. The data warehouse exploration was

been done using OLAP and data mining techniques.

This data analysis process was supported by the

Analysis Services component.

OLAP techniques allow the analysis of the data

under different perspectives, using the

multidimensional structure of the data warehouse

model. Several cubes were created to analyse the

correlation between the different facts (for instance,

classes presences, e-learning platform accesses, and

results assessment) and also the influence of the

different attributes related with the student (for

instance, full-time/worker-student, registration year,

admission phase, assiduity type). Figure 3 shows an

example of a cube extract. More details about this

cube can be found in (Piedade and Santos, 2009a).

Data mining techniques allow identifying

models that exhibit patterns and trends in data. In

this particular case, the data mining main purpose

was to identify the students’ profile in order to

decrease the failure rate and the failure risk in future

unit editions. A classification task was implemented

to find a model that describes the predictable

attribute as a function of the input attributes. The

PROMOTING STUDENTS SUCCESS WITH A BUSINESS INTELLIGENCE SYSTEM

Figure 3: OLAP cube extract example.

classification task was carried out using a decision

tree algorithm.

One of the obtained models describes the mark

attribute as a function of the input attributes: phase

of admission to higher education (phase), students’

origin local (origin), theoretical classes assiduity rate

(theoretical) and unit interaction through the e-

learning platform (NumDays). Analysing the

obtained model, the students’ profile, considering

the mark results - Fail, Satisfactory, Good and Very

Good, was identified.

This process of obtaining students knowledge

follows the traditional steps of the knowledge

discovery in databases process: data selection, data

treatment, data pre-processing, data mining and

results interpretation (Fayyad and Uthurusamy,

1996).

Figure 4 shows the obtained model in a tree

form. Each tree node has a set of conditions that lead

to a specific decision. More details about this model

can be found in (Piedade and Santos, 2009b).

Figure 4: Data mining model.

OLAP and data mining analyses allow us to

verify that to decrease the failure profile it is

necessary to take special attention to the new

students differentiating them through the admission

phase and, also, by looking at origin local, since

several students are away from their familiar

environment.

The students that are at the first time in the unit

must be encouraged to go in a regular basis to the

different types of classes. These students are, in

many cases, influenced by older students that say to

them to avoid classes, mainly the theoretical classes.

For the second phase students, an additional

support must be given to them as they arrive to the

University when half semester has already passed.

Due to this situation, these students lose the initial

curricular contents explanation and the subsequent

curricular content comprehension, fact that could

help to explain their failure rate. For these cases, the

institution could adopt specific activities or

procedures, as extra classes or tutorial orientation,

providing them additional support. It is also

necessary, for all the students, to verify the evolution

of the project implementation, motivating the

students and providing them additional support

when necessary. This support can be achieved using

tutorial classes. This was not the case of the current

edition of the unit. In what concerns repeating

students, it is also necessary to motivate them to go

to the classes, although in many situations these

students have timetable incompatibilities. To

overcome this limitation, the institution could adopt

a differentiation in the schedule, like classes in the

morning for the first year students and in the

afternoon for the second year students. In

complement, it is also necessary to motivate the use

of the e-learning platform increasing the interaction

of the student with the unit. These different

situations need to be evaluated without neglecting

the students that present a “success profile”.

Regarding the students that are away from home, the

course director/coordinator must take a special

attention to these students, verifying if they have

some integration difficulties and providing them

additional support, if necessary.

The analysis of the obtained profile allows the

identification of the characteristics of the students

that fail the unit and also the ones that are approved

(positive marks) in the unit with satisfactory and

with good marks.

One of the actions identified to fight against the

fail behaviour is the presence of the students in

classes, as the students must go in a regular basis to

the different type of presential classes (theoretical,

practical and tutorial classes). This confirms that the

CSEDU 2010 - 2nd International Conference on Computer Supported Education

presences monitoring is one of the activities that

must be included in the SRM practice. Due to its

importance, this activity was already implemented

and is now supported by a web application.

The web application integrates several

functionalities related with the management of

several entities: the graduate courses, the curricular

units, the groups, the classes, the teachers, tutors, or

course directors, and the students. Figure 5 shows a

page view related with the classes presences. All the

information that could be used to identify a student

was omitted.

Figure 5: Classes page view.

As already mentioned, this application registers

the presence/absence of students in classes. An

automatic alert message is sent by email to the

students when they match certain behaviour (in this

case, a deviating behaviour related with class

presences).

The main purpose of this action is to alert the

students to the importance of their presence in

classes and to the need of a daily study.

An automatic email is also sent in a weekly basis

to the course director/coordinator and to the teacher

responsible by the unit, integrating a report with the

students’ presences. Through this process, the course

director/coordinator, and also the teacher, know how

the semester is going. In case of abnormal situations,

they can take the necessary actions to motivate the

students to be present in the classes. This procedure

also allows the detection of any problem related with

the students and that can affect their behaviour.

Figure 6 shows a view of the presences report.

Neither the student nor the institution is identified in

this example.

Figure 6: Presences report view.

