Skip to main content
L
LR_97965861-Visitor
1-Visitor
June 1, 2021
Solved

Does thingworx have MLOps capabilities for champion-challenger experiments?

  • June 1, 2021
  • 2 replies
  • 1038 views

I have to develop a solutions that involve supervision of the model performance over time, and compare the production model against other models with different algorithms or trained with different data.

 

The flow could be analogous to the below image, were the Production Model is the main one, but if any of the other models gets better results, e.g. Challenger 3 then it takes the position as the new champion. 

LR_9796586_1-1622556172730.png

 

 

Best answer by cmorfin

Hi @LR_9796586 

 

There is no such functionality in ThingWorx Analytics.

If the models are stored in ThingWorx Analytics, there is possibly ways to achieve this but that will require you to write services to compare the performance of each models and then use the best one for scoring new data.

 

You can also post a Product Idea to have this type of functionality added in the product in future release.

 

Christophe

2 replies

C
cmorfin19-TanzaniteAnswer
19-Tanzanite
June 2, 2021

Hi @LR_9796586 

 

There is no such functionality in ThingWorx Analytics.

If the models are stored in ThingWorx Analytics, there is possibly ways to achieve this but that will require you to write services to compare the performance of each models and then use the best one for scoring new data.

 

You can also post a Product Idea to have this type of functionality added in the product in future release.

 

Christophe

S
slangleyCommunity Manager
Community Manager
June 3, 2021

Hi @LR_9796586.

 

If you feel your question has been answered, please mark the previous response as the Accepted Solution for the benefit of others with the same question.

 

Regards.

 

--Sharon

Terms & ConditionsCookie settingsAccessibility statement