As a Marketing Ops leader, there are many business questions we need to tackle every day. With MadKudu, we help make answering those questions easier.

Story

One of the business questions that we've seen many customers have is:

"How do I boost a personal email tied to a qualified account to at least a good score?"

The trigger for this is that leads with personal emails that are tied to a good account are not shown as qualified to Sales. These personal emails typically come from ads (Facebook, LinkedIn, etc) where prospects would enter their email addresses that are non-corporate. Likely personal emails are not a population of leads that convert well and this is the reason why the model scores them low. 

The objective is to boost a personal email tied to a qualified account to at least a good score to make sure these good leads are sent to Sales. 

How to do this via the MadKudu platform?

Pre-requisites

• You have the permissions of the Architect role
• You know what an Attribute is 
• You know what a Computation is
• You know what an Override is

Option 1: The account enrichment is available in fields on the Lead record or the Account it is attached too

[Available for Salesforce, HubSpot and Segment]

We can use enrichment sitting on your Lead or Account record to score the personal leads and contacts. 

• For example, if the Lead record john@gmail.com is enriched by a 3rd party filling the fields such as Title, Industry, Country, NumberOfEmployee, or other custom fields, then you can boost john@gmail.com's score with an override based on this SFDC enrichment. 
• For example, if john@gmail.com is explicitly attached to the account ibm.com which is flagged as a target account in an SFDC field, or your SFDC enrichment says Industry = Internet Software & Service, NumberOfEmployee = 20,000, then we can boost john@gmail.com's score with an override based on your SFDC enrichment. 

Here are the steps to accomplish this:

Step 1: Pull relevant fields

1. Pull from your Salesforce into MadKudu relevant Lead, Contact and Account fields that could be used to separate good from bad personal emails even when tied to known accounts (company size, industry….) following these instructions.
2. Wait for the confirmation email. 

Step 2: Map the fields in the Attribute mapping

1. In your MadKudu app account, map the Salesforce fields containing the relevant enrichment points in the Attribute mapping to make them available in the Data Science Studio so you can create an override
2. Wait for a confirmation email.  

Step 3: Create a computation for each of the fields

1. Navigate to the Data Science Studio.
2. Duplicate the Customer Fit model with the labels: "Live as Standard" and "batch".
3. Go to the Customer Profile > Computations to create a Computation
   1. Type: String
   2. Name: field_lead_salesforce 
   3. Configuration mode: OneToOne
   4. Field: select the attribute you created in step 1
      

Tip: If you have an field Industry on both the Lead, Contact and the Account, use the Configuration mode "Advanced mode" and write COALESCE (attribute1,attribute2, attribute3...)
Example:  COALESCE (salesforce_lead_industry, salesforce_contact_industry, salesforce_account_industry) which means "get the value of the industry first in the Lead record, otherwise in the Contact record, otherwise the Account record it is attached too" -> the order is important. 

1. Repeat the same for each field you'll want to use in the override 
2. Once created, Click on "Release & Recompute"

The training and validation datasets will be enriched with this new computation to append the Account fit score to each lead in the training and validation datasets

Step 4: Create the Override on personal emails

In the Data Science Studio, in the model you duplicated, add the Override.

The override should boost personal email based on the same traits as your ICP. 

Example

1. 1. • IF is_personal  IS 1 
      • AND country_salesforce IS ANY OF United States, Canada
      • AND industry_salesforce IS Internet Software & Services
      • THEN should at least be good

You could also add additional AND conditions based on the person's title for example to restrict the boosting of personal emails only to leads from qualified accounts and with a good title. 

Alternatively, you can leave this override like this and create a second one like 

• IF is_personal  IS 1 
• AND country_salesforce IS ANY OF United States, Canada
• AND industry_salesforce IS Internet Software & Services
• AND title_salesforce contains data
• THEN should be very good

Tip: Instead of using the computation salesforce_industry, create another computation named target_industry_salesforceor target_title_salesforce to list all the good industries and titles you would like to use in the overrides, and signals to avoid reusing the same logic several times

Step 5: Check the performance of the model 

Before deploying your changes you'd like to make sure the override does not boost too many leads otherwise you may flood your marketing and sales teams with too many new leads. Check the performance of the model in the Validation tab to make sure the performance still looks good. 

