Documentation Index
Fetch the complete documentation index at: https://www.cashfree.com/docs/llms.txt
Use this file to discover all available pages before exploring further.
Cashfree’s Name Match is an AI-powered name comparison API designed specifically for India’s complex naming conventions. It helps businesses instantly verify if two names refer to the same person by returning the following:
- Name match score:
0 to 1
- Name match category:
Direct Match, Partial Match, or No Match
Set custom risk thresholds and automate decisions for KYC, payouts, fraud prevention, and other processes. In India, traditional string-matching algorithms often return inaccurate results because of initials, variations in name order, local spellings, and missing components. These issues can lead to rejection rates of up to 18% and increased operational effort. Name Match is designed to handle these scenarios.
Key factors behind the Name Match reliability
- Handles initials, middle names, and abbreviations.
- Understands phonetic and regional spelling variants.
- Recognises missing or extra spaces.
- Supports subset matching such as Harsh Kishore vs HKishore.
- Detects salutation-based name patterns such as Aditya Roy S/O Jatin.
- Considers sequence, gender, and regional norms as it is context aware.
Key benefits
The following points highlight the key capabilities of Cashfree’s Name Match feature:
-
Built for Indian names:Trained on over 100 million Indian name records, the model understands initials, salutation formats, and regional variations.
-
Accurate and explainable: Returns both a match score and a category, enabling you to build rule-based logic around onboarding or rejection.
-
Higher conversion, lower friction: Reduce false mismatches, improve user on#boarding success rates, and cut down on manual reviews.
-
Real-time and scalable: Integrates with your existing stack to validate names instantly at scale.
Use cases
The following are key use cases for the Name Match API:
| Business type | Benefits |
|---|
| Fintech and payments | Prevent fraud and accelerate onboarding |
| KYC and lending | Automate compliance checks and reduce manual overhead |
| E-commerce | Decline suspicious collect requests or wallet withdrawals automatically |
| Payout and reconciliation | Minimise payout failures and automate reconciliation |
| Risk and fraud prevention | Flag name mismatches for deeper review |
Verifying name match
Follow these steps to verify the Name Match in the Merchant Dashboard:
- Log in to the Merchant Dashboard.
- In the left navigation menu, select Regulated Digital KYC, and then select Name Match.
- In the input fields, enter the two names you want to compare.
- Select Verify to start the name match check.
- View the
match score and match category in the popup.
You can also try the Verify Name Match API for real-time, programmatic validation.
Score categorisation
The following table lists the match categories and their corresponding score ranges returned by Name Match.
| Match category | Match score range |
|---|
| Direct Match | 1.00 |
| Good Partial Match | 0.85–0.99 |
| Moderate Partial Match | 0.60–84 |
| Poor Partial Match | 0.34–0.59 |
| No Match | 0.00–0.33 |
Examples
The following examples show sample name comparisons, their match scores, and the corresponding match categories.
| Name 1 | Name 2 | Match score | Match category |
|---|
| Rahul Verma | Rahul Verma | 1.00 | Direct Match |
| S K Mishra | Satish Kumar Mishra | 0.92 | Good Partial Match |
| Harsh Kishore | HKishore | 0.84 | Moderate Partial Match |
| Jatin Kumar | Jatin Roy | 0.52 | Poor Partial Match |
| Rakesh Sharma | Ritu Sharma | 0.23 | No Match |
