How to analyze a behavioral model



Hello, in this video we will be looking at how to analyze a Behavioral model. To view the model you need to login to your infer portal and select the models tab on the left hand menu.


Here you will see a list of all the models that are deployed for you and some details showing what they are. This includes the type of entity that the model is scoring, whether they are fit or behavioral models and when they were created. For this video, we will be looking at the Behavior Lead to Opportunity model, so click on the name in the list and it will open the model view.


The screen now changes to show an overview of the model, with a description of the model itself and the details of how the model has been set up. Below this there are three different graphics showing the conversion rates for various points, such as the main activity types, the frequency, which is the number of activities carried out and the number of different activity types carried out by each lead.


There are also other tabs across the top of the model view page, let's take a look at the first one called key signals. This tab gives you a table showing the main signals used by the model and information on these signals. The table shows the category of the signal, or where it has come from; the count of the signal which is how many leads contain that signal; the number of converted entities that have that signal; the converted rate, which is the percentage of times that a lead with that signal present has converted. The lift is the conversion rate of that signal compared to the average conversion rate. Finally we have the coverage and converted coverage columns, which show the percentage of overall and converted leads that contain the signal. You can also view these signals on a graph rather than a table by clicking the tab at the top right of the list, and if needed, you can download a list of the signals as a CSV file.


The next tab is Activity Signals and this goes into more detail of the main signals used by the model. You can see the tabs across the top of the table with the main signal category and when you go into these you will see a more comprehensive list of each item that goes into the signals. Again we have the count of leads which have carried out that activity, whether that be for example to click on a specific link or fill out a particular form, along with the number of converted leads for that activity, the multiplier value and the conversion and coverage percentages.


Next we have the scoring matrix. On this tab you can see how fit and behavioral models interact together if you have both available, and how likely to convert each entity is. You can compare the groups on conversion multiplier, conversion rate or coverage. Looking at the table showing the conversion multipliers you can see that a lead with a behavioral score of 1 and a Fit score in group A is 12x more likely to convert.


The final tab on the page is score explanations. Using this tab you can upload an email address or Salesforce ID for a lead along with a particular date and click on look up to see the score and the activities carried out by that lead. This means that if you have a specific lead that you wish to find out more about and see how likely they are to convert or if you want to pursue them further you can see what activities they have been carrying out and tailor your communications accordingly.


I hope you found this video on behavioral models useful, please take a look at our other videos and articles for more information.