{"id":1,"date":"2019-01-17T19:59:32","date_gmt":"2019-01-17T19:59:32","guid":{"rendered":"http:\/\/groups.cs.umass.edu\/equate\/?p=1"},"modified":"2019-04-03T17:03:50","modified_gmt":"2019-04-03T17:03:50","slug":"explainability","status":"publish","type":"post","link":"https:\/\/groups.cs.umass.edu\/equate\/research\/explainability","title":{"rendered":"Explainability in Data Analysis"},"content":{"rendered":"

Explanations are an integral part of human behavior: people provide\u00a0<\/span>explanations to justify choices and actions, and seek explanations to\u00a0<\/span>understand the world around them. The need for explanations extends to\u00a0<\/span>technology, as crucial activities and important societal functions\u00a0<\/span>increasingly rely on automation. Yet, today’s data is vast and often\u00a0<\/span>unreliable and the systems that process data are increasingly complex. As a\u00a0<\/span>result, data and the algorithms that process data are often poorly understood,\u00a0<\/span>potentially leading to spurious analyses and insights. Many users even shy\u00a0<\/span>away from powerful analysis tools whose processes are too complex for a human\u00a0<\/span>to comprehend and digest, instead opting for less sophisticated yet\u00a0<\/span>interpretable alternatives. The goal of our research is to promote users’\u00a0<\/span>trust in data and systems through the development of data analysis toolsets\u00a0<\/span>where explainability and interpretability are explicit goals and priorities of\u00a0<\/span>the systems’ function.<\/span><\/p>\n

Publications<\/h4>\n