Name (LN, FN, MI): GARCIA, KYLA MAE A.

_________________________________________________ Score: ________

IT 311 – Advanced Database System

Task 3

1. Download and read the article attached. After reading fill out the matrix below.

Author, Year Article Title Problem Objective Methodology Findings Summary Contribution
J. Malini and “Investigation Identifying The main The article employs According to the The article The article adds to the
Y. Kalpana, of factors and objective of this data mining findings of the article, emphasizes the field of educational data
2021 affecting understanding study is to use techniques, economic background significance of mining by emphasizing
student the factors Educational Data including machine factors have a economic the importance of
performance that influence Mining (EDM) learning algorithms, considerable impact on background economic background
evaluation students' techniques to to analyze a students’ characteristics in factors in predicting
using academic characterize the dataset obtained academic performance. predicting and student success. The
education performance, distinct factors from the UCI When including comprehending study, which used
materials data particularly in affecting Repository of economic factors, students' several machine learning
mining the context of students' secondary school bagging and academic algorithms, gives useful
technique” their performance, students' MultiBoost classifiers success. insights for educators
economic with a focus on performance. gave superior accuracy According to the and institutions to build
background. the economic Various classifiers, in early predicting findings, more targeted
background of such as Bagging, students' success. economic interventions and
students. The MultiBoost, and Economic factors such background have support systems to
authors aim to MLP, are used to as family size, parental a substantial improve the academic
predict and assess the impact education, and others impact on the success of kids,
analyze these of different are important ability of students particularly those from
factors through attributes predictors of students' to perform well in low-income families. It
efficient (academic, academic success. their academics. emphasizes the need of
algorithms. personal, and taking a holistic picture
economic of student
background) on characteristics while
student planning and making
performance. educational decisions.
2. Write a reflection of at least 250 words about the article. Observe correct grammar usage, spelling, and sentence construction.

The article "Investigation of factors affecting student performance evaluation using education materials data mining technique" by J. Malini and Y.
Kalpana was a fascinating read. It delves into the world of educational data mining, analyzing a dataset of secondary school students using techniques such
as Bagging, MultiBoost, and MLP.

What's interesting is how the authors focus on students' economic backgrounds and how it affect their academic achievement.What struck me the most
was how these data mining techniques could reveal the significance of economic attributes in predicting student success. The findings imply that a student's
economic background can play a significant role in predicting their academic success. This emphasizes the importance of addressing economic disparities in
education. The article makes a significant addition to the field of educational data mining. It emphasizes the real problems students from varied economic
backgrounds encounter, as well as how these challenges might affect their learning practices and academic performance. This knowledge can be a helpful
resource for educators and policymakers aiming to enhance student performance, particularly for students from low-income families.
The article also emphasizes the significance of viewing students holistically while developing educational programs and making decisions. It serves as a
reminder that data analysis can uncover insights that would otherwise go overlooked.

