Community Tip - If community subscription notifications are filling up your inbox you can set up a daily digest and get all your notifications in a single email. X
I was trying out the example on Prescriptive analytics in thingworx. However, i am not familiar with the meaning of the result as shown. What is the meaning of originalScore and optimisedScore and why is it the same in this case.
How does this information translate into the results of prescriptive analytics which is to offer solution to the problems identified by predictive analytics.
Solved! Go to Solution.
HI @hujingrui
Prescriptive scoring attempt to modify some selected features from the dataset in order to optimize the goal.
Those selected features, called lever, are provided by the user when sending the scoring job.
So you do need to make sure you have provided some relevant lever - I can't tell from the screenshot if you filled in something or not. If no levers are provided no optimization can be done.
Then depending on the levers it is possible that the optimized score is the default score, because there is no better result while changing the lever values.
It can be useful to read this page in the Help Center too: https://support.ptc.com/help/thingworx_hc/thingworx_analytics_8/#page/thingworx_analytics_8%2Ftwxa-thingoptimizer.html
Hope this helps
Kind regards
Christophe
HI @hujingrui
Prescriptive scoring attempt to modify some selected features from the dataset in order to optimize the goal.
Those selected features, called lever, are provided by the user when sending the scoring job.
So you do need to make sure you have provided some relevant lever - I can't tell from the screenshot if you filled in something or not. If no levers are provided no optimization can be done.
Then depending on the levers it is possible that the optimized score is the default score, because there is no better result while changing the lever values.
It can be useful to read this page in the Help Center too: https://support.ptc.com/help/thingworx_hc/thingworx_analytics_8/#page/thingworx_analytics_8%2Ftwxa-thingoptimizer.html
Hope this helps
Kind regards
Christophe