A revolutionary new tool is sifting out bad data to correct errors before they get processed.
Ihab Ilyas, a professor at Waterloo’s David R. Cheriton School of Computer Science and his colleagues from the University of Wisconsin and Stanford University developed HoloClean to improve data sets.
“More and more machines are making decisions for us, so all our lives are touched by dirty data daily,” said Ilyas. “If organizations like banks or utility companies are working with bad data, it could negatively impact things such as credit scores or mortgage approvals.”
HoloClean generates bad examples of data so that the system can be trained to find these types of errors and correct them on its own. After the artificial intelligence is trained, errors will be identified and the system will determine what the most probable value for the missing data would be. This results in a cleaner, more trustworthy data set that a user can use in their analytics.
“This work deviates from the old way of manually trying to clean the data which was expensive, didn’t scale, and does not meet the current needs for cleaning the data,” said Ilyas. “This system addresses the problem where the information is out there, and people are using it to run analytics, but it is not correct. It doesn’t provide information that was not there, but instead corrects information you assume is correct.”
The next step for the researchers is to pair error detection and data repair in one end-to-end solution for the ultimate data quality dashboard.