US 12,112,344 B2
Techniques for preventing shrink based on hybrid machine learning system
Gopi Subramanian, Delray Beach, FL (US); Michael C. Stewart, Delray Beach, FL (US); and Harish Yadav, Boca Raton, FL (US)
Assigned to SENSORMATIC ELECTRONICS, LLC, Boca Raton, FL (US)
Filed by Sensormatic Electronics, LLC, Boca Raton, FL (US)
Filed on Apr. 21, 2021, as Appl. No. 17/236,604.
Prior Publication US 2022/0343349 A1, Oct. 27, 2022
Int. Cl. G06Q 30/0202 (2023.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 30/0202 (2013.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01)] 15 Claims
OG exemplary drawing
 
6. A method for performing data analytics using machine learning comprising:
training a plurality of machine learning algorithms using a training dataset;
extracting data associated with one or more shrink predictions generated by a hybrid machine learning algorithm, wherein a hybrid machine learning model selects and tests a plurality of combinations of learning algorithms from the plurality of machine learning algorithms by feeding outputs of a first machine learning algorithm as inputs to a second machine learning algorithm in a particular order and selecting two or more machine learning algorithms from the plurality of machine learning algorithms and a particular order such that the hybrid machine learning model provides a lower margin of error than the margin of error achieved from any one of the plurality of machine learning algorithms individually;
identifying one or more products that are at an elevated risk for shrink during a forthcoming period of time based in part on the data associated with the one or more shrink predictions provided by the hybrid machine learning algorithm;
generating a shrink control plan that identifies actionable steps to minimize risk for shrinkage for the one or more products identified, wherein the shrink control plan includes actionable steps to implement for securing the one or more products; and
displaying the shrink control plan on a display device.