Skip to content
This repository was archived by the owner on Sep 29, 2025. It is now read-only.

Commit 5dc186b

Browse files
committed
Reformat the structure of the project. Conceptual Proposal + Analysis
1 parent c10c15d commit 5dc186b

14 files changed

+561
-336
lines changed

Data-Driven Admissions in Education: Enhancing Student Success by Matching Profiles to Optimal Academic Paths.tex

Lines changed: 0 additions & 325 deletions
This file was deleted.

bib/references.bib

Lines changed: 150 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,143 @@
11

2+
@inreference{noauthor_bootstrap_2023,
3+
title = {Bootstrap aggregating},
4+
rights = {Creative Commons Attribution-{ShareAlike} License},
5+
url = {https://en.wikipedia.org/w/index.php?title=Bootstrap_aggregating&oldid=1169729264},
6+
abstract = {Bootstrap aggregating, also called bagging (from bootstrap aggregating), is a machine learning ensemble meta-algorithm designed to improve the stability and accuracy of machine learning algorithms used in statistical classification and regression. It also reduces variance and helps to avoid overfitting. Although it is usually applied to decision tree methods, it can be used with any type of method. Bagging is a special case of the model averaging approach.},
7+
booktitle = {Wikipedia},
8+
urldate = {2023-12-14},
9+
date = {2023-08-10},
10+
langid = {english},
11+
note = {Page Version {ID}: 1169729264},
12+
}
13+
14+
@inreference{noauthor_random_2023,
15+
title = {Random forest},
16+
rights = {Creative Commons Attribution-{ShareAlike} License},
17+
url = {https://en.wikipedia.org/w/index.php?title=Random_forest&oldid=1189363809},
18+
abstract = {Random forests or random decision forests is an ensemble learning method for classification, regression and other tasks that operates by constructing a multitude of decision trees at training time. For classification tasks, the output of the random forest is the class selected by most trees. For regression tasks, the mean or average prediction of the individual trees is returned. Random decision forests correct for decision trees' habit of overfitting to their training set.: 587–588 The first algorithm for random decision forests was created in 1995 by Tin Kam Ho using the random subspace method, which, in Ho's formulation, is a way to implement the "stochastic discrimination" approach to classification proposed by Eugene Kleinberg.An extension of the algorithm was developed by Leo Breiman and Adele Cutler, who registered "Random Forests" as a trademark in 2006 (as of 2019, owned by Minitab, Inc.). The extension combines Breiman's "bagging" idea and random selection of features, introduced first by Ho and later independently by Amit and Geman in order to construct a collection of decision trees with controlled variance.},
19+
booktitle = {Wikipedia},
20+
urldate = {2023-12-14},
21+
date = {2023-12-11},
22+
langid = {english},
23+
note = {Page Version {ID}: 1189363809},
24+
}
25+
26+
@misc{noauthor_donnees_2022,
27+
title = {Données relatives à l’épidémie de {COVID}-19 en France : vue d’ensemble},
28+
url = {https://www.data.gouv.fr/fr/datasets/donnees-relatives-a-lepidemie-de-covid-19-en-france-vue-densemble/},
29+
number = {5f69ecb155c43420918410b8},
30+
urldate = {2023-12-09},
31+
date = {2022-05-17},
32+
}
33+
34+
@misc{noauthor_statistiques_2023,
35+
title = {Statistiques sur les effectifs d'étudiants inscrits par établissement public sous tutelle du ministère en charge de l'Enseignement supérieur (avec doubles inscriptions {CPGE})},
36+
url = {https://www.data.gouv.fr/fr/datasets/statistiques-sur-les-effectifs-detudiants-inscrits-par-etablissement-public-sous-tutelle-du-ministere-en-charge-de-lenseignement-superieur-avec-doubles-inscriptions-cpge/#/resources/0c713161-26fb-415e-ac1d-8769125f338d},
37+
number = {0c713161-26fb-415e-ac1d-8769125f338d},
38+
urldate = {2023-12-09},
39+
date = {2023-09-26},
40+
}
41+
42+
@online{noauthor_hes-so_nodate,
43+
title = {{HES}-{SO} - Gouvernance - Haute école},
44+
url = {https://www.hes-so.ch/la-hes-so/a-propos/gouvernance},
45+
urldate = {2023-11-30},
46+
}
47+
48+
@misc{taplin_toc-tech-papers_imppdf_2013,
49+
title = {{ToC}-Tech-Papers\_imp.pdf},
50+
author = {Taplin, Dr. Dana H. and Collins, Eoin and Clark, Dr. Heléne and Colby, David C.},
51+
urldate = {2023-10-31},
52+
date = {2013-04},
53+
}
54+
55+
@book{ahrne_meta-organizations_2008,
56+
title = {Meta-organizations},
57+
isbn = {978-1-84844-265-8},
58+
abstract = {A growing number of organizations are meta-organizations; rather than individuals they have other organizations as their members. This comprehensive book explains, in-depth, the unique way in which meta-organizations function, how they differ from organizations with individual membership, and how they are crucial agents in the process of globalization.},
59+
pagetotal = {201},
60+
publisher = {Edward Elgar Publishing},
61+
author = {Ahrne, Göran and Brunsson, Nils},
62+
date = {2008-01-01},
63+
langid = {english},
64+
keywords = {Business \& Economics / Management},
65+
}
66+
67+
@article{gulati_meta-organization_2012,
68+
