Huawei Cloud Travel and Hospitality China Translated from Chinese

Hainan Airlines (海南航空股份有限公司)

Fraud Detection · Risk Management

Hainan Airlines needed to stop scraping, fake seat holds, and marketing abuse across its digital channels because those attacks were raising costs, destabilizing pricing, and hurting direct-sales conversion.

direct-sales rate was below 50%
more than RMB 10 million in annual marketing losses from abuse
more than RMB 5 million in annual losses from ticket-information scraping
overall flight-query costs decreased by 90%

Reported impact

Business outcome

The system reduced abusive traffic and fraudulent activity, stabilized airfare-query operations, and improved legitimate customer experience while saving the airline substantial operating cost.

  • Cost Reduction
  • Customer Experience
  • Risk Reduction

Solution

Hainan Airlines deployed Dingxiang's intelligent risk-control stack to stop bots and abuse across airfare search, seat inventory, and marketing workflows. The core intelligent risk-control platform combines multi-dimensional business data to score traffic and identify risky behavior in real time. Around that core, the airline added an intelligent CAPTCHA service for human-versus-bot verification and a device-fingerprint tool that creates a unique identifier for each device so spoofed clients can be detected even when they rotate accounts or requests. Query, booking, and campaign interactions are evaluated by the risk engine, which can block malicious crawling, false seat holds, and promotional abuse while allowing normal passengers to continue with minimal friction. The deployment stabilizes the airline's pricing system by cutting invalid query traffic and gives operations teams a common fraud-response layer instead of manual review across separate channels.

Data flow

Ticket-query, seat-booking, and campaign requests are combined with device signals and other business data, then checked by device fingerprinting, CAPTCHA, and the intelligent risk-control platform. The risk engine decides whether to block or allow the interaction, reducing scraping, fake seat holds, and fraudulent campaign activity before those requests affect pricing or customer experience.

Solution architecture

3 components · 2 layers
  1. Compute
    • device fingerprint tool Generates unique device identifiers so spoofed clients and repeated abuse can be detected.
  2. Serving
    • Dingxiang intelligent risk-control platform Scores traffic and business activity from multiple data dimensions to identify risky airline interactions.
    • intelligent CAPTCHA tool Performs human-versus-bot verification to block automated abuse in airline workflows.

Architecture clues

  • Human verification and device fingerprinting are separate control layers around the scoring platform.
  • The deployment targets scraping, fake seat holds, and promotional abuse in airline digital channels.
  • The risk engine combines multi-dimensional business data for automated risk judgment.

Evidence from the source

"Marketing abuse such as coupon farming caused annual losses of more than RMB 10 million. (original: 薅羊毛等营销作弊行为,每年给航司造成1000万以上的营销费用损失。)"
"The Dingxiang intelligent risk-control platform helped Hainan Airlines identify risk precisely, save several million yuan in operating costs, reduce overall flight-query fees by 90%, and improve normal users' query efficiency and experience. (original: 顶象智能风控平台助力海航精准识别风险,节省运营成本数百万元,航班查询费用整体下降90%,同时提升了正常用户的航班查询效率及体验。)"
"The intelligent risk-control platform combines multi-dimensional business data to judge risk intelligently. (original: 结合多维度业务数据,智能判断风险。)"
"Third-party OTA companies held seats maliciously, which sharply reduced conversion and kept the direct-sales rate well below 50%. (original: 第三方OTA公司实占、虚占航班座位,导致销售转化率大幅降低,直销率远低于50%。)"
"Third-party OTA companies scraped airline ticket information and caused annual economic losses of more than RMB 5 million. (original: 第三方OTA公司爬取航司票务信息,每年造成经济损失500万以上。)"
Transparency Evidence & methodology 100/100 reference value · 81% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence81%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency10/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Huawei Cloud

    海南航空股份有限公司_客户案例-华为云

    First-party
    https://www.huaweicloud.com/cases/hnair.html
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes

Date evidence

  • First archived Aug 5, 2025 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.