STOCK TITAN

Yiren Digital's AI-Enabled Fraud Detection Framework Helped Avoid RMB165 Million in Potential Fraud-Related Losses in 2025

(Moderate)
(Neutral)
Tags
AI

Yiren Digital (NYSE: YRD) reported that its AI-enabled fraud detection framework, centered on the Hawkeye system and DiTing intelligent decision platform, intercepted 10,300 fraudulent borrowers across 14,500 cases in 2025, helping avoid approximately RMB165 million (US$23 million) in potential fraud-related losses.

According to the company, its end-to-end AI risk framework spans pre-loan, in-loan and post-loan stages, combining risk models, data analysis and expert review. By end-2025, its proprietary blacklist held about 800 million records, with Hawkeye and DiTing cumulatively identifying over 500,000 suspected fraudulent borrowers and 41,993 malicious actors.

Loading...
Loading translation...

Positive

  • RMB165 million in potential fraud-related losses avoided in 2025
  • 10,300 fraudulent borrowers intercepted across 14,500 cases in 2025
  • Blacklist database reached approximately 800 million records by end-2025
  • Hawkeye and DiTing identified over 500,000 suspected fraudulent borrowers
  • 41,993 malicious actors linked to black-market operations identified
  • DiTing can screen about 30,000 potentially risky credentials per day

Negative

  • None.

Market Context

YRD’s AI-tagged history averaged -3.75% across five events, adding a cautionary platform benchmark t...
Analysis

YRD’s AI-tagged history averaged -3.75% across five events, adding a cautionary platform benchmark to this fraud-detection announcement. The prior close was $1.23; reported operating results remain a relevant reference point.

Key Figures

Fraudulent borrowers intercepted: 10,300 borrowers Fraud cases screened: 14,500 cases Fraud losses avoided: RMB165 million (US$23 million) +5 more
8 metrics
Fraudulent borrowers intercepted 10,300 borrowers 2025
Fraud cases screened 14,500 cases 2025
Fraud losses avoided RMB165 million (US$23 million) 2025 fraud-related losses
Blacklist database Approximately 800 million records As of the end of 2025
Suspected fraudulent borrowers identified More than 500,000 borrowers Cumulative identification by Hawkeye and DiTing
Malicious actors identified 41,993 actors Cumulative identification associated with black-market operations
Daily credential screening capacity Approximately 30,000 credentials DiTing daily screening capacity
Daily fraud detections Approximately 1,500 counterfeit documents and more than 1,000 video-fraud cases Daily identification by document and identity-verification tools

Previous AI Reports

5 past events · Latest: Aug 04 (Positive)
Same Type Pattern 5 events
Date Event Sentiment 24h Move Catalyst
Aug 04 AI operations Positive +0.9% AI agents expanded customer-service automation with reported answer-rate and complaint outcomes.
Jul 30 ESG report Positive +4.7% ESG report described responsible-AI controls and broader enterprise platform deployment.
Jul 23 AI efficiency Positive -3.2% AI agents reduced human handling and increased service tickets per employee.
Jul 08 AI warrant deal Positive -10.4% Warrant agreement offered staged rights to a potential controlling stake in platform.
May 26 AI investments Positive -10.6% Follow-on investments expanded the AI ecosystem with performance-based ownership warrants.

24h Move is the share-price change in the day after each event; other market factors may also have contributed.

Pattern Detected

YRD's AI-related announcements showed mixed outcomes, with two positive reactions and three declines; the tag-specific average move was -3.75%.

Key Terms

underwriting, credit-risk assessment, multi-agent platform
3 terms
underwriting financial
"improve underwriting quality and support timely intervention"
Underwriting is the process where a financial institution agrees to buy and then resell new stocks or bonds to investors. It matters because it helps companies raise money quickly and smoothly, while the bank takes on the risk of selling those securities at the agreed price. Think of it like a booker guaranteeing to sell all tickets for a concert before opening the doors.
View in glossary
credit-risk assessment financial
"supporting fraud identification, refined credit-risk assessment"
An evaluation of a borrower’s ability and likelihood to repay debts, based on factors like income, assets, existing liabilities, credit history and broader economic conditions. Like a mechanic inspecting a used car before a buyer commits, it helps lenders, bond investors and creditors estimate default risk, set interest rates or required returns, and price or provision for potential losses in portfolios and financial statements.
multi-agent platform technical
"the MagiCube 2.0 multi-agent platform"
A multi-agent platform is a software environment where many independent programs, or “agents,” work together or compete to perform tasks like data analysis, trading, or customer interactions. Think of it as a team of specialized robots each handling parts of a job—coordinating, sharing information, and adapting to changes. Investors care because these platforms can speed decision-making, cut costs, scale services, and introduce new operational or regulatory risks that can affect profitability and valuation.

