@shiss  you see in IH too

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

@sundm It depends on the use case. But usually when you present multiple offers and only one gets clicked on, negatives are captured for the rest.

@shiss Assume an inbound situation, if a customer sees 2 offers and clicks on only one, it means the other was not of their interest. So a negative gets captured. Otherwise, how could your model learn a negative behavior.

@shiss There will be a negative response if no positive comes back. But usually, conversion models require a longer time compared to click models just due to the nature of the procedure.

@shiss Data Science academy course could help.

@shiss In 8.5 and especially 8.6 the UI setting can be easily used to set up a conversion model.  Some prior data science discussion can help identify whether a conversion modeling is the appropriate solution, benefits, cons etc. But the technical implementations are made much easier in 8.6.

@shiss Click and conversion models fulfill different goals and capture different behaviors.

@shiss Not sure about that. It could involve different aspects. I would imagine what you are interested in is the strategy run-time which is on the decision node. another aspect  is model node where models are created.

@shiss Usually we have up to several hundred potential predictors. It is always recommended to use predictors of various sources (demographic data, behavioral data, contextual data).  That means, we COULD have up to several hundred but that does not mean we SHOULD have that many, It is better to have a good selection of predictors.

@shiss Some data transformations could be done in the strategy. Type conversion, duration extraction (from date time) and other instance-level transformation could potentially be done on strategy. More complex transformation (Imputing, etc.) should be done outside of the strategy.  Some basic imputing could also be done in strategy too (like simply replacing a NULL value with 0 or things of that nature that do not require very  sophisticated statistical calculations).

@shiss A new generation of adaptive models will be available soon. These models are based on Gradient Boosting algorithms (a type of ensemble methods).  The new algorithm was released in 8.6 but in lab mode. A newer version will be available soon.

@shiss That could potentially duplicate the negative responses.

@shiss IH aggregations are extremely powerful. The idea is simple, prior behavior of customers are potential predictors in defining their future behavior. The OOTB IH aggregation dimensions in Pega ADM models have been decided after rigorous testing.

@shiss Sometimes customers might need to use algorithms that are not supported by Pega. Or they might have access to data that are not provided to Pega engine so they would want to create models offline and bring into Pega.

@shiss Since ADM internally bins the data, it can handle large volumes and reduce dimensionality. However, in use cases where data volume is a lot and customer behavior could potentially change over time, memory settings could be used.

@shiss There is no plan to incorporate this feature in a future release as of now.  Using Sagemaker or GoogleML would be your best option.

@shiss As of 8.5 we have a new feature to capture the data that passes through ADM. This provides an opportunity to explore the data as well as using it to make new models. This data collection will not just be the customer behavior data, it will include any data that was passed through the ADM rule as well as the response label.

@shiss Model context refers to the context in which the model is making a prediction. A context that includes a treatment means that an adaptive model exists for every treatment in the system. A context that includes only action means that a model exists for every action, which is used for all treatments associated with that action.

@shiss The control group that is configured on predictions allows you to calculate lift (for example in CTR) by providing a benchmark performance to compare against. Champion challenger functionality has been used to accomplish the same thing, but now it is much more straightforward to set up in the prediction.

@shiss Response timeout is a mechanism that provides a solution in outbound. The responses are queued for a certain timeframe, and then they are sent back to the models. 

Extend the response timeout window to an appropriate length so that you can capture those later responses. If propensities are low across the board, that’s not completely unusual. Propensities are often very low numbers.

@shiss There is a separate control group per prediction which usually contains one adaptive model rule.

@shiss I don’t think it’s a question of which is better but rather how adaptive models can enhance what they are already doing with their predictive models. There may be good reason to use both.    Additionally, the true value of Naive Bayes in Pega is its capability of learning on the fly. Not every off-the-shelf machine learning algorithm has the capability of turning into an online learner. Also, Naive Bayes in Pega is preceded with a data analysis step that prepares the data for the algorithm including taking care of correlated predictors.