By David Speights, The Retail Equation
Businesses, including retailers, are losing 5% of revenues to fraud every year, according to the Association of Certified Fraud Examiners (ACFE) 2014 Global Fraud Study. Many are taking action to combat fraud by employing new technologies to monitor high-risk retail transactions using big data tools, real-world and proven statistical modeling, and predictive analytics. This is helping reshape retail loss prevention operations to deliver a better customer shopping experience, while protecting company bottom lines.
Advertisement
Technology Enhances The Collection And Monitoring Of Data
Retailers collect data from many sources, including store sales transactions, store video, traffic counters, alarms, merchandise movement, loyalty programs, ecommerce click paths and more. Additionally, they store 30 to 60 GB of video per store, per day. For a 1,000-store retailer, this could total 22 Petabytes per year (the equivalent of 23,068,672 Gigabytes).
Conventional systems uncover direct relationships that occurred in the past. But big data analytical tools take analysis to a new level by detecting the connections among seemingly unrelated identifiers to reveal underlying larger groups of transactions and individuals in real time. Many companies have approached the data size or analytics problems by investing in bigger, faster hardware, but isolate the work to a small number of machines. However, the massive amounts of data building up and the complex analytical methods required to unearth the information is more resource-intensive than most companies are willing to devote to the loss prevention function.
Big Data-oriented companies achieve high-processing speeds by using special tools to split data into thousands of chunks and distribute the load across a very large number of machines. A query that may take five hours to process on a conventional single-server system takes only minutes on a Hadoop or IBM PureData (Netezza) parallel processing architecture. In the field, a return authorization completes in milliseconds.
Knowing Precisely What To Look For
Predictive algorithms and machine learning techniques rely on big data tools to quickly improve the shopping experience and reduce return fraud and shrink simultaneously. Companies can process the data from all the transactions in the chain and identify suspicious behavior indicative of any form of return fraud/abuse including renting/wardrobing, returning stolen merchandise, receipt fraud, price arbitrage, price switching, double dipping, ORC, check fraud and tender fraud. When someone attempts to make a return, systems perform calculations, and in a fraction of a second, predict the likelihood of whether the return is fraudulent.
While most consumers (about 99%) are approved, those whose actions are highly suspicious are warned or denied. Most importantly, the system allows and supports generous return policies so profitable consumers enjoy a fast and pleasant return process, including those who make many, many returns. In fact, the most valuable consumers tend to have a very high number of returns, which is why it is best to not rely on simple return-velocity calculations.
The amount of return-related fraud is a staggering $9 billion to $16 billion dollar problem, according to the 2013 Consumer Returns In The Retail Industry report released in January 2014 by the NRF and The Retail Equation. Many of these losses are preventable using the technology available today. Fraudsters depend on system delays and lapses in judgment by the cashiers and associates on the front lines. However, when big data analytics replace subjective decisions, fraud and shrink diminish by an average of 8.2% and shrink by 12.9%. A $2 billion retailer would see about $15 million in savings per year, and retailers see a steep decline in return rates beginning immediately after the system is live.
Dr. David Speights is the Chief Data Scientist for The Retail Equation. He has 20 years of experience developing and deploying analytical solutions for some of the world’s largest companies. Throughout his career, he has managed massive amounts of data using big data tools. Currently, he is responsible for analytical modeling and managing POS data from more than 25 national retailers (equating to more than 100 million rows of new data daily). He has been with The Retail Equation since 2000. Prior to joining the company, Speights was first vice president of Mortgage Credit Risk Modeling at Washington Mutual and chief statistician at HNC Software. He is often asked to consult on projects within a number of industries. Speights holds a Ph.D. in Biostatistics from the University of California, Los Angeles and has several patents.
