MadKudu’s likelihood to buy (or PQL) models learns from historical patterns to uncover specific behaviors that separate leads who were on the path to conversion from others. MadKudu continuously scores all your active leads based on their behavior (in-app behaviors, marketing & sales interactions…) to determine which are on the verge of closing.
You can now view your likelihood to buy models in the Data Science Studio.
Here's a quick breakdown of how to navigate the different tabs in the Data Science Studio for likelihood to buy models.
Feature evaluation is used to set the weights of the events used in the model. In this page, you can also see which events are performing best in terms of lift to conversion.
To read the "Feature" table:
- Factor Loading: weight of the event
- Decay: the decay of the event in days
- Average for converted: how many times was this event performed by a person that converted (on average)
- Average for non-converted: how many times was this event performed by a person that did not convert (on average)
- Did X: how many people performed this event
- Did not do X: how many people did not perform this event
- Did X conversion rate: CVR of people who did this event
- Did not do X conversion rate: CVR of people who did not do this event
- Lift: Ratio between event specific conversion rate and overall average conversion rate
- Recall conversions: proportion of conversions that did this event
- Recall non conversions: Proportion of non converters that did this event
- Average for converted * factor loading: multiplication of the event weight and the average number of occurrences of this event per conversion
Setting thresholds for the different segments would be done in the Ensembling tab. On this page, you are also able to see the performance of the model on the training dataset.
Validation reflects the performance of the model (similar to charts in Ensembling tab) but on the validation dataset.
Every mapped event will appear in the Signals field pushed to your CRM field. However, there are certain events that may not be helpful to show to your Sales team as they evaluate new MQLs, for example: non-user activities.