You Can’t Predict Retail Shrink. Or Can You?

Does your loss prevention department have a data scientist on the team? Chances are, you don’t, but it’s not a bad idea to start thinking like one.

Addressing retail shrink and loss in 2018 really starts with the consolidation of relevant data from a variety of sources and the use of prediction models to monitor performance and drive down down shrink.

[text_ad use_post=’2384′]

- Sponsors -

In a feature article in the October 2018 issue of LPM Online, Tom Meehan, LPM retail technology editor, reflects on the building of statistical models in a previous retail role and the operational value culled from the data findings. From the article:

Our most reliable predictor of shrink was order pick percentage. This makes sense intuitively—if we are having issues finding items consistently, that usually means that inventory is either misplaced or gone. This metric was also an indicator of poor execution.

Another consistently useful metric was employee‑engagement scores. The theory, which seems to hold up, is that the more engaged the employees are, the more they care about their store and customers, leading to less loss.

Check out the full article, “Can Shrink Be Predicted? Yes, Just Don’t Use the Word ‘Predict,'” to learn more, including the five major categories used for over fifty metrics, and what Meehan found most surprising about the prediction-modeling project.

If you’ve missed any of our previous LPM Online editions, go to the Archives. Be sure to become an LPM digital subscriber, so you are the first to know when new issues are available. If you haven’t already, SUBSCRIBE NOW for free. If you would like a free subscription to our award‑winning print magazine, go to

Stay Updated

Get critical information for loss prevention professionals, security and retail management delivered right to your inbox.