Analysis of Students’ Academic Performance by Using Machine Learning Tools
F.M. Gafarov, Ya.B. Rudneva, U.Yu. Sharifov, A.V. Trofimova, P.M. Bormotov
Available Online 13 May 2020.
- https://doi.org/10.2991/assehr.k.200509.104How to use a DOI?
- academic (educational) analytics, data mining, Python, predictors, academic success, forecasting, neural networks
- In higher education, considerable experience has been gained in applying analytics using multidimensional databases (including retrospective ones). One of the promising areas in this area is data mining. Data mining as an interdisciplinary field of research allows creating predictive models of students’ academic success. However, questions remain in the scientific community about the types and sources of data relevant for building prognostic models, about the methods of processing this data, and about the variables that determine students’ academic success. The purpose of the study is to analyze, using machine learning methods and artificial neural networks, which variables affect the academic success of students. SPSS Statistics and data mining methods using the Python programming language were used to process and analyze data. The study analyzed data on student performance at Kazan Federal University from 2012 to 2019. Preliminary results showed that data mining methods have good potential for creating information-analytical systems that allow not only modeling or visualizing data, but also predicting stable trends.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - F.M. Gafarov AU - Ya.B. Rudneva AU - U.Yu. Sharifov AU - A.V. Trofimova AU - P.M. Bormotov PY - 2020 DA - 2020/05/13 TI - Analysis of Students’ Academic Performance by Using Machine Learning Tools BT - International Scientific Conference “Digitalization of Education: History, Trends and Prospects” (DETP 2020) PB - Atlantis Press SP - 570 EP - 575 SN - 2352-5398 UR - https://doi.org/10.2991/assehr.k.200509.104 DO - https://doi.org/10.2991/assehr.k.200509.104 ID - Gafarov2020 ER -