AI-generated analysis. How Rhea-AI works. Not financial advice.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google
Add on Google

Hawkeye and DiTing helped prevent RMB165M (approximately US$23M) in fraud losses in 2025, reinforcing Yiren Digital's credit-risk discipline

BEIJING, Aug. 12, 2026 /PRNewswire/ -- Yiren Digital Ltd. (NYSE: YRD) ("Yiren Digital" or the "Company"), a leading company specializing in financial technology and artificial intelligence innovation across multiple industries in China and global markets, today announced that its AI-powered fraud detection systems intercepted 10,300 fraudulent borrowers across 14,500 cases in 2025, helping avoid RMB165 million (US$23 million) in fraud-related losses and demonstrating how enterprise AI can strengthen credit-risk management through AI-led fraud detection and intelligent decision-making.

As part of its broader "All-in-AI" strategy, Yiren Digital has established a proactive AI risk management framework spanning pre-loan, in-loan and post-loan processes. The framework combines the Company's Hawkeye fraud detection system, the DiTing intelligent decision-making platform, risk models, data analysis and specialist review to identify suspicious activity, improve underwriting quality and support timely intervention.

"Risk management is one of the clearest examples of how AI can create measurable value across highly regulated financial services," said Mr. Ning Tang, Chairman and Chief Executive Officer of Yiren Digital. "Our third-generation AI fraud detection technology represents a significant advancement in financial risk management, enabling more adaptive and precise detection while continuously responding to emerging fraud patterns. Built on years of innovation, this advanced platform is now available as an exportable service, enabling financial institutions and fintech companies to deploy enterprise-grade fraud protection without massive infrastructure investment."

Yiren Digital uses a monitoring-analysis-response-review process to track asset quality, compliance dynamics and other risk indicators, trigger warnings when specified thresholds are reached, and coordinate responses across risk control, legal and other functions, supporting more proactive portfolio risk management.

Its proprietary DiTing system applies AI models to analyze multidimensional information, including credit reports, user behavior and other authorized data, supporting fraud identification, refined credit-risk assessment and more consistent credit decisions. Hawkeye uses accumulated fraud cases and structured feedback to update screening rules and strengthen future detection.

Yiren Digital's AI Fraud Protection at Scale

  • Fraud losses avoided: In 2025, the Company intercepted 10,300 fraudulent borrowers across 14,500 cases, helping avoid RMB165 million (US$23 million) in losses.
  • Cumulative fraud intelligence: As of the end of 2025, the Company's proprietary blacklist database contained approximately 800 million records. Hawkeye and DiTing had cumulatively identified more than 500,000 suspected fraudulent borrowers and 41,993 malicious actors associated with black-market operations.
  • High-volume screening: DiTing supports AI-driven risk decisions with daily capacity to screen approximately 30,000 potentially risky credentials. Related document and identity-verification tools identify approximately 1,500 counterfeit documents and more than 1,000 video-fraud cases each day.
  • Human oversight and governance: Hawkeye analyzes fraud-risk events using historical cases, risk-assessment results and algorithmic rules, and generates virtual work orders for fraud detection specialists. Automated identification is combined with human review to support consistent, reviewable decisions in higher-risk cases.

The Company's fraud detection capabilities are built on its proprietary enterprise AI architecture, including the MagiCube 2.0 multi-agent platform, which provides common infrastructure for enterprise AI deployment across risk management and other core business functions, allowing proven AI capabilities to be deployed more efficiently across the organization.

These production AI deployments illustrate how Yiren Digital is applying enterprise AI beyond workflow automation to strengthen credit-risk management, improve fraud detection, enhance credit decision-making and help reduce potential fraud-related losses across regulated financial services.

Going forward, Yiren Digital will continue strengthening AI-enabled credit-risk management and governance across its credit and insurance operations, while enhancing model monitoring, explainability and human oversight across regulated business lines to support long-term asset quality, operational resilience and responsible AI deployment.

