It all Starts with

If you are going to unify customer data - you need an engine built from the ground up for that purpose.

Our Approach to Data Matching is Like Nothing You’ve Seen Before

We completely reimagined how contact data matching should work, and created a unique matching engine built from the ground up specifically for the challenges of working with customer data. We eliminated the complexity, difficulty, and uncertainty of traditional matching processes, to enable users of all skill levels to quickly build and deploy highly accurate contact data matching models with greater accuracy and in a fraction of the time of conventional fuzzy matching methods.

We did this by building an engine that performs an interconnected three stage process, where the AI automatically analyzes, normalizes and tokenizes data- builds matching models, and intelligently Grades, Scores and Groups Matches. Each stage feeds the next, intelligently applying multiple forms of data matching and analysis to the entire contact record.

Why matchit? Because your matching logic can’t handle this!

matchit is amazingly tolerant to the wide variations and nuances specific to customer data – even on large datasets from disparate sources! Unlike ‘traditional’ applications, matchit doesn’t require data extraction, transformation, standardization, correction or manipulation prior to matching, and it doesn’t even require two different data sources to be normalized into a standard format or a target database! It doesn’t even need the same number of address lines in each record to compare the addresses.

How do we do it?

matchit performs an analysis to better understand the data in each contact record.

The AI looks at patterns in the data, the nature and position of words, classifies word types, creates word associations, and identifies where it is poorly formatted, or has incomplete or uncertain information. It provides a description of the data that informs the engine of the trustworthiness of the record. Each result feeds the engine values that are used to measure the quality of every record.

Later during the match scoring stage when record ‘A’ is compared to record ‘B’ this logic helps matchit understand how the data was input, what the overall quality of that input was, what types of issues were identified, and then… how to grade suspect matching records.

One Engine - Multiple Techniques


Bower and Bauer

Hernández and Hernandes

Muhammad, and Mohamed

Non-Phonetic Similarity

Street & St, Straße & Str.

Auto, Motors and Car

1 = One, First , 1st


Turner Broadcasting Company ~ TBC

LLC = Limited Liability Corporation


Wilson, Wislon & Wilsn

95128 ~ 91528

7350 ~ 07350


Jose Gonzalez

Gonzalez Jose

560 Main St Ste 106

Suite 106 560 Main St


Inc, Incorporation, LLC

Insurance, Assurance

The State Farm Insurance Company of California LLC


Michael = Mike Michel, Mickey, and Mikhael

Jacqueline = Jacklynn, Jaclyn, Jackie

Parsing &Restructuring

|Mr Jose R Gonzalez Jr MMD | =

|Mr | Jose | R | Gonzalez | Jr | MMD |

| AtlantaGA30305 |

| Atlanta | GA | 30305 |

International DataUnicode - Transliteration

أبراج الاتحاد = 'abraj al etihad

ਬਲਰਾਜ = Balarāja
にこらす = Nikkarasu

matchit is designed to be intelligent – applying all forms of data matching to the entire contact record to achieve results that are human-like in perception.

Deploying multiple algorithms, lexicons, and processes, matchit intelligently applies them to ensure that all types of difference are detected. Essentially, taking a multi-dimensional view of the data, never relying on any single item of data being correct or consistent!

Say what? I've got to see this!

The Result

The 360Science Secret Sauce

For most users and decision makers, how 360Science works isn’t as important as how well it works. However, for IT decision makers, we know you’ll want to learn more about the data science behind matchit to understand better why 360Science is one of the most innovative customer data analytics solutions available today.

Get the whitepaper
Matching stack

I’m a DBA/Data Analyst

I’m a Marketer, DBA or Data Analyst and I want to improve my customer data-driven processes.

Let's Get Started

I’m a Developer

I’m a Developer looking to build data quality into our systems, platforms or products.

Learn More

I really don’t know what I need – but I could use some help on a data quality problem.

Help me out

Verticals and use cases where you’ll find 360Science

Financial Services

  • Risk Analysis
  • Credit Decisioning
  • Fraud Detection
  • Mergers & Acquisitions
  • Regulatory Compliance
  • Collections & Recovery
  • Financial Decision-Making

Marketing, Sales & CRM

  • Marketing Automation
  • Lead prioritization
  • Territory Management
  • Response Analysis
  • Segmentation
  • Direct Marketing
  • Buyer Influencer Mapping

Insurance & Healthcare

  • Insurance Risk
  • Eligibility
  • Claims Processing
  • Collections & Recovery
  • Medical Records (EHR)
  • HIPAA Compliance
  • Call Center

Retail / eCommerce

  • Point of Sale (POS)
  • Call Center
  • Loyalty
  • Order Fulfillment
  • Fraud Detection
  • Channel optimization

Data Management

  • Direct Marketing
  • Customer Analytics
  • List Management
  • Data Cleansing
  • Market Intelligence
  • Data Integration
  • Data Warehousing