Hiring is a high-stakes decision-making process that balances the joint objectives of being fair and accurately selecting the top candidates. The industry standard method employs subject-matter experts to manually generate hiring algorithms; however, this method is resource intensive and finds sub-optimal solutions. Despite the recognized need for algorithmic hiring solutions to address these limitations, no reported method currently supports optimizing predictive objectives while complying to legal fairness standards. We present the novel application of Evolutionary Many-Objective Optimization (EMOO) methods to create the first fair, interpretable, and legally compliant algorithmic hiring approach. Using a proposed novel application of Dirichlet-based genetic operators for improved search, we compare state-of-the-art EMOO models (NSGA-III, SPEA2-SDE, bi-goal evolution) to expert solutions, verifying our results across three real world datasets across diverse organizational positions. Experimental results demonstrate the proposed EMOO models outperform human experts, consistently generate fairer hiring algorithms, and can provide additional lift when removing constraints required for human analysis.

Modeling student knowledge is critical in adaptive learning environments. Predictive student modeling enables formative assessment of student knowledge and skills, and it drives personalized support to create learning experiences that are both effective and engaging. Traditional approaches to predictive student modeling utilize features extracted from students’ interaction trace data to predict student test performance, aggregating student test performance as a single output label. We reformulate predictive student modeling as a multi-task learning problem, modeling questions from student test data as distinct “tasks.” We demonstrate the effectiveness of this approach by utilizing student data from a series of laboratory-based and classroom-based studies conducted with a game-based learning environment for microbiology education, Crystal Island. Using sequential representations of student gameplay, results show that multi-task stacked LSTMs with residual connections significantly outperform baseline models that do not use the multi-task formulation. Additionally, the accuracy of predictive student models is improved as the number of tasks increases. These findings have significant implications for the design and development of predictive student models in adaptive learning environments.

Recent years have seen a growing interest in block-based programming environments for computer science education. Although block-based programming offers a gentle introduction to coding for novice programmers, introductory computer science still presents significant challenges, so there is a great need for block-based programming environments to provide students with adaptive support. Predictive student modeling holds significant potential for adaptive support in block-based programming environments because it can identify early on when a student is struggling. However, predictive student models often make a number of simplifying assumptions, such as assuming a normal response distribution or homogeneous student characteristics, which can limit the predictive performance of models. These assumptions, when invalid, can significantly reduce the predictive accuracy of student models.