Feature Manifold Transformer for Detection of Differential Item Functioning: Visual Detection of Categorical Feature Nonconformity through Attention-Based Analysis

Methods for interpreting complex feature interactions in educational assessment data remain a critical challenge, with traditional statistical approaches often creating barriers to accessibility and interpretability. We introduce the Feature Manifold Transformer (FMT), a novel machine learning approach that leverages dimensionality reduction, representation learning, and transformer architectures to visualize and interpret feature relationships in categorical data. Using the Concept Inventory of Natural Selection (CINS) and Concept Assessment of Natural Selection (CANS) datasets as testbeds, we demonstrate the FMT’s ability to capture subtle relationships between student demographics and response patterns. Our methodology enables both global and local pattern analysis, providing interpretable visualizations of complex feature interactions that would be challenging to identify with traditional methods, especially as feature set size increases and interactions become exponentially more complex to model explicitly. The results establish the FMT as an effective exploratory data analysis tool for identifying meaningful subgroup patterns within high-dimensional categorical spaces. While demonstrated through educational assessment data, the approach is generalizable to any domain involving complex categorical feature interactions, making it a versatile tool for pattern detection across diverse fields.