Editorial
NEW KID ON THE BLOG
Steve Hearn
Distinguishing the usual from the unusual
must admit to finding it mildly
I
amusing when I was asked to
contribute an article for this
section, as after 16 years in retail
loss prevention I could hardly be
described as the “new kid” anywhere.
On reflection, after five years with the
iconic fashion label Jaeger, many of
the things we are currently doing are
“new”, at least to the brand, and
none more new and exciting than our
data mining venture which went live
in July 2008.
New to Jaeger certainly, but new to
me also was the manner in which we
had chosen to implement the system
by deciding to integrate many
differing data sources into the data Jaeger’s granular level that we would need have identified numerous procedural
mining (DM) tool, and the innovative Cardiff to help combat the risk a slightly less issues that have sat below the radar.
way the system will be used. store controlled environment can bring. This tool, aligned with the audit
We all know the relative merits of a In the marketplace we approached team taking custody of the day to
good DM tool so I shall not patronise several vendors and took another day management of the DM
you here, but what has been different “new” decision in selecting data function has already driven
in our journey is the selection of specialists IDM and their data mining significant savings and identified
vendor, in this case a new DM tool Loss Manager. New because profit improvement potential well
company albeit with a management IDM is a new company although the beyond any ROI calculations run at
pedigree and knowledge second to directors will be known to many of conception. It would be remiss of me
none, and the open discussion from you, and new because we were to to mention margin specifics but lets
the start about merging differing and be the first takers of their signature just say improvement is significant
disparate data sets. product. and ROI on the project will literally
From the outset my vision was So what was new about the be measured in weeks not months.
always to stretch the limits of DM approach. Sure, we all know that In my distant past I always
from a data point of view. Jaeger, not EPOS data in its truest form is the remember a police training sergeant
unlike many other medium size mainstay of a DM tool, but we telling me that the secret to good
retailers has not over encumbered its considered merging other data sets policing was “the ability to
staff with unworkable, overbearing to allow a truly business wide view distinguish the usual from the
and time consuming polices, seeking of data and process risk, process unusual”. Sounds simple doesn’t it,
instead to allow staff to concentrate error trend and obviously potential but try doing that amongst the
on the customer and Jaeger offer. fraud signatures. Amongst other many hundreds of thousands of
This clearly presents a greater risk in sources we integrated time and transactions that retailers process
the control environment, but one that attendance data, product design and each day and you soon realise the
must be managed appropriate to the procurement to name but a few. difficultly in delivering such a simple
sales gains to be made. (Shrewd news The bottom line? Well vision. With truly integrated data,
indeed in the current trading climate). immediately we benefited from and a data mining tool such as Loss
We quickly identified therefore that taking data beyond POS and have Manager to interrogate your
any DM tool would not only need to triggered many lines of enquiry. Of transactions and processes, you
be simple and intuitive in its use, but course we have uncovered really can start to see beyond the
would necessarily have to offer the fraudulent activity, who wouldn’t data. Data Mining; distinguishing
freedom of data interrogation at a with such a powerful tool, but we the usual from the unusual. RF
ISSUE 2 SEPTEMBER 2008 • 39
Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44