Educational stakeholders are often particularly interested in sparse, delayed student outcomes, like end-of-year statewide exams. The rare occurrence of such assessments makes it harder to identify students likely to fail such assessments, as well as making it slow for researchers and educators to be able to assess the effectiveness of particular educational tools. Prior work has primarily focused on using logs from students full usage (e.g. year-long) of an educational product to predict outcomes, or considered predictive accuracy using a few minutes to predict outcomes after a short (e.g. 1 hour) session. In contrast, we investigate machine learning predictors using students' logs during their first few hours of usage can provide useful predictive insight into those students' end-of-school year external assessment. We do this on three diverse datasets: from students in Uganda using a literacy game product, and from students in the US using two mathematics intelligent tutoring systems. We consider various measures of the accuracy of the resulting predictors, including its ability to identify students at different parts along the assessment performance distribution. Our findings suggest that short-term log usage data, from 2-5 hours, can be used to provide valuable signal about students' long-term external performance.

Intelligent Tutoring Systems (ITSs) often contain an automated feedback component, which provides a predefined feedback message to students when they detect a predefined error. To such a feedback component, we often resort to template-based approaches. These approaches require significant effort from human experts to detect a limited number of possible student errors and provide corresponding feedback. This limitation is exemplified in open-ended math questions, where there can be a large number of different incorrect errors. In our work, we examine the capabilities of large language models (LLMs) to generate feedback for open-ended math questions, similar to that of an established ITS that uses a template-based approach. We fine-tune both open-source and proprietary LLMs on real student responses and corresponding ITS-provided feedback. We measure the quality of the generated feedback using text similarity metrics. We find that open-source and proprietary models both show promise in replicating the feedback they see during training, but do not generalize well to previously unseen student errors. These results suggest that despite being able to learn the formatting of feedback, LLMs are not able to fully understand mathematical errors made by students.

Intelligent learning technologies (ILT) include a diverse array of computer-based systems and tools designed to foster meaningful student learning. These technologies are intelligent to the extent they implement artificial intelligence principles and techniques to create teachable structure from content, analyze and model inputs from the learner, and generate personalized and adaptive feedback and guidance. Intelligent tutoring systems (ITSs) represent a classic example. ITSs, broadly defined, possess an outer loop that intelligently selects the next relevant task, or content object, for learners to complete based on prior performance, and an inner loop that provides iterative and intelligent feedback as learners work toward completing their tasks. However, intelligent learning technologies encompass more than just intelligent tutors. Increasingly, educational games, automated writing evaluation, virtual pedagogical agents, simulations, virtual worlds, open-ended problem solving, generative concept maps, AI-assisted authoring systems, learning content aggregation programs, and e-textbooks rely on some form of artificial intelligence to enrich the learning experience.