What challenges did GCash face before AI implementation?

The legacy on-premise platform struggled to accommodate dynamic operational scaling. Growing data volumes created insufficient real-time insights and advanced analytics needs. GCash needed a secure, always-on cloud platform for advanced analytics, risk modeling, fraud detection, and uninterrupted service.

What was the impact of the AI solution?

The collaboration enabled always-on, secure service at scale for millions of users and merchants. The platform supports advanced real-time analytics and AI-driven risk and fraud capabilities. GCash’s cloud journey also improved platform stability, regulatory compliance, and operational excellence.

Source

AlibabaScaled productionEvidence: Medium55/100

GCash on Alibaba Cloud: scalable, real-time finance platform with PAI-based risk and fraud modeling

Use case typeReal-time analyticsUpdated Jun 16, 2026

GCash partnered with Alibaba Cloud to migrate a legacy on-premise platform to a scalable cloud architecture for its digital payments super app in the Philippines. The platform supports high-concurrency transactions, secure storage, batch and real-time analytics, and AI model development for risk modeling, fraud detection, and user insights. Alibaba Cloud services used include Elastic Compute Service (ECS), Object Storage Service (OSS), MaxCompute, Hologres, Machine Learning Platform for AI (PAI), Web Application Firewall (WAF), Log Service (SLS), and ZOLOZ Real ID.

Organization: GCash
Industry: Finance
Location: Philippines
Published: June 2026

Reported outcomes

Strategic outcomes

Scale & capacityEnabled always-on service at scaleBetter decisions & insightSupported real-time analytics and insightsRisk & complianceImproved regulatory compliance and operational excellence

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: GCash
Provider: Alibaba
Maturity: Scaled Production
Linked source: Alibaba Cloud Customers

The collaboration enabled always-on, secure service at scale for millions of users and merchants

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 2 of 2

1Real-time analytics
2Data platform modernization

The legacy on-premise platform struggled to accommodate dynamic operational scaling.
Growing data volumes created insufficient real-time insights and advanced analytics needs.
GCash needed a secure, always-on cloud platform for advanced analytics, risk modeling, fraud detection, and uninterrupted service.

GCash implemented a scalable Alibaba Cloud architecture with ECS for dynamic compute, OSS for storage, and managed services for high-concurrency transaction processing and low-latency caching.
MaxCompute supports large-scale batch processing while Hologres enables real-time and interactive analytics.
PAI is used to build and deploy machine learning models for risk modeling, fraud detection, and user insights, with WAF, SLS, and ZOLOZ Real ID strengthening security, logging, and eKYC.

Technologies

Alibaba Cloud Elastic Compute Service Alibaba Cloud Object Storage Service (OSS)Alibaba Cloud MaxCompute Alibaba Cloud Hologres Alibaba Cloud Machine Learning Platform for AI Alibaba Cloud Web Application Firewall Alibaba Cloud Log Service ZOLOZ Real ID

The collaboration enabled always-on, secure service at scale for millions of users and merchants.
The platform supports advanced real-time analytics and AI-driven risk and fraud capabilities.
GCash’s cloud journey also improved platform stability, regulatory compliance, and operational excellence.

Architecture

GCash deployed a multi-service Alibaba Cloud architecture using ECS, OSS, MaxCompute, Hologres, PAI, WAF, SLS, and ZOLOZ Real ID. The design supports high-concurrency OLTP, batch warehousing, real-time analytics, identity verification, and operational monitoring, with grayscale deployment and contingency planning guidance from Alibaba Cloud engineers.

Sources & evidence1

Evidence: Medium55/100Evidence strength