Machine Learning for Supplementing Behavioral Assessment

The Questions About Behavioral Function (QABF) has a high degree of convergent validity, but a gap exists between the results of the assessment and those obtained through experimental functional analysis. Machine learning (ML) can improve the validity of instruments by using data to build a mathematical model for more accurate predictions. We used published QABF and subsequent functional analyses to train ML models to identify the function of behavior. With ML models, predictions can be made from indirect assessment results based on learning from results of past functional analyses. In study one, we compared the results of two classification algorithms to the QABF criteria using a leave-one-out cross-validation approach. Both classifiers outperformed the QABF assessment on multi-label overall accuracy, but false negatives remained an issue. In study two, we augmented the data with 1,000 artificial samples to train and test an artificial neural network. The artificial network outperformed other models on all measures of accuracy. The results indicated that ML could be used to inform conditions that should be present in a functional analysis after more data are collected from the field.