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

Commit c10c15d

Browse files
committed
Save before refactoring of the paper
1 parent 5c9f215 commit c10c15d

File tree

2 files changed

+10
-3
lines changed

2 files changed

+10
-3
lines changed

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

Lines changed: 10 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -121,7 +121,7 @@ \subsubsection{Analytical approach}
121121
\end{itemize}
122122
We can decisively take into account these factors for our study has they have been proven to be recurrent factors throughout the literature on predicting students dropout.
123123

124-
In another study based in South Korea, they have defined other type of factor for students (high-school students) \cite{lee_machine_2019} :
124+
In another study based in South Korea, they have defined the other type of factor for students (high-school students) \cite{lee_machine_2019} :
125125
\begin{itemize}
126126
\item Diseases
127127
\item Family Problem
@@ -304,9 +304,16 @@ \subsubsection{Predictive Approaches}
304304
\vspace{8pt}
305305
\subsubsection{Conclusion}
306306
This review has shown the multifaceted nature of the issue. The analytical approach — exploring psychological, economic, and socio-cultural dimensions — has emphasized the significance of a broad spectrum of factors. The predictive approach has demonstrated the capabilities of machine learning algorithms in identifying students at risk of dropping out, with techniques like Decision Trees, Logistic Regression, K-Nearest Neighbors, Neural Networks, and Random Forest showing varying levels of precision and applicability.
307+
From the studies in student's dropout, we can extract interesting information to base our subject on. We could use these findings and train our machines differently to predict success and not failure.
307308

308-
%\section{Conclusion}
309-
%Moving forward, the synergy of thorough analytical research with advanced predictive algorithms presents significant potential in addressing student dropout. By continuously refining these models and incorporating a wider array of variables, the predictive accuracy can be enhanced, contributing to the development of more effective educational policies and support systems.
309+
\section{Conceptual implementation}
310+
311+
\begin{figure}
312+
\centering
313+
\includegraphics[width=1\linewidth]{res//diagram/approach_v1_raw.jpeg}
314+
\caption{Methodology mock-up v.1}
315+
\label{fig:enter-label}
316+
\end{figure}
310317

311318
\vspace{16pt}
312319
\section*{Acknowledgment}

res/diagram/approach_v1_raw.jpeg

658 KB
Loading

0 commit comments

Comments
 (0)