In conclusion, this article contributes to the body of knowledge in educational data mining and emphasizes the importance of addressing economic
inequities in education. It urges educators and politicians to consider a multifaceted approach to assisting students while increasing their chances of
success.
Author, Year Article Title Problem Objective Methodology Findings Summary Contribution
Pranav “Educational data Predicting To predict students' The study The findings The article highlights This article
Dabhade, mining for students' academic involves data pre- suggest that the the importance of contributes to the
Ravina predicting academic performance using processing, factor linear model and past academic field of educational
Agarwal, students’ performance in a data mining analysis, and the the support performance in data mining by
K.P. academic technical techniques and application of vector regression predicting future demonstrating how
Alameen, performance institution in machine learning machine learning model with a performance. It also machine learning
A.T. using machine India. Academic algorithms. The algorithms. The linear kernel reveals that the algorithms can
Fathima, R. learning institutions are authors aim to use authors used provided the best dataset exhibited a predict students'
Sridharan, algorithms” often concerned a dataset obtained multiple linear fit for the linear relationship, academic
and G. about monitoring through a regression and available dataset. which is why linear performance
Gopakuma, students' questionnaire-based various support They achieved an models performed effectively. It
2021 performance and survey and data vector regression accuracy of well. Additionally, it emphasizes the
taking measures from the academic algorithms to 83.44% for shows that students' importance of past
to improve it. section to identify make predictions. predicting behavior and performance and
Factors affecting factors influencing They also students' personal features the importance of
academic student conducted an in- academic can significantly taking into account
performance are performance. depth analysis of performance in impact academic a student's
multifaceted, the collected the final outcomes. background,
involving data. semester. behavior, and
personal, personal
educational, and characteristics when
behavioral generating
features. predictions. The
article contributes
to knowledge by
utilizing data mining
techniques to
enhance education
and student
outcomes, aiding
educational
institutions and
policymakers in
addressing potential
issues.
 The article starts by addressing a common concern – how can we enhance our academic performance? It's something that we all think about, so the
problem statement of this article feels very relatable. The authors' objective is clear: they aim to predict academic performance using data mining techniques. To
achieve this, they collect data through a survey and combine various aspects, such as personal information and academic history, to make predictions.
The methodology used in the article, which involves data pre-processing and machine learning algorithms, is explained in a way that's easy to understand. It's
great to see how they cleaned the data and reduced its dimensionality to make it more manageable. As a student, I can appreciate the rigorous approach they
took.
The findings are fascinating, showing that linear models and support vector regression are effective in predicting academic performance. What's particularly
noteworthy is that past performance and students' backgrounds and behaviors play a crucial role in making these predictions. As a student, this emphasizes the
importance of maintaining a good academic track record and paying attention to my behavior and habits.
The article's contribution to the field of educational data mining is substantial. It shows how data mining techniques can be practically applied to improve
academic outcomes. This is not just theoretical; it has real-world applications that can benefit both students and educational institutions.
In conclusion, as a fellow student, I see this article as a valuable addition to the education literature. It opened my eyes to the possibilities of using machine
learning to understand and enhance academic performance, and I believe it has relevance and importance for both students and educators.
Author, Year Article Title Problem Objective Methodology Findings Summary Contribution
Marcelo “Evaluating the Students in To evaluate the The researchers The support The study addressed The study shows that
Almeida Effectiveness of introductory efficacy of used data mining vector machine the effectiveness of methods based on
Santana, Educational programming educational data techniques such was the most educational data data mining can be
Evandro B. Data Mining courses fail at a mining techniques as decision tree, successful in mining techniques in used to predict
Costa, Techniques for high rate, which in predicting random forest, predicting predicting student students' academic
Baldoino Early Prediction presents crucial academic failure in and support students' academic failure in failure in
Fonseca, of Students’ problems about introductory vector machine academic failure introductory program introductory program
Joilson Academic Failure prediction programming to predict in introductory ming courses. The ming courses, allowing
Rego, in Introductory features. courses. students' programming researchers gathered educators to act
Fabrísia Programming academic failure courses. information from two immediately to reduce
Ferreira de Courses” from two separate courses and the failure rate. The
Araújo different utilized data mining study also emphasizes
introductory techniques to forecast the importance of
programming students' academic algorithm
courses. failure. The support improvement and data
vector machine was pretreatment in
found to be the most improving prediction
effective tool for algorithms. The
predicting academic findings of this study
failure. can be used to
improve student
performance in
programming classes
and to guide the
development of more
relevant educational
data mining tools.
 The article "Evaluating the effectiveness of educational data mining techniques for early prediction of students' academic failure in introductory
programming courses" to be quite interesting. The article discusses the use of educational data mining techniques to predict students' academic failures in
programming courses. It highlights the importance of identifying students who are likely to fail early on in order to provide timely interventions and support.
The article presents a comparative study that evaluates the effectiveness of different educational data mining techniques in predicting students' academic failures.
It poses several research questions and provides insights into the methodology used in the study. The authors collected data from two independent introductory
programming courses and analyzed the effectiveness of four different techniques, including the Support Vector Machine.
One of the key findings of the study is that the Support Vector Machine technique showed the highest effectiveness in predicting students' failures. This suggests
that this technique could be a valuable tool for educators in identifying students who may be at risk of failing early on. The article also discusses the importance of
data preprocessing and fine-tuning algorithms in improving the effectiveness of the educational data mining techniques.
Overall, the article provides valuable insights into the use of educational data mining techniques for predicting students' academic failures. It highlights the
potential benefits of early identification and intervention in improving student outcomes. As a student, I believe that these techniques could be beneficial in
providing personalized support and guidance to students who may be struggling in programming courses.