pxDecisionResults Data Set - Detail understanding
Can anyone please explain the details usage, purpose and working methodology of the pxDecisionResults data set.
When I tried to find in PDN, I see some article on delayed learning for adaptive model, and there it has mentioned how to use pxDecisionResults dataset. but why and details of pxDecisionResults datset is missing.
any explanation, or supporting link will be helpful.
Regards
Shankha
EPAM Systems, Inc.
ES
Accenture
IN
still I have below questions...
Q1. When we define Engagement type of a Campaign as RealTime container, I don't see any option to define those 4 modes for a decision strategy. Those 4 options are only coming when we call a strategy from Data Flow. So how to define any of those 4 modes from Campaign when I am defining real time container via Campaign run?
Q2. I was referring to the data flow "DecisionFlow" in the class "DMOrg-DMSample-Int-Decision", I see that "Make the decision and store data for later response capture" mode has been mentioned while calling the strategy "NextBestAction", but no where "pxDecisionResults" DataSet has been referred, does it get used automatically and internally?
Regards
Shankha
Pegasystems Inc.
US
Q1. Campaigns, real-time containers and NBA designer configurations are always automatically configured to use adaptive learning on your behalf and you need not set these data flow settings.
Q2. The decision results dataset is automatically managed for you based on your data flow setting and you need not reference them in any way other than setting the mode.
In the Adaptive model of decision strategy, making decision learn from the real-time customer interactions.
The system learns from customer choices and captures responses, "Next-Best-Action" decision strategy is adaptive in this case.
There are 4 modes for a decision strategy in the adaptive model namely, "Make Decision"(Without storing the customer response), "Make decision and store data for later response capture","Capture response for previous decision by interaction ID"(Considering all the captured responses made in previous decisions for a particular interaction id) and
"Capturing response to the previous decision in the past period"(Considering captured responses made in the previous decision for a particular time period).
In the "Make the decision and store data for later response capture" mode, the inputs used for the prediction/decision are stored in a Cassandra data set. And it's called "pxDecisionResults".
The dataset stores the data into pxdecisionresults using below Keys:
SujectID
pxInteractionID
For additional details please go through the PDN course: IMPLEMENTING ADAPTIVE DECISIONING.
Hope it gives you an idea about "pxDecisionResults". Kindly notify if it does by marking this post as answered/helpful for larger Pega audience.