Domain Expertise vs. Machine Learning: The Debate Continues

“The startup’s three co-founders have backgrounds in engineering and data science, but not weather, and there are no meteorological models involved. By keeping weather predictions within a two-hour window, they believe statistics are sufficient.”–Mashable in “Can Statistics Predict Weather Without Meteorologists? This App Thinks So” on Ourcast, a  new app that uses real-time radar data and crowdsourcing to predict how weather at a given location will change within the next two hours. 

For a (short, recent) history of the debate, see Mike Driscoll’s summary of the deliberations of the panel arguing for and against machine learning and domain expertise at the recent Strata conference (video here), the results of a KDnuggets poll, and Mike Loukides’ passionate defense of expertise, concluding that “the real value of a subject matter expert: not just asking the right questions, but understanding the results and finding the story that the data wants to tell. Results are good, but we can’t forget that data is ultimately about insight, and insight is inextricably tied to the stories we build from the data.”