US 11,915,106 B2
Machine learning for determining suitability of application migration from local to remote providers
Pritpal S. Arora, Bangalore (IN); and Klaus Koenig, Essenheim (DE)
Assigned to KYNDRYL, INC., New York, NY (US)
Filed by Kyndryl, Inc, New York, NY (US)
Filed on Jul. 9, 2020, as Appl. No. 16/924,441.
Prior Publication US 2022/0012627 A1, Jan. 13, 2022
Int. Cl. G06F 9/46 (2006.01); G06N 20/00 (2019.01); G06F 9/48 (2006.01); G06F 8/76 (2018.01); G06F 8/77 (2018.01)
CPC G06N 20/00 (2019.01) [G06F 9/4856 (2013.01); G06F 8/76 (2013.01); G06F 8/77 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer implemented method for migrating applications comprising:
normalizing historical key performance indicators to provide a normalized scale of non-successful to successful migration of applications based on historical values;
transforming the normalized scale into a migration model;
entering input key performance indicators for a target application migration into the migration model to provide an output for a probability of successful migration;
executing a simulation employing the migration model, wherein migration modifying key performance indicators are input into the migration model for the simulation; and
modifying the application for successful migration with key performance indicators that increase the probability of success of migration in the simulation to be greater than the output for the probability of successful migration from the migration model.