PhD
student
Alireza
Heidari
and
Professor
Ihab
Ilyas at
the
Cheriton
School
of
Computer
Science
along
with
international
colleagues have
developed
a
novel
tool
to
manage the
quality
of
your
data.
Called
HoloClean,
this
revolutionary
tool
is
the
first
to
use
artificial
intelligence
to
sift
out
dirty
data
and
correct
errors
before
processing
it.
“More
and
more
machines
are
making
decisions
for
us,
so
all
our
lives
are
touched
by
dirty
data
daily,”
said
Professor 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.”
The HoloClean system, developed by Professor Ilyas and his colleagues from the University of Wisconsin and Stanford University, successfully tackles the problem of insufficient training data by automatically generating bad examples without messing with the information, but enough to train the system to find errors and correct them on its own.
After the AI is trained, it can then figure out independently what’s an error, what’s not, and if there’s an error determine the most probable value for the missing data. Users will then have a cleaner dataset to use in their analytics, which will produce more trustworthy results.
“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 Professor 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.
The paper detailing the error-detection module titled “HoloDetect: Few-shot Learning for Error Detection” is slated to appear in Proceedings of the 2019 ACM SIGMOD conference. It is authored by Professor Ihab Ilyas, Cheriton School of Computer Science PhD candidate, Alireza Heidari and their colleagues — Theodoros Rekatsinas, assistant professor in the Department of Computer Sciences at the University of Wisconsin-Madison and Joshua McGrath, academic researcher at the University of Wisconsin.