We propose a novel model, Wide & Deep Item Response Theory (Wide & Deep IRT), to predict thecorrectness of students’ responses to questions using historical clickstream data. This model combinesthe strengths of conventional Item Response Theory (IRT) models and Wide & Deep Learning for RecommenderSystems. By leveraging clickstream data, Wide & Deep IRT provides precise predictions ofanswer correctness while enabling the exploration of behavioral patterns among different ability groups.Our experimental results based on a real-world dataset (EDM Cup 2023) demonstrate that Wide &Deep IRT outperforms conventional IRT models and state-of-the-art knowledge tracing models whilemaintaining the ease of interpretation associated with IRT models. Our model performed very well in theEDM Cup 2023 competition, placing second on the public leaderboard and third on the private leaderboard.Additionally, Wide & Deep IRT identifies distinct behavioral patterns across ability groups. In theEDM Cup 2023 dataset, low-ability students were more likely to directly request an answer to a questionbefore attempting to respond, which can negatively impact their learning outcomes and potentially indicatesattempts to game the system. Lastly, the Wide & Deep IRT model consists of significantly fewerparameters compared to traditional IRT models and deep knowledge tracing models, making it easier todeploy in practice. The source code is available via Open Science Framework https://osf.io/8vcfd/.