In conventional product development, humans use the data output from one experiment to inform the design of subsequent experiments. This becomes increasingly ineffective as the amount of data output rises exponentially through accelerated development, and human pattern recognition is ill-suited to highly multi-dimensional decision making. Using machine learning techniques such as Bayesian Optimization to learn complex trends (that would not be obvious to human researchers) in high-order data output space helps to guide future experiments and achieve design objectives effciently.