The web application is now functioning by the

first time. A trial version was used on the second

semester of the 2008/2009 curricular year, during

the last five weeks. After this experience, it is

possible to confirm that the automatic e-mailing of

the alert messages has a positive effect on the

students’ behaviour, once their reaction is in general

to make a replay with a personal justification and,

also in general, they attend to the next classes.

The impact of these actions, in the students’

results (marks), could not be assessed with precision

due to fact that the web application operation was

available only during five weeks.

It is only possible to confirm that more students

were evaluated in the final exams, comparatively

with the previous curricular year. However, this

behaviour could not be associated, as a whole, to the

impact of the web application operation.

In this current curricular year (2009/2010), the

web application is already in operation (since the

beginning of the classes). It is expected, at the end of

the semester, the assessment of the results of the

undertaken actions.

Next steps in this project include: (i) the

implementation of other activities that integrate the

SRM practice and that enable the closely monitoring

of the students; (ii) the SRM practice assessment,

verifying its impact on the students’ behaviour and

on their final results.

5 CONCLUSIONS AND FUTURE

WORK

With the implementation of the Bologna Process,

the number of contact hours between the teachers

and the students decreased. This requires, among

PROMOTING STUDENTS SUCCESS WITH A BUSINESS INTELLIGENCE SYSTEM

other things, greater student autonomy. In this

scenario, it is essential to design and to implement

mechanisms that facilitate the monitoring and the

supervising of the students’ academic activities and

that facilitate the interaction with the students. In

this context, we believe that the SRM concept and

practice implementation, supported by the SRM

system, create an advantage towards the students

success promotion, and, therefore, in the institution

success, ensuring an effective student-institution

relationship.

The development of this project has occurred in

different stages. In the first stage, it was defined the

SRM concept and practice and, also, their validation

was carried out. It was also verified the lack of an

adequate technological support to the SRM concept

and practice (such as defined and understood on the

scope of this work). The second stage included the

structural framework definition and the SRM system

architecture proposal. The third stage includes the

SRM prototype implementation and validation. The

future work includes concluding the prototype

implementation and its validation.

REFERENCES

Budding, T. and Cools, M. 2007. The use of computer

software to analyze management accounting field

data: current state and future potential. In 30th

Annual Congress European Accounting Association.

Lisboa. 24-27 April 2007.

Fayerman, M. 2002. "Customer Relationship

Management." New Directions for Institutional

Research nº113 57-67.

Fayyad, U. and Uthurusamy, R. 1996. "Data mining and

Knowledge Discovery in Databases." Communications

of the ACM 39(11): 24-26.

Hansen, B. H. and Kautz, K. 2005. Grounded Theory

Applied - Studying Information Systems Development

Methodologies in Practice. In Proceedings of the 38th

Annual Hawaii International Conference on Systems

Sciences.

Mundy, J., Thornthwaite, W. and Kimball, R. 2006. The

Microsoft Data Warehouse Toolkit with SQL Server

2005 and the Microsoft Business Intelligence Toolset:

Wiley Publishing, Inc.

Negash, S. and Gray, P. 2003. Business Intelligence. In

Ninth Americas Conference on Information Systems.

Nóvoa, A., Curado, A. P. and Machado, J. 2005. Percursos

Escolares dos Estudantes da Universidade de Lisboa:

Factores de sucesso e insucesso escolar na

Universidade de Lisboa. Edição: Reitoria da

Universidade de Lisboa. 2005. (in Portuguese).

Nóvoa, A., Curado, A. P. and Machado, J. 2006. Percursos

Escolares dos Estudantes da Universidade de Lisboa:

Estudo sobre abandono. Edição: Reitoria da

Universidade de Lisboa. 2006. (in Portuguese).

Payne, A. 2006. Handbook of CRM. Achieving

Excellence in Customer Management: Elsevier-BH

Pereira, A., Motta, E. and Vaz, A. 2006. "Sucesso e

desenvolvimento psicológico no Ensino Superior:

Estratégias de intervenção" (in Portuguese). Aná.

Psicológica. [online]. 24(1): 51-59.

Piedade, M. B. and Santos, M. Y. 2008. Student

Relationship Management: Concept, Practice and

Technological Support. In IEMC 2008 - IEEE

International Engineering Management Conference.

Estoril. Portugal. 28-30 June 2008.

Piedade, M. B. and Santos, M. Y. 2009a. Business

Intelligence in Higher Education Institution:

Managing the Relationships with Students. In KDIR -

International Conference on Knowledge Discovey and

Information Retrieval. Funchal. Madeira. Portugal. 6-8

October 2009.

Piedade, M. B. and Santos, M. Y. 2009b. Business

Intelligence Supporting the Teaching-Learning. In

Proceedings of the 5th WSEAS International

Symposium on Data Mining and Information

Processing. Budapest Tech. Budapest. Hungary. 3-5

September 2009.

Pile, M. and Gonçalves, I. 2007. Programa de

Monitorização e Tutorado (in Portuguese). In "A

qualidade em estabelecimentos de ensino superior.

Exemplo de boas práticas". Instituto Português da

Qualidade. Caparica. 15 Novembro 2007.

CSEDU 2010 - 2nd International Conference on Computer Supported Education