Recommender system to identify students with learning deficiencies in assessments

Abstract

[EN] Find areas and indicators of achievement where students need to reinforce their knowledge is a difficult task for teachers in schools. This article presents a decision-making support system that allows teachers to identify students with poor academic performance. The strategy is a Matrix Based Recommender System to rate assessments and share the results using statistical graphs. To validate this proposal we used focus group and daily meetings methodologies. The proposed strategy was tested in UGEL07-Lima-Perú with 135 schools and 25491 students in evaluation process. The evaluation results show that teachers agree with the proposed strategy, because it allows them to have assessment information everywhere and at every time. The results also highlight that using the tool users can have visual information in real time. Furthermore, the information shared through the application improves decision-making on corrective actions for poor academic performance in evaluated areas.