Adaptive Model
Adaptive models are scoring models in Pega Platform that can capture and analyze customer
responses in real time.
To capture the responses and to monitor the model's Adaptive decision manager will take care of
everything.
Implementation:
For capturing interaction history CDH->Content->Real time Artifacts-> Container
Open our container and change impression capture radio option as Capture on Retrieval.
After we changed this when ever we launch the portal will get the outcome as impression..
But we need outcomes as accepted / rejected based on the customer behaviour right...
So for that we need to take OOTB Service Rest CaptureResponse and we need to create Connect-
REST in another application(i.e., banking application)
We need to save as the CaptureResponse service rest and also activity of that service rest.
Before creating connect rest we need to create class structure..
Make sure that create properties with the same names..
After creating class structure create Connect-REST manually..
In the offers displaying section add two buttons accept offer and reject offer.
For accept offer button give the parameter response value as Accepted and for reject offer button
give the parameter response value as Rejected
Capture Response Activity:
Now if we accept the offer / reject the offer the response will be stored in Interaction History..
Creation of Adaptive Model:
Prediction studio-> models-> new-> adaptive model
Click create
Add the predictors which you required in predictors tab.
In settings tab update the model responses to 1 response so that model will update for every one
response.
To use all received responses for each update cycle, click Use all
responses.
To assign more weight to recent responses when updating a model, click
Use subset of responses.
In the Monitor performance for the last field, enter the number of weighted responses used to
calculate the model performance that is used in monitoring.
The default setting is 0, which means that all historical data is to be used in performance monitoring.
In the Data analysis binning section, in the Grouping granularity field, enter a value between 0 and 1
that determines the granularity of the predictor binning.
The higher the value, the more bins are created. The value represents a statistical threshold that
indicates when predictor bins with similar behaviour are merged. The default setting is 0.25.
In the Grouping minimum cases field, enter a value between 0 and 1 that determines the minimum
percentage of cases per interval.
Higher values result in decreasing the number of groups, which can be used to increase the
robustness of the model. Lower values result in increasing the number of groups, which can be used
to increase the performance of the model. The default setting is 0.05.
In the Predictor selection section, in the Activate predictors with a performance above field, enter a
value between 0 and 1 that determines the threshold for excluding poorly performing predictors.
The value is measured as the Area Under the Curve (AUC) of the predictor as compared to the
outcome. A higher value results in fewer predictors in the final model. The minimum performance of
AUC is 0.5, therefore the value of the performance threshold should always be set to at least 0.5.
The default setting is 0.52.
In the Group predictors with a correlation above field, enter a value between 0 and 1 that
determines the threshold for excluding correlated predictors.
The default setting is 0.8. Predictors that have a mutual correlation above this threshold are
considered similar, and only the best of those predictors are used for adaptive learning. The
measure is the correlation between the probabilities of positive behaviour of pairs of predictors.
Now in the Capture response service rest we have an activity
Open that activity and add the step
In that step call the pxAdaptiveAnalytics dataset.
To capture the responses of model we need to call the model in strategy.
Before calling the model, we need to set the issue, group, action, direction and channel by using set
property.
After the set property add the adaptive model.
Offer acceptance value will be stored in model positives property.
So we are prioritizing the offers based on ModelPositives.
When we accept the offer or rejects the offer that response will be stored in model.
We can see the responses in monitor tab of Adaptive model.
We have a data set pxDecisionResults , in this data set we can see the results i.e., whether the data
is coming or not we can check in this dataset.
Run this dataset.
