CDH Community Event: Adaptive Modeling Lessons from the Field

Pega-as-a-Service
, , , , , , , ,
1

The predictions functionality in Pega Customer Decision Hub makes it easier than ever to drop adaptive models into Next-Best-Action decision logic. Some work is still needed, however, to help clients leverage the best of what CDH has to offer while providing confidence in the results.

In this session, Cheri Gaudet, Lead Consultant, CXForward shares lessons from the field on how to guide customers through an adaptive modeling project. You’ll also learn how you can add value to your project by using OOTB reports.

Watch a replay

https://players.brightcove.net/1519050010001/default_default/index.html?videoId=6283217134001

Note that Q&A from the session have been posted as replies below. Please continue the discussion there!

Find more events like this.

View the presentation slide deck (attached)

Adaptive Modeling Lessons From Field_CDH Community_vFINAL.pdf (912 KB)

2

@shiss Does the Negative Response captured automatically during the Response Timeout is written to the Interaction History as well OR only in Adaptive Model?

3

@shiss From 8.6 onwards, I see starting propensity calculation formula is not available. Are we following a different approach for new proposition where it takes some time to learn?

4

@shiss Is it always required to have a negative outcome recorded when multiple propositions are recommended and only 1 is selected?

5

@shiss How does it change the behaviour when the negative responses are not recorded for the ones that are not selected?

6

@shiss If conversion models’ responses can take a long time, will the model not automatically timeout on response before it is actually received?

7

@shiss Is there an end to end modeling exercise in Pega Academy anywhere? I found bits and pieces, and I am looking for a complete CDH use case

8

@shiss What are the typical configuration requirements for a conversion model?

9

@shiss Is Image Processing supported in Pega? If not, is there a plan to incorporate this feature in the near future?

10

@shiss On the conversion models, have you ever found these to outperform clicks in the long-term?

11

@shiss Are there any performance benchmarks that can give insight on processing speed and throughput of adaptive models on Pega cloud? How do you measure it on Private cloud or On prem servers?

12

@shiss What is the typical number of predictor candidates?

13

@shiss Is it a good idea to apply data transformations (feature engineering) over predictors data before they are fed into the model? In other words, will the ADM automatically handle that data transformation implicitly?

14

@shiss Does Pega support ensemble Machine learning Algorithm like hard voting and Soft voting of multiple Algorithms?

15

@shiss In case even impressions are recorded as negative response and we record a no-click as another negative response, does it not mean it is recording incorrectly ?

16

@shiss How have you found the OOTB IH summaries that get auto-added to the models? I’ve heard these prove to be quite predictive.

17

@shiss How do we make sure we capture negative outcome if delay learning fails to capture the Negative outcome?

18

@sundm Propensity smoothing is now deprecated for ADM-based decisions. Thompson Sampling is used during cold start.

19

@shiss Could you throw some light or use cases of other AI platforms like H2O and other ones leveraged with Pega CDH for clients?

20

@shiss What is the maximum volume of data, Predictive analytics can handle in Numeric Modelinng