Interpretability

Data collection, of course, has to comply with specific constraints that guarantee the causal interpretability of that data.

MIT researchers are striving to improve the interpretability of features so decision makers will be more comfortable using the outputs of machine-learning models.

“There’s this whole area of explainability, interpretability, where people want to understand how stuff works,” said Church. “With the older methods, you can actually get an answer to what’s going on. The latest, greatest stuff is kind of like magic. It works a lot better than the older stuff. But when it goes, it’s really bad.”