Supporting student success requires collaboration among multiple stakeholders. Researchers have explored machine learning models for academic performance prediction; yet key challenges remain in ensuring these models are interpretable, equitable, and actionable within real-world educational support systems. First, many models prioritize predictive accuracy but overlook human-centered principles, limiting trust among students and reducing their usefulness for educators and institutional decision-makers. Second, most models require at least a month of data before making reliable predictions, delaying opportunities for early intervention. Third, current models primarily rely on sporadically collected, classroom-derived data, missing broader behavioral patterns that could provide more continuous and actionable insights. To address these gaps, we present three modeling approaches-LR, 1D-CNN, and MTL-1D-CNN-to classify students as low or high academic performers. We evaluate them based on explainability , fairness , and generalizability to assess their alignment with key social values. Using behavioral and self-reported data collected within the first week of two Spring terms, we demonstrate that these models can identify at-risk students as early as week one. However, trade-offs across human-centered principles highlight the complexity of designing predictive models that effectively support multi-stakeholder decision-making and intervention strategies. We discuss these trade-offs and their implications for different stakeholders, outlining how predictive models can be integrated into student support systems. Finally, we examine broader socio-technical challenges in deploying these models and propose future directions for advancing human-centered, collaborative academic prediction systems.

The safety and accessibility of our homes is critical to quality of life and evolves as we age, become ill, host guests, or experience life events such as having children. Researchers and health professionals have created assessment instruments such as checklists that enable homeowners and trained experts to identify and mitigate safety and access issues. With advances in computer vision, augmented reality (AR), and mobile sensors, new approaches are now possible. We introduce RASSAR, a mobile AR application for semi-automatically identifying, localizing, and visualizing indoor accessibility and safety issues such as an inaccessible table height or unsafe loose rugs using LiDAR and real-time computer vision. We present findings from three studies: a formative study with 18 participants across five stakeholder groups to inform the design of RASSAR, a technical performance evaluation across ten homes demonstrating state-of-the-art performance, and a user study with six stakeholders. We close with a discussion of future AI-based indoor accessibility assessment tools, RASSAR’s extensibility, and key application scenarios.

In this demo paper, we introduce RASSAR, a mobile AR application for semi-automatically identifying, localizing, and visualizing indoor accessibility and safety issues using LiDAR and real-time computer vision. Our prototype supports four classes of detection problems: inaccessible object dimensions (e.g., table height), inaccessible object positions (e.g., a light switch out of reach), the presence of unsafe items (e.g., scissors), and the lack of proper assistive devices (e.g., grab bars). RASSAR’s design was informed by a formative interview study with 18 participants from five key stakeholder groups, including wheelchair users, blind and low vision participants, families with young children, and caregivers. Our envisioned use cases include vacation rental hosts, new caregivers, or people with disabilities themselves documenting issues in their homes or rental spaces and planning renovations. We present key findings from our formative interviews, the design of RASSAR, and results from an initial performance evaluation.

Recent research has demonstrated the capability of behavior signals captured by smartphones and wearables for longitudinal behavior modeling. However, there is a lack of a comprehensive public dataset that serves as an open testbed for fair comparison among algorithms. Moreover, prior studies mainly evaluate algorithms using data from a single population within a short period, without measuring the cross-dataset generalizability of these algorithms. We present the first multi-year passive sensing datasets, containing over 700 user-years and 497 unique users’ data collected from mobile and wearable sensors, together with a wide range of well-being metrics. Our datasets can support multiple cross-dataset evaluations of behavior modeling algorithms’ generalizability across different users and years. As a starting point, we provide the benchmark results of 18 algorithms on the task of depression detection. Our results indicate that both prior depression detection algorithms and domain generalization techniques show potential but need further research to achieve adequate cross-dataset generalizability. We envision our multi-year datasets can support the ML community in developing generalizable longitudinal behavior modeling algorithms.