title = {Meta-organization design: Rethinking design in interorganizational and community contexts},
69+
volume = {33},
70+
rights = {Copyright © 2012 John Wiley \& Sons, Ltd.},
71+
issn = {1097-0266},
72+
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/smj.1975},
73+
doi = {10.1002/smj.1975},
74+
shorttitle = {Meta-organization design},
75+
abstract = {This article provides conceptual foundations for analyzing organizations comprising multiple legally autonomous entities, which we call meta-organizations. We assess the antecedents of the emergence of such collectives and the design choices they entail. The article identifies key parameters on which such meta-organizations' designs differ from each other. It also presents a taxonomy that elucidates how such forms of collective action vary and the constraints they must address to be successful. We conclude with implications for research on meta-organizational design. Copyright © 2012 John Wiley \& Sons, Ltd.},
76+
pages = {571--586},
77+
number = {6},
78+
journaltitle = {Strategic Management Journal},
79+
author = {Gulati, Ranjay and Puranam, Phanish and Tushman, Michael},
80+
urldate = {2023-11-13},
81+
date = {2012},
82+
langid = {english},
83+
note = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/smj.1975},
84+
keywords = {communities, design, interorganizational relationships, meta-organization},
85+
}
86+
87+
@article{berkowitz_concept_2016,
88+
title = {The Concept of Meta-Organization: Issues for Management Studies},
89+
volume = {13},
90+
rights = {© 2016 European Academy of Management},
91+
issn = {1740-4762},
92+
url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/emre.12076},
93+
doi = {10.1111/emre.12076},
94+
shorttitle = {The Concept of Meta-Organization},
95+
abstract = {In a seminal paper, Ahrne and Brunsson coined the word ‘meta-organization’. More than a label, this word describes a challenging and stimulating concept that can be valuable for management studies when approached with different units of analysis and research methodologies. ‘Meta-organization’ refers to a central phenomenon in the contemporary world, namely the increasing importance of collective action at the level of organizations, ensuing from major issues related to sustainable development, human rights and corporate responsibility. The concept calls for new forms of theorizing of global collective action. The diversity and heterogeneity of meta-organizations raise methodological issues that require original approaches. In this paper, we show the novelty of the concept of meta-organization; we then address the methodological difficulties and propose a research agenda on meta-organizations for management studies.},
96+
pages = {149--156},
97+
number = {2},
98+
journaltitle = {European Management Review},
99+
author = {Berkowitz, Héloïse and Dumez, Hervé},
100+
urldate = {2023-11-13},
101+
date = {2016},
102+
langid = {english},
103+
note = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1111/emre.12076},
104+
keywords = {collective action, concept, inter-organizational collaboration, meta-organization, research methodology},
105+
}
106+
107+
@online{noauthor_concept_nodate,
108+
title = {The Concept of Meta‐Organization: Issues for Management Studies - Berkowitz - 2016 - European Management Review - Wiley Online Library},
109+
url = {https://onlinelibrary.wiley.com/doi/10.1111/emre.12076},
110+
urldate = {2023-11-13},
111+
}
112+
113+
@misc{european_commision_european_2019,
114+
title = {The European Universities Initiative: first lessons, main challenges and perspectives},
115+
author = {European Commision},
116+
urldate = {2002-10-31},
117+
date = {2019},
118+
}
119+
120+
@online{hearn_when_2016,
121+
title = {When and how to develop an impact-oriented monitoring and evaluation system},
122+
url = {https://odi.org/en/publications/when-and-how-to-develop-an-impact-oriented-monitoring-and-evaluation-system/},
123+
abstract = {This guidance note looks at what an impact-oriented M\&E system involves, and when might it be useful to establish one},
124+
titleaddon = {{ODI}: Think change},
125+
author = {Hearn, Simon and Pasanen, Tiina and Buffardi, Anne},
126+
urldate = {2023-11-11},
127+
date = {2016-03-07},
128+
langid = {english},
129+
}
130+
131+
@online{unita_unita_nodate,
132+
title = {{UNITA} - Universitas Montium},
133+
url = {http://www.univ-unita.ubi.pt},
134+
abstract = {{UNITA} - We are an alliance of six comprehensive research universities from five countries with different sizes and trajectories gathering together more than 160 000 students and 13 000 staff members.},
135+
titleaddon = {{UNITA} - Universitas Montium},
136+
author = {{UNITA}},
137+
urldate = {2023-11-11},
138+
langid = {portuguese},
139+
}
140+
2141
@article{kuh_what_2006,
3142
title = {What Matters to Student Success: A Review of the Literature},
4143
abstract = {{THE} {FOUNDATION} {FOR} {STUDENT} {SUCCESS}: {STUDENT} {BACKGROUND} {CHARACTERISTICS}, {PRECOLLEGE} {EXPERIENCES}, {AND} {ENROLLMENT} {PATTERNS}................................................................},
@@ -1017,17 +1156,6 @@ @article{kuh_assessing_2001
10171156
note = {Publisher: Taylor \& Francis},
10181157
}
10191158