Open in a separate tab of your browser the model live you duplicated the model from and compare side by side whether the performance has greatly decreased in terms of conversion rates for each segment (refer to the second section in the screenshot).

Step 6: Update signals

So far your Sales team has been seeing in the Customer Fit signals in Salesforce a negative signal
x Lead is using a personal email

and no other information. 

1. Go to the Signals tab and add Signals based on the computations you've used in the Override

Step 7: Review 

Before deploying any change to production, review a sample of leads in the Spot check tab, see if you can find personal emails boosted and with the new signals. 

Step 8: Deploy the model and announce it to the Sales team

Now that the override has been added to the model, you will need to push this update to your model in production to update the scores in Salesforce. 

Keep these considerations in mind when deploying overrides:

1. All your Leads, Contacts, or Accounts that are usually scored by MadKudu will get rescored with the next batch scoring within the next 4-12 hours (see when the next Analysis then Sync process should run in the Processes Page).
2. Adding, editing, or deleting overrides that increase or decrease prospect scores may trigger automated workflows in your CRM which are based on the customer fit or lead grade score (like your MQL workflow). 
3. Don't forget to give a heads-up to your Marketing and Sales team about the override you added and why they'll see personal emails now scores good or very good.

When you are ready, go to the Deploy tab 

• If the live model you are editing is flagged "Live as Standard", then go into the first sub-tab "deploy as standard" and click Primary deploy
• If the live model you are editing is flagged "Live as Multi-fit" please submit a support ticket to our support team, and we'll help you with that. 

Well done!

Option 2: you have an Account Fit model scoring your Salesforce Accounts 

[Only available in Salesforce on plans including the Account Fit]

We can use the Account Fit score sitting on your accounts to score the personal leads and contacts explicitly attached to the accounts through an account ID. 

• For example, john@gmail.com is explicitly attached to the account ibm.com which is scored very good, then we can boost john@gmail.com's score with an override based on ibm.com account score. 

Here are the steps to accomplish this

Step 1: Map the Account Customer Fit segment field in the Attribute mapping

1. In your MadKudu app account, map the mk_customer_fit_segment__c Salesforce field in the Attribute mapping to make the Account score available in the Data Science Studio so you can create an override.
   
   • Object: Account 
   • Field: mk_customer_fit_segment__c
   • Attribute name: salesforce_account_mk_customer_fit_segment
2. Wait for a confirmation email.  

Step 2: Create a computation with the Account Customer Fit segment

1. Navigate to the Data Science Studio.
2. Duplicate the Customer Fit model with the labels: "Live as Standard" and "batch".
3. Go to the Customer Profile > Computations to create a Computation
   • Type: String
   • Name: customer_fit_segment_account_salesforce 
   • Configuration mode: OneToOne
   • Field: select the attribute you created in step 1
4. Once created, Click on "Release & Recompute"

The training and validation datasets will be enriched with this new computation to append the Account fit score to each lead in the training and validation datasets

Step 3: Create the Override on personal emails

In the Data Science Studio, in the model you duplicated, add the Override.

Conditions: 

1. 1. • IF is_personal  IS 1 
      • AND customer_fit_segment_account_salesforce IS ANY OF very good, good 
      • THEN should at least be good

You could also add additional AND conditions based on the person's title for example to restrict the boosting of personal emails only to leads from qualified accounts and with a good title. 

Alternatively, you can leave this override like this and create a second one like 

• IF is_personal  IS 1 
• AND customer_fit_segment_account_salesforce IS ANY OF very good, good
• AND title_lead_salesforce IS ANY OF ... 
• THEN should be very good

Then follow Step 5 to Step 8 described above. Well done!