About Yiren Digital

Yiren Digital Ltd. is a leading company specializing in financial technology and artificial intelligence innovation across multiple industries in China and global markets. The Company leverages advanced artificial intelligence and emerging technologies to enhance customer experience, optimize capital efficiency, and expand financial inclusion. Following the regulatory filing of its in-house developed Large Language Model Zhiyu, and the significant enhancement of its MagiCube Agent platform, Yiren Digital is establishing a new growth engine to accelerate its evolution into an AI-native, multi-industry operating platform extending beyond traditional financial services. For more information, please visit https://ir.yiren.com.

Safe Harbor Statement

This press release contains forward-looking statements. These statements are made under the "safe harbor" provisions of the U.S. Private Securities Litigation Reform Act of 1995. These forward-looking statements can be identified by terminology such as "aim," "anticipate," "believe," "estimate," "expect," "hope," "going forward," "intend," "ought to," "plan," "project," "potential," "seek," "may," "might," "can," "could," "will," "would," "shall," "should," "is likely to" and the negative form of these words and other similar expressions. This press release contains forward-looking statements within the meaning of Section 21E of the Securities Exchange Act of 1934, as amended, and as defined in the U.S. Private Securities Litigation Reform Act of 1995. These statements can be identified by terminology such as "will," "expects," "anticipates," "future," "intends," "plans," "believes," "estimates," "target," "confident," and similar expressions. Forward-looking statements are based on management's current expectations, assumptions, and assessments of current market and operating conditions. These statements involve inherent risks, uncertainties, and other factors, many of which are outside the control of the Company, and which could cause actual results to differ materially from those expressed or implied in such statements. Actual results may differ materially from those expressed or implied in forward-looking statements due to a variety of factors and other risks described in the Company's filings with the U.S. Securities and Exchange Commission. All forward-looking statements speak only as of the date of this press release. The Company undertakes no, and expressly disclaims any, obligation to update or revise any forward-looking statements, whether as a result of new information, future events, or otherwise, except as required under applicable law.

Cision View original content:https://www.prnewswire.com/news-releases/yiren-digitals-ai-enabled-fraud-detection-framework-helped-avoid-rmb165-million-in-potential-fraud-related-losses-in-2025-302849501.html

SOURCE Yiren Digital Ltd.

FAQ

What did Yiren Digital (NYSE: YRD) report about AI fraud loss prevention in 2025?

Yiren Digital reported avoiding about RMB165 million (US$23 million) in potential fraud-related losses in 2025. According to Yiren Digital, its Hawkeye and DiTing AI systems intercepted 10,300 fraudulent borrowers across 14,500 cases, strengthening its overall credit-risk management framework.

How many fraudulent borrowers did Yiren Digital’s AI systems block in 2025?

Yiren Digital’s AI fraud detection intercepted 10,300 fraudulent borrowers across 14,500 cases in 2025. According to Yiren Digital, this interception helped avoid RMB165 million in potential losses and showcased the effectiveness of its enterprise AI risk management framework in financial services.

What is the scale of Yiren Digital’s blacklist database as of the end of 2025?

As of the end of 2025, Yiren Digital’s proprietary blacklist database contained about 800 million records. According to Yiren Digital, Hawkeye and DiTing had cumulatively identified more than 500,000 suspected fraudulent borrowers and 41,993 malicious actors connected to black-market operations.

How many risky credentials can Yiren Digital’s DiTing platform screen daily?

Yiren Digital’s DiTing platform can screen around 30,000 potentially risky credentials per day. According to Yiren Digital, related document and identity-verification tools detect about 1,500 counterfeit documents and over 1,000 video-fraud cases each day, supporting large-scale, AI-driven risk decisions.

How does Yiren Digital combine AI and human review in fraud detection for YRD?

Yiren Digital combines automated AI detection with specialist review for higher-risk cases. According to Yiren Digital, Hawkeye generates virtual work orders from historical cases and algorithmic rules, enabling fraud detection specialists to deliver consistent, reviewable decisions within its enterprise risk governance framework.

Is Yiren Digital’s AI fraud detection platform available to other financial institutions?

Yes, Yiren Digital states its third-generation AI fraud detection technology is available as an exportable service. According to Yiren Digital, this allows financial institutions and fintech companies to deploy enterprise-grade fraud protection without undertaking massive infrastructure investment in their own systems.

What role does Yiren Digital’s MagiCube 2.0 play in its AI strategy?

MagiCube 2.0 provides the enterprise AI architecture underpinning Yiren Digital’s fraud detection and risk tools. According to Yiren Digital, this multi-agent platform offers common infrastructure so proven AI capabilities can be deployed more efficiently across core business functions, including risk management and credit decisions.