Identifying bias when sensitive attribute data is unavailable: Exploring Data from the HMDA

To test their automated systems for possible bias across racial or gender lines, organizations may seek to know which individuals belong to each race and gender group. However, such information may not be easily accessible, and organizations may use techniques to infer such information in the absence of available data [1]. Here, we explore a … Continue reading “Identifying bias when sensitive attribute data is unavailable: Exploring Data from the HMDA”