Frequently Asked Questions
1. What is an Account Fit model?
In Rev.Up ABX, an Account Fit model (or Custom Event model) is a propensity model built using a list of Accounts and success criteria for each account. The success criteria (stored in the Event column) tell whether each account experienced a significant event on its journey with you. Typical success criteria are events when a prospect account becomes a customer.
2. What if my target segment has both prospects and customers in it?
All accounts in the segment will be scored by the Account Fit model, so be careful that you run the right campaigns against your accounts to connect with them based on where they are in their journey with you. For example, if the Account Fit model is created to predict prospect accounts that are likely to become customers, such model should be used to score segments that contain only prospect accounts.
The best practice is to separate prospects and customers into separate segments so that you can meaningfully use the scores from the Account Fit models. Do this by creating separate segments for prospective new business versus relationship growth bases, etc.
3. What if my target segment doesn’t have enough accounts to train a model?
D&B recommends using at least 10,000 accounts when training an Account Fit model. If the training data is clean and has a high match rate, the number of accounts can be slightly smaller.
Sometimes more training data is needed. If you have not already done so, try enhancing your segment accounts with data from your lead database. Rev.Up ABX makes this easier by enabling you to filter out personal email domains if they are in your file but don’t have company information.
If you can’t find enough accounts within your segment, try expanding the definition of the segment in the Query Builder so that the number of accounts is sufficient to build a model.
4. Can I use my transaction data in Rev.Up ABX to create the training file?
When your spending data is available in Rev.Up ABX, you can use "Has Purchased" attributes to create a segment of accounts that have been targeted successfully. You can export this list of accounts to the training file.
5. How does "One record per account" work when I have different Event values for the same account?
The "One record per account" option will choose a record that has a successful event for any given account when at least one such event is available in the training data.
6. How can I use opportunities to create good success criteria?
Pull a list of accounts with Open Opportunities. Include Opportunity Stage in the pull. Now you can experiment to find the stage that will give you a good picture of top versus bottom funnel to build an Account Fit model.
Comments
1 comment
Can this be easily updated so it does not say Lattice and Atlas? I would like to use this as a link for training using the Digital Assistant
Please sign in to leave a comment.