Medios & EntretenimientoInteligencia de Negocio

Cómo Millennium bcp Usa BigQuery ML para Aumentar las Tasas de Conversión de Préstamos

Millennium bcp, el mayor banco privado de Portugal, utilizó las herramientas de machine learning de Google Cloud BigQuery para construir modelos predictivos de audiencia en campañas de préstamos personales, logrando una tasa de conversión 2,6 veces mayor y una reducción del 36% en el coste por adquisición.

Impacto

90%

Incremento de Tasa de Conversión — Medios Propios

10x

Incremento de Volumen de Conversión — Medios Propios

5 days to 13 hours

Incremento de Volumen de Conversión — Medios de Pago

10 min to seconds

Incremento de Tasa de Conversión — Medios de Pago

Desafío

La dependencia de procesos presenciales en sucursal para préstamos personales limitaba la escalabilidad e impedía alcanzar digitalmente a los clientes elegibles de forma personalizada.

Solución

El equipo interno construyó modelos predictivos con BigQuery ML para segmentar clientes por propensión al préstamo y activó estas audiencias en canales propios y de pago a través de Google Analytics 4, Firebase y Display & Video 360.

Herramientas y tecnologías

Lo que dicen los líderes

Llevamos más de seis años trabajando con la tecnología de Google Cloud. Ha sido un contribuidor significativo a nuestros avances tecnológicos, impulsando la innovación y desafiándonos con las últimas tendencias. Estamos comprometidos a seguir siendo adoptadores tempranos, explorando nuevas funcionalidades y descubriendo oportunidades para hacer crecer nuestro negocio.

John Adams, Responsable de Analítica Digital, Millennium bcp
Entiende todo el contexto.

Regístrate para leer casos de estudio completos, acceder a métricas detalladas y recibir todos los reportes.

Historia completa

Millennium bcp dependía de procesos presenciales en sucursal para la tramitación de préstamos personales, lo que limitaba la escalabilidad y no satisfacía las expectativas digitales de los clientes modernos. El banco necesitaba una forma de dirigirse digitalmente solo a los clientes existentes elegibles con ofertas de préstamo personalizadas y a escala.

El equipo interno de marketing digital construyó modelos predictivos con BigQuery ML para segmentar a los clientes existentes según su propensión a solicitar un préstamo. Estas audiencias se activaron en canales propios y de pago a través de Google Analytics 4, Firebase y Display & Video 360.

Los resultados superaron las expectativas: las audiencias creadas con BigQuery generaron una tasa de conversión 2,6 veces mayor y un volumen de conversiones 2,4 veces superior en medios propios, mientras que en medios de pago el volumen de conversiones se duplicó y la tasa de conversión fue 1,9 veces mayor. El coste por adquisición se redujo un 36%.

Casos similares

L
Luminate
334%
increase in daily data processing speed

Luminate powers the Billboard music charts and provides data intelligence across music, film, and television for major record labels, studios, and talent agencies. After migrating from on-premises Spark and SQL Server to Snowflake, the company achieved 334% faster daily data processing across more than 3.5 terabytes of daily input. Market reports that previously took a full month now run overnight, and Luminate can for the first time deliver cross-industry insights correlating music and TV consumption.

Media & EntertainmentSSnowflakeSCSnowflake Cortex AI
M
MrBeast
1M+
players who engaged with ai agent

MrBeast and Salesforce built an AI-powered interactive puzzle challenge for Super Bowl 2026, engaging over 1 million players through a Slackbot agent that helped fans organize clues and test theories in real time. The entire enterprise-grade platform — capable of handling 1.5 million simultaneous users — was built in 42 days using Agentforce, Experience Cloud, and MuleSoft, with zero data retained from players.

Media & EntertainmentSASalesforce AgentforceMMuleSoft
TW
The Washington Post
100%
invoice tax accuracy coverage

The Washington Post is a technology-forward media company combining world-class journalism with digital innovation. Facing an unmanageable volume of vendor invoices with inconsistent tax formats, The Post deployed an AI Agent powered by proprietary large language models through Automation Anywhere’s Agentic Process Automation platform. The result: 100% of invoices are now validated for tax accuracy, tax overpayments have been eliminated entirely, and the Finance team captured $1 million in automation value within year one.

Media & EntertainmentAAAutomation Anywhere
TM
The Metropolitan Museum of Art

The Metropolitan Museum of Art partnered with OpenAI to create a conversational AI experience called "Chat with Natalie" for its Sleeping Beauties fashion exhibition, letting visitors interact with a historically accurate AI portrayal of a 1930s New York socialite whose wedding dress is on display.

Media & EntertainmentCChatGPTCCCustom Chat Experience
BI
Beast Industries
1 million+
players who relied on slackbot’s guidance

Beast Industries is the creator-led conglomerate behind MrBeast, one of the world’s most-followed YouTube channels with hundreds of millions of subscribers. For Super Bowl 2026, Beast Industries partnered with Salesforce to build a first-of-its-kind AI-powered puzzle hunt that ran for a month, supporting over 1 million active players and 1.5 million simultaneous users at peak. An agentic Slackbot — built on Salesforce’s Trust Layer — guided players through clue discovery without revealing answers, blocking 64,000 prompt injection attacks in the process.

Media & EntertainmentSASalesforce Agentforce
L
Luminate
334%
increase in daily data processing speed

Luminate, the entertainment data company behind the Billboard music charts, migrated from on-premises infrastructure to Snowflake to unify 3.5TB of daily data across music, film, and television. The move delivered 334% faster daily processing, reduced market report turnaround from a full month to overnight, and enabled cross-industry analytics the company could not previously perform.

Media & EntertainmentSMSnowpark MLSSnowflake
T
TRY
30%
reduction in time spent on routine tasks

TRY, Norway's largest creative agency group with 400+ professionals, deployed Claude Enterprise as an enterprise-wide AI platform across creative, strategy, and technical teams. The implementation drove a 30% reduction in time spent on routine tasks and a 40% acceleration in proposal development. Over 50 use cases have been deployed across the organization's six business units.

TechnologyMedia & EntertainmentCEClaude Enterprise
O
Omnicom
90%
compute infrastructure cost reduction

Omnicom is one of the world’s largest marketing communications networks, with 75,000 employees serving over 5,000 clients across 70+ countries. The company migrated nine global data centers to AWS and built an AI-powered platform on Amazon Bedrock and Amazon SageMaker to deliver hyper-personalized campaigns at scale. The migration cut compute infrastructure costs by 90% while enabling real-time processing of 400 billion daily marketing events.

Media & EntertainmentASAmazon SageMakerABAmazon Bedrock