1020-
@article{sandoval_understanding_2005,
1021-
title = {Understanding students' practical epistemologies and their influence on learning through inquiry},
1022-
volume = {89},
1023-
pages = {634--656},
1024-
number = {4},
1025-
journaltitle = {Science education},
1026-
author = {Sandoval, William A.},
1027-
date = {2005},
1028-
note = {Publisher: Wiley Online Library},
1029-
}
1030-
10311159
@article{lovas_higher_1980,
10321160
title = {Higher Degree Examination Procedures in Australian Universities.},
10331161
volume = {23},
@@ -1039,6 +1167,17 @@ @article{lovas_higher_1980
10391167
note = {Publisher: {ERIC}},
10401168
}
10411169

1170+
@article{sandoval_understanding_2005,
1171+
title = {Understanding students' practical epistemologies and their influence on learning through inquiry},
1172+
volume = {89},
1173+
pages = {634--656},
1174+
number = {4},
1175+
journaltitle = {Science education},
1176+
author = {Sandoval, William A.},
1177+
date = {2005},
1178+
note = {Publisher: Wiley Online Library},
1179+
}
1180+
10421181
@article{rastrollo-guerrero_analyzing_2020,
10431182
title = {Analyzing and predicting students’ performance by means of machine learning: A review},
10441183
volume = {10},

main.tex

Lines changed: 88 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,88 @@
1+
\documentclass[conference]{IEEEtran}
2+
\IEEEoverridecommandlockouts
3+
% The preceding line is only needed to identify funding in the first footnote. If that is unneeded, please comment it out.
4+
\usepackage{cite}
5+
\usepackage{amsmath,amssymb,amsfonts}
6+
\usepackage{algorithmic}
7+
\usepackage{graphicx}
8+
\usepackage{textcomp}
9+
\usepackage{xcolor}
10+
\usepackage{float}
11+
\usepackage{subfiles}
12+
%\restylefloat{table}
13+
\def\BibTeX{{\rm B\kern-.05em{\sc i\kern-.025em b}\kern-.08em
14+
T\kern-.1667em\lower.7ex\hbox{E}\kern-.125emX}}
15+
\begin{document}
16+
17+
18+
\title{Data-Driven Admissions in Education: Enhancing Student Success by Matching Profiles to Optimal Academic Paths\\
19+
{\footnotesize \textsuperscript{}}
20+
\thanks{}
21+
}
22+
23+
\author{\IEEEauthorblockN{Clément Combier}
24+
\IEEEauthorblockA{\textit{Master 2 SIGLIS} \\
25+
\textit{Université de Pau et des Pays de l'Adour}\\
26+
Anglet, France \\
27+
28+
\maketitle
29+
\thispagestyle{plain}
30+
\pagestyle{plain}
31+
32+
\tableofcontents
33+
34+
\section*{abbreviation}
35+
\begin{itemize}
36+
\item[] AI : Artificial Intelligence
37+
\item[] ML : Machine learning
38+
\item[] KNN : K-Nearest Neighbors
39+
\item[] CNN : Convolutional Neural Networks
40+
\item[] RNN Recurrent Neural Networks
41+
\item[] SVM : Support Vector Machines
42+
\item[] RF : Random Forest
43+
\item[] SMOTE : Synthetic Minority Oversampling TEchniques
44+
\end{itemize}
45+
46+
47+
\vspace{16pt}
48+
49+
\begin{abstract}
50+
In the wake of the COVID-19 pandemic and the release of the new \textit{baccalaureate} reform, French education authorities in higher studies faces a surge of enrolments and higher dropouts numbers. Higher grade from students in the baccalaureate as lead, the French registration system in place to accept more and more students in higher degrees paths. Sadly, these new reforms did not take into account the difficulty step created between secondary and higher studies. Thus augmenting the number of dropouts in students who don't have the capacity, motivation and/or will to continue in their path.
51+
52+
We propose a solution to mitigate this dropout as well as helping academia to find \textit{excellence students} with compatible profile for a certain path (diploma and domain). Taking the problem at its root could lead to a \textit{two birds with one stone} resolution to the problem.
53+
54+
This paper focuses on critical issues within the education system and tries to differ a more holistic and personalized approach to student placement. By using data mining, analytic and machine learning, we hope to create a more harmonious and productive education landscape for both students and academic alike.
55+
\end{abstract}
56+
\vspace{8pt}
57+
58+
\begin{IEEEkeywords}
59+
Higher education, Admission process, Machine learning, Data analytics, Success rate, Dropout rate, Student profile, Optimization, Profile-degree matching, Admission management, High-achieving students, Adaptive education.
60+
\end{IEEEkeywords}
61+
\vspace{16pt}
62+
63+
\section{Introduction}
64+
\label{sec:introduction}
65+
\subfile{sections/introduction}
66+
67+
\section{State of the art}
68+
\label{sec:soa}
69+
\subfile{sections/soa}
70+
71+
72+
\section{Analysis}
73+
\label{sec:analysis}
74+
\subfile{sections/analysis}
75+
76+
77+
\section{Conceptual implementation}
78+
\label{sec:conceptualanalysis}
79+
\subfile{sections/conceptual_proposal}
80+
81+
\vspace{16pt}
82+
\section*{Acknowledgment}
83+
\vspace{12pt}
84+
85+
\bibliographystyle{plain}
86+
\bibliography{bib/references}
87+
88+
\end{document}

