BanditCAT and AutoIRT: Machine Learning Approaches to Computerized Adaptive Testing and Item Calibration
This work addresses the need for efficient test development and administration in educational or assessment settings, though it appears incremental as it builds on existing AutoML and IRT methods.
The paper tackles the problem of quickly calibrating and administering large-scale computerized adaptive tests with limited data, resulting in a framework that uses AutoIRT for item calibration and BanditCAT for adaptive administration, with initial deployment on a practice test showing reliability and exposure metrics.
In this paper, we present a complete framework for quickly calibrating and administering a robust large-scale computerized adaptive test (CAT) with a small number of responses. Calibration - learning item parameters in a test - is done using AutoIRT, a new method that uses automated machine learning (AutoML) in combination with item response theory (IRT), originally proposed in [Sharpnack et al., 2024]. AutoIRT trains a non-parametric AutoML grading model using item features, followed by an item-specific parametric model, which results in an explanatory IRT model. In our work, we use tabular AutoML tools (AutoGluon.tabular, [Erickson et al., 2020]) along with BERT embeddings and linguistically motivated NLP features. In this framework, we use Bayesian updating to obtain test taker ability posterior distributions for administration and scoring. For administration of our adaptive test, we propose the BanditCAT framework, a methodology motivated by casting the problem in the contextual bandit framework and utilizing item response theory (IRT). The key insight lies in defining the bandit reward as the Fisher information for the selected item, given the latent test taker ability from IRT assumptions. We use Thompson sampling to balance between exploring items with different psychometric characteristics and selecting highly discriminative items that give more precise information about ability. To control item exposure, we inject noise through an additional randomization step before computing the Fisher information. This framework was used to initially launch two new item types on the DET practice test using limited training data. We outline some reliability and exposure metrics for the 5 practice test experiments that utilized this framework.