Abstract
The paper describes development of a multi-criteria decision support system (MCDSS) to improve the quality of school education. It is proposed to apply interpretable machine learning models for making decisions on improving the quality of education in secondary schools. Existing DSS are based on the expert judgement, which can be subjective. In addition, the large amount of data and features makes manual analysis difficult. Our approach is referred to as MCDSS with “black boxes” explainer, it consists of three stages. First, we develop the target indicators that measure the quality of education. A set of four features of quality of education (Q-Edu) has been developed. Secondly, we build regression models that link the data of the national educational database (NEDB) with target indicators. Thirdly, we use machine learning model interpreters to develop recommendations. The disadvantage associated with the difficulties of interpreting the results of models is overcome by SHAP (SHapley Additive exPlanations), which is used as a basis for developing recommendations for what features of educational institution could be altered in order to improve quality indicators. Using the described process, we, in particular, revealed the positive impact of the location of the school, ratio of experienced teachers, sports, technical and art studios on Q-Edu indicators. The ratio of experienced teachers and, at the same time, young teachers younger than 25 year positively affects the number of significant student achievements. The proposed universal approach reduces the subjectivity and laboriousness of parameter significance determination in MCDSS.
PUBLIC INTEREST STATEMENT
Secondary education is a state-guaranteed free education level, which is an important link in the formation of personality. One of the task is to ensure equal access to quality education, regardless of regional location, language of instruction and socio-economic status of the family. In this regard, it is necessary to make decisions to improve the quality of education both in general and in a separate school. We offer a decision support system that uses data from the national and international rating agencies and national educational database (NEDB).
To make a decision, we proposed 4 target parameters called Q-Edu, which describe academic achievements and learning outcomes.
These Q-Edu are associated with input NEDB data using a non-linear regression model. We use SHAP (Shapley Additive exPlanations) to evaluate the effect of NEDB parameters in the model. The explanations received are the basis for making informed decisions to improve the quality of education.
Additional information
Funding
Notes on contributors
R. Muhamedyev
R. Muhamedyev (PhD) (shown in the photo) currently holds the positions of professor at Satbayev University (SU) and leading researcher at the Institute of Information and Computational Technologies MES RK (IICT). His research interests include machine learning (ML), natural language processing, decision support systems, scientometrics.
K. Yakunin
K. Yakunin is PhD student of SU and leading programmer-engineer at the IICT. His research interests include ML, data processing, etc.
YA. Kuchin
YA. Kuchin is PhD student of Riga Technical University and programmer-engineer at the IICT.
A. Symagulov
A. Symagulov (M.Sc.) is programmer-engineer at the IICT.
T. Buldybayev
Timur Buldybayev is currently the Director of the Department of Applied Research and Development of the Information Analytical Center. His research interest focuses on social sciences and big data.
S. Murzakhmetov
S. Murzakhmetov (M.Sc.) is a programmer at the IICT.
A. Abdurazakov
A. Abdurazakov is PhD student of SU. His research interest focuses on the use of ML in education.