Impact of Adaptive Model Predictor type change for an existing model
We are planning to change the Predictor type from "Numeric" to "Symbolic" for an working Adaptive Model in Production post analysis of Predictor performance. We want to get the impact of changing the PredictorType in the behavior report. What would happen to the response collected for that predictor earlier? We believe by changing the PredictorType, previous response collected will be lost. Is there any way to retain the previous response collected for the predictor?
Changing predictor type effectively means removing and adding a predictor. There is no way to retain previous responses - because Pega does not keep a record of all individual response data but instead only keeps binned aggregates.
Usually removing/changing a single predictor has little impact as models learn quickly given the response rates in typical applications. Also the impact of a single predictor is usually limited because there is often a large set of predictors, many of which show some correlations.
If you just want to study the impact of a different predictor type (or setting) you could also consider introducing a different adaptive model rule and plug that in into your strategy just before the current one - so it piggybacks on learning but its propensities are not used.