Configuration design problems are common in everyday life as well as engineering, with examples ranging from the selection and arrangement of furniture for a living room to the type of problem-solving used by NASA engineers to return Apollo 13 safely to Earth. There are many theoretical approaches for solving configuration design problems but few studies have examined how humans naturally solve them. This work used data-mining techniques (specifically hidden Markov models) to study the behavioral patterns shown by humans solving two distinct configuration design problems. Mining this data revealed beneficial process heuristics that are potentially generalizable to the entire class of configuration design problems. The trained models indicate that designers proceed through four procedural states, beginning in a state dominated by topology design and progressing to a final state with a focus on parameter design. The mined models also indicate that high-performing designers opportunistically tune parameters early in the process, enabling a more effective and nuanced search for good solutions.