Don’t rely on guesswork. Know who your buyers will be.

As B2B marketers, we all know that having a lead scoring system to identify sales-ready leads or potential buyers is critical to running successful demand generation programs and to maintaining marketing-and-sales alignment. But implementing a lead scoring system that actually works is easier said than done. With Mintigo, you can now have lead scoring models that leverage the power of predictive analytics and big data to help you find your buyers faster. No more guessing.

Leveraging Your CRM

1. We start with what you know by leveraging your CRM and marketing automation data

You probably know some things about your leads: Which campaigns they’ve seen, where they clicked and what they filled on your form. We leverage this valuable data to start building your predictive model.

Your marketing and content efforts may yield a large quantity of leads, but unfortunately, the vast majority of them will not end up as buyers. While marketing automation platforms help you collect more behavioral information than ever, it’s still hard to identify likely buyers. Your marketing and CRM data can deliver valuable insights provided the following major challenges are addressed:

  • Limited number of variables: the average company CRM has only 10 demographic variables, which typically include name, location, industry, revenue and number of employees.
  • Messy data: CRM data comes from multiple sources; making the same data points such as job title (Marketing Director vs. Director of Marketing) and State (California vs. CA) appear in various formats.
  • Incomplete/Inaccurate data: most marketers collect limited information via web forms to reduce drop rates at landing pages. As a result, records have only partial data, which is often inaccurate.
  • Outdated records: marketing databases degrade quickly and up to 30% of leads change jobs or are simply no longer valid after one year.

Mintigo developed sophisticated algorithms for cleansing and completing your data. The result of this process is a highly accurate and standardized database of your records, which then becomes a solid foundation for predictive lead scoring modeling.


  • CRM Data Cleansing: updating or deleting dated and incorrect CRM records. Mintigo identifies bad data such as duplicates, bad emails, bounced emails, bad names, bad titles, bad company names, etc. It then updates your data using its own data and public data on the Web.
  • CRM Data Standardization: classifying and consolidating CRM data into standard formats. Names, company name, addresses and other data elements are standardized.

Adding Marketing Indicators

2. We add what we know by adding thousands of online marketing indicators

Mintigo collects and continuously updates thousands of data points on millions of companies. This information includes public information on financials, staff, hiring, technologies, marketing and sales tactics as well as semantic analysis of the company’s digital footprint. The result – a 360-degree profile of each lead in your database.

Companies and decision-makers leave a digital footprint that can be analyzed to predict their tendency to buy products and services. Mintigo monitors the online behavior of several millions of B2B companies and tens-of-millions of prospects and decision-makers.

Mintigo mines data from the Web and keeps an up-to-date database containing thousands of indicators that can predict buying behavior. Mintigo scans billions of Web pages daily and continuously updates its database from sources such as:

  • Company websites, press releases, news sites and third party websites
  • Job boards
  • Social networks
  • Private and public databases

Mintigo applies the rigor of proven data-science and machine learning to build and maintain thousands of MIs such as Microsoft SQL Server above. When combined with your CRM data, it yields a richer and insightful 360-degree profile of your prospects and customers alike.


  • Rich Marketing Indicators (MIs): mining the Web to identify thousands of indicators including specific indicators that matter to your business.
  • Vast Data Coverage: robust database of indicators that covers millions of companies, including those in your CRM records.
  • Unparalleled Matching: sophisticated multi-stage algorithms that merge CRM and Web data into one robust database.
  • Real-Time CRM Data Enrichment: merging your CRM data with thousands of up-to-date indicators mined from the Web.

Crunching Data

3. We apply predictive analytics by crunching massive data with machine learning to crack your CustomerDNA™

Mintigo takes your data, our own data, and your highest value leads and uses machine learning to find your CustomerDNA™, the set of indicators that make them unique compared to all of the other leads in your database. The result is a set of indicators and a scoring model that can predict the likelihood to convert.

Predictive analytics help you identify likely buyers in your marketing and sales databases. Mintigo leverages your highest value customer-data and crunches a massive amount of data in order to find what makes them unique. We call that CustomerDNA™ — the combination of Marketing Indicators or features that make your buyers unique as compared to all other leads in your database.

The result of a CustomerDNA™ analysis is a set of indicators and a scoring model that can predict the likelihood to convert.


  • Best-In-Class Predictive Modeling: Mintigo’s model was developed by some of the world’s leading Machine Learning experts and applies the cutting-edge new research in data-science.
  • Model Validation: Mintigo’s CustomerDNA™ has been successfully deployed and tested with dozens of clients, showing impressive predictive power.
  • Optimization Across The Funnel: optimizing at any point of the funnel; from marketing campaign engagement to closed and won opportunities and lifetime value
  • Multiple Use Cases: Mintigo’s CustomerDNA™ helped marketers score leads for new markets and high volume freemium products, find up-sell and cross-sell opportunities and helped evaluate database potential after mergers and acquisitions.
  • Scalability: The predictive model scales from thousands to millions of leads, without losing its predictive power.
  • Flexibility: Mintigo’s CustomerDNA™ can handle missing values or partial data and still maintain its predictive power.

Identifying Propensity To Buy

4. We score your accounts and leads database and identify those most likely to buy

Mintigo’s predictive lead scoring leverages your CustomerDNA™ to assess the likelihood of leads in your database to become customers. Mintigo uses your unique predictive scoring model to score your accounts as well as every lead that enters your funnel in your marketing and sales systems such as Oracle Marketing Cloud (Eloqua), Marketo, Adobe Campaign,, Oracle Sales Cloud and MS Dynamics. This has direct impact on your revenue — Now you know which leads to send directly to Sales and which ones to keep nurturing.

Identify the golden nuggets in your marketing database with Predictive Lead Scoring. Mintigo’s comprehensive application combines CRM data, online Marketing Indicators and machine learning to help you find and act on the leads that are most likely to buy and lets you boost sales and close more deals.


  • Understand Score Drivers: Mintigo’s lead scoring is not a black box. As part of your lead scoring model, you will get reports and full visibility to the predictive marketing indicators that are driving your score.
  • Control Over The Predictive Process: Mintigo’s SaaS product allows for unlimited drill-down into model results with full visibility at individual lead level.
  • Marketing Automation Integrations: Mintigo offers a deep integration with workflows in Marketo, Eloqua and Salesforce.
  • Real-Time Scoring: After your predictive model is set-up, Mintigo’s real time lead scoring applications score new leads instantly and effortlessly in your marketing automation platform to allow you to manage your lead funnel dynamically.


Predictive Scoring Resources

View All Predictive Scoring Resources