Academic performance prediction in a gender-imbalanced environment

Abstract

Individual characteristics and informal social processes are among the factors that contribute to a student's performance in an academic context. Universities can leverage this knowledge to limit drop-out rates and increase performance through interventions targeting at-risk students. Data-driven recommendation systems have been proposed to identify such students for early interventions. However, as we show in this paper, it is possible to identify certain groups of students whose performance is best predicted using indicators that differ from those predictive for the majority. Naïve approaches that do not account for this fact might favor the majority class and lead to disparate mistreatment in the case of minorities. In this paper we investigate the low academic performance predictors of female and male participants of the Copenhagen Networks Study. We find that social indicators (e.g. mean grade point average of peers or fraction of low-performing peers) predict lowperformance of male participants more accurately than they do for female participants, and that this situation is reversed for individual behaviors. Because of the gender imbalance among the participants, optimal gender-oblivious models detect low-performing male students with higher accuracy than low-performing female students. We review the existing approaches to addressing the disparate mistreatment problem and propose our own method that outperforms the alternatives on the dataset in question.

Educational Anomaly Analytics: Features, Methods, and Challenges

“…Gitinabard et al (2019) use network science-related methods to analyze students' social networks and uncover their connection to their academic performance to better support struggling students early in the semester to provide timely intervention. Sapiezynski et al (2017) also add social features to their predictions of course failure. In addition to social attributes such as degree, they also consider the impact of their friends' academic performance.…”

“…In addition to the background features and behaviours mentioned above, psychological characteristics are used to make predictions about course failure frequently (Sapiezynski et al, 2017;Ruiz et al, 2020), because research demonstrate that students' mindsets when studying determines their learning efficiency. Ruiz et al (2020) design experiments to explore the association between students' feedback about the emotions they feel in class and their academic performance.…”

Closed-Form Results for Prior Constraints in Sum-Product Networks

“…We should also note that such properties cannot be imposed at inference time, since even the marginal distribution of Y might have been affected by information regarding the protected attribute, which leaked during training. This situation could arise under a variety of circumstances, such as when training a model using an imbalanced dataset (Sapiezynski and Valentin Kassarnig, 2017;Mehrabi et al, 2019), in which case conditional constraints can be utilized to impede such information leakage from happening.…”

Highly Accurate, But Still Discriminatory

“…In this scenario, an unweighted support vector machine algorithm would lead to a suboptimal hyperplane and separation of the classes (color figure online) (SVM) would overestimate the overrepresented classes and lead to an impaired performance. In contrast to that, imbalances in the representation of the data have been discussed in the context of worse performances of algorithms for certain subgroups of the population (Sapiezynski et al 2017). The representation imbalance is often mistaken for the class imbalance problem, though it is conceptually different.…”