res/AlgorithmDefinition.tex

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,4 @@
1+
\section{Random Forest}
2+
3+
In particular, trees that are grown very deep tend to learn highly irregular patterns: they overfit their training sets, i.e. have low bias, but very high variance.
4+
\cite{noauthor_random_2023}

res/diagram/ML Workflow.png

81.5 KB
Loading

sections/analysis.tex

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,16 @@
1+
\documentclass[../main.tex]{subfiles}
2+
\graphicspath{{\subfix{../res/}}}
3+
\begin{document}
4+
We will now do an analysis from the literature review on how we can approach the problem, using what's been already made and how we can improve on it.
5+
6+
\subsection{Factors}
7+
First of all, what differentiate this research from all the other we have read throughout the literature analysis is that we are not seeking prediction on student's dropout but rather on student success and early in the process and not during the curriculum year. However, there is plenty of interesting information we can gather from these papers. As described in the \ref{sec:soa} State of Art, we can gather factors that, in theory could help predict student's dropout. We can hypothesize that by using these factors to determine if one student is at risk of dropping-out, it could for another predict its success in a specific formation. From the list of factors we were able to gather, we have made a statistical analysis of the frequency they appear and their overall score within each paper they are mention it. Below, the table from this study concluding our research.
8+
9+
\subsection{Machine Learning algorithm}
10+
Secondly, we need to understand which algorithm model have been used the most and which present the best outcome for our need. As for the factors, we can extrapolate the problem and take it in reverse. So by learning which algorithm presents the best result to predict student's dropout, we could hypothesize that they could also be used to detect student's success.
11+
12+
\subsection{Analysis conclusion}
13+
Both our hypothesis and result must now be verified by providing a methodology and using a test dataset to send to our pipeline in order to feed our machines.
14+
We may find that one or both hypothesis are not correct and we will need to restudy factors and machine learning algorithm to answer our need and problematic.
15+
In the next part, \ref{sec:conceptualanalysis} Conceptual implementation, we are going to present our methodology and workflow. Explaining the reasons for our choice of factors and algorithm as well as presenting our entire pipeline for our system.
16+
\end{document}

sections/conceptual_proposal.tex

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,20 @@
1+
\documentclass[../main.tex]{subfiles}
2+
\graphicspath{{\subfix{../res/}}}
3+
\begin{document}
4+
5+
We now need to create our pipeline and workflow before we can start building it. The questions we need to answer are : what data are we going to feed into the pipeline and which algorithm are we going to feed?
6+
It is clear that by the results from our state of the art and analysis that not one algorithm must be used in our workflow to achieve the best result.
7+
To extract as much information and get the possible best results, we have split our system into three inner parts, each with their responsibility, input and output.
8+
But first, let's look into which data we have access to and what to use to feed our system.
9+
10+
\subsection{Feeding data}
11+
\label{subsec:conceptualimplementation_feedingdata}
12+
13+
\begin{figure*}
14+
\centering
15+
\includegraphics[width=\textwidth]{res//diagram/ML Workflow.png}
16+
\caption{Machine Learning methodology}
17+
\label{fig:Machine workflow}
18+
\end{figure*}
19+
20+
\end{document}

0 commit comments

Comments
 (0)