logo
Lead Scoring is an advanced conversion type in SegmentStream that uses machine learning to assign quality scores to your leads based on their characteristics and likelihood to convert. This feature helps you identify high-value prospects and optimize your marketing spend toward leads that are most likely to generate revenue.

Overview

Lead Scoring analyzes your lead data to identify qualified leads that meet your business criteria and estimates their potential deal value. This allows you to:
  • Focus on qualified leads that are most likely to convert
  • Optimize marketing campaigns toward lead quality, not just quantity
  • Improve ROI by focusing budget on channels that generate valuable leads
  • Export qualified leads to advertising platforms for better targeting

Getting Started

To implement Lead Scoring for your business:
  1. Assess Your Data: Review whether you have the required lead and sales data
  1. Choose Integration Method: Determine if you can use a standard CRM integration or need custom data setup
  1. Contact SegmentStream: Reach out to discuss your specific requirements and begin the setup process
Lead Scoring is an enterprise feature that requires collaboration with SegmentStream's data team for proper implementation and optimization.

Data Requirements

To implement Lead Scoring, you need to provide SegmentStream with information about your leads and their outcomes. There are two main approaches depending on your CRM setup:
Option 1: Standard CRM Integration
If you use a well-known CRM system, SegmentStream can automatically connect to your existing data. For example, we support HubSpot with a ready-to-use integration - Connection Guide.
Contact us to get more details about connecting your specific CRM system.
With standard CRM integration, SegmentStream automatically collects lead data and deal outcomes to train the scoring model.
Option 2: Custom Data Integration
If you use a custom CRM or one not in our catalog, you'll need to provide lead and sales data in the following format:
Leads Data Table
Your leads table should contain the following information:
Required Fields:
  • created_at - When the lead was created
  • updated_at - When the lead was last updated
  • lead_id - Unique identifier for each lead
  • google_client_id - Google Analytics Client ID when the lead was created
  • user_id - Internal user identifier that links to sales data
Custom Properties (Recommended): Include as many relevant lead characteristics as possible to improve model accuracy, for example:
  • user_email - Lead's email address
  • first_name - Lead's first name
  • last_name - Lead's last name
  • company_name - Company name
  • company_size - Number of employees
  • industry - Industry sector
  • job_title - Lead's job title
  • seniority_level - Decision-making level (C-Suite, Manager, Individual Contributor)
  • lead_source - How the lead was acquired (Organic Search, Paid Ads, Referral, etc.)
  • country - Geographic location
  • annual_revenue - Company's annual revenue
  • budget - Stated budget for your solution
  • pain_points - Specific challenges mentioned
  • product_interest - Which products/services they're interested in
Example Lead Record:
Column
Value
Required
Comment
created_at
2024-01-15 10:30:00
updated_at
2024-01-15 10:30:00
lead_id
lead_12345
google_client_id
1234567890.1234567890
NULL if not collected
user_id
user_abc123
user_email
first_name
John
last_name
Doe
company_name
Acme Corporation
company_size
250
industry
Technology
job_title
VP of Marketing
seniority_level
C-Suite
lead_source
Google Ads
country
United States
annual_revenue
10000000
Sales/Deals Data Table
Your sales table should track successful conversions from leads:
Required Fields:
  • created_at - When the deal was closed
  • updated_at - When the deal was last updated
  • order_id - Unique identifier for each sale/deal
  • value - Revenue amount of the deal
  • user_id - Links back to the lead data (same user_id)
💡
Important for LTV Prediction: To accurately predict customer lifetime value, include ALL purchases attributed to each user_id in this table, not just the first purchase. This helps the model understand the complete revenue potential of similar leads.
Example Sales Record:
Column
Value
Required
created_at
2024-03-20 14:15:00
updated_at
2024-03-20 14:15:00
order_id
order_67890
value
25000.00
user_id
user_abc123

How Lead Scoring Works

  1. Data Analysis: SegmentStream analyzes your historical lead and sales data to identify patterns
  1. Model Training: Machine learning models learn which lead characteristics predict successful conversions
  1. Qualification: New leads are evaluated and only those meeting quality thresholds become conversions
  1. Value Prediction: The system estimates potential deal value for each qualified lead
  1. Daily Updates: Lead qualification and scoring are updated daily as new data becomes available

What You Get

Qualified Lead Conversions
Only high-quality leads that meet configurable thresholds are created as conversions in SegmentStream. We can work with you to determine the optimal threshold that meets your business needs.
Predicted Deal Values
Estimated revenue potential for each qualified lead, allowing you to focus marketing spend on high-value opportunities.
Exportable Data
Qualified lead conversions can be exported to advertising platforms like Google Ads and Meta Ads for:
  • Enhanced Conversions: Send high-quality conversion signals back to ad platforms
  • Lookalike Audiences: Create audiences based on your qualified leads
  • Bid Optimization: Optimize toward lead value rather than just lead volume
Reporting and Analytics
Use Lead Scoring conversions in SegmentStream reports to:
  • Analyze qualified lead performance by traffic source
  • Compare channel effectiveness based on lead quality and predicted value
  • Optimize marketing attribution for lead generation campaigns

Implementation Process

  1. Data Assessment: SegmentStream's data team evaluates your lead and sales data
  1. Setup: We setup Lead Scoring conversion for you once data is validated
  1. Model Training: Initial machine learning models are trained on your historical data
  1. Testing Phase: Lead scores are generated and validated against known outcomes
  1. Go Live: Daily lead scoring begins with continuous model improvement

Best Practices

Data Collection
  • Capture Google Client ID: Ensure your forms capture the Google Analytics Client ID to link website behavior with lead data
  • Collect Rich Attributes: The more relevant information you collect about leads at the time of lead creation, the more accurate the scoring will be.
    • 💡
      Attributes must be available immediately when the lead is created to ensure they can be used for next-day conversion processing. Attributes added later in your sales process (e.g., after sales calls) may not be available for new lead scoring
  • Maintain Data Quality: Keep lead and sales data clean and up-to-date
  • Historical Data: Provide at least 6 months of historical data for optimal model training

Support

For questions about Lead Scoring implementation or to begin the setup process, please contact your SegmentStream account manager or reach out to our support team.