Use Case Intelligence RSS Search use cases Search
Snowflake Media and Entertainment Nashua, New Hampshire

Yieldmo

Marketing Personalization · Real-time Analytics

serve privacy-first advertising predictions at low latency without moving huge data volumes out of Snowflake or overpaying for inference infrastructure.

Read the original story Explore all use cases
20x faster advertising predictions
75% cost reduction for inference layer
a quarter of the cost
billions of daily impressions

Reported impact

Business outcome

Yieldmo made advertising predictions 20 times faster at a quarter of the cost, improved collaboration with partners, and created a path to score every impression instead of relying on heavy sampling.

  • Cost Reduction
  • Customer Experience
  • Revenue Growth

Solution

Yieldmo uses Snowflake, Snowpark Container Services, and Secure Data Sharing on Snowflake to serve privacy-first advertising predictions at low latency without moving huge data volumes out of snowflake or overpaying for inference infrastructure. Signals such as smartphone scrolls, tilts, and swipes from billions of daily impressions are stored and processed in Snowflake for campaign prediction workloads. Yieldmo develops models with H2O Driverless AI and runs H2O eScorer on Snowpark Container Services so inference happens next to the data instead of after large exports. The resulting predictions support near-real-time advertising decisions, while Secure Data Sharing lets Yieldmo collaborate with vendors and cybersecurity partners without building ETL pipelines. Keeping ingestion, storage, transformation, and downstream access on one governed platform reduces data copying, simplifies operations, and gives teams a single trusted operating view for analytics and AI. Yieldmo made...

Data flow

behavioral ad-impression signals and log data flow into Snowflake, Snowpark Container Services, and Secure Data Sharing; curated data and model outputs are then served to prediction services, operations teams, and external partners.

Solution architecture

3 components · 3 layers
  1. Compute
    • Snowpark Container Services Runs containerized inference or application services close to Snowflake data.
  2. Storage
    • Snowflake Provides the centralized data platform that stores governed datasets and serves analytics or AI workloads.
  3. Serving
    • Secure Data Sharing Shares governed data with partners or internal consumers without moving copies.

Architecture clues

  • Keeps data in Snowflake instead of moving it into a separate inference environment.
  • Uses H2O Driverless AI for model development and H2O eScorer running on Snowpark Container Services for inference.
  • Uses Secure Data Sharing for governed collaboration with Kumo and HUMAN Security.

Evidence from the source

By developing and running AI models on Snowpark Container Services, Yieldmo delivers predictions 20 times faster at a quarter of the cost
Yieldmo uses H2O Driverless AI to develop machine learning models and produce predictions
provides log file data to another Snowflake partner, HUMAN Security
securely shares data with Snowflake partner and AI software company Kumo
Transparency Evidence & methodology 95/100 reference value · 79% 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 value95/100
  • 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 scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence79%
  • 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
    4 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency8/10
    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. Snowflake

    Yieldmo customer story

    First-party
    https://www.snowflake.com/en/customers/all-customers/case-study/yieldmo/
    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 Apr 9, 2025 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source
  • Sitemap last modified Jul 9, 2026 · Snowflake · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Snowflake Archived · Sep 24, 2026 Foodics Software / SaaS Saudi Arabia Foodics needed near-real-time analytics for tens of thousands of restaurant branches, but older systems struggled with reliability, code-heavy integration work, and the scale of daily reports and jobs. 2M daily reports for over 39,000 customers Marketing PersonalizationReal-time Analytics Snowflake · Snowflake Secure Data Sharing · custom ODBC driver Google Cloud Archived · Sep 13, 2026 Machina Sports Media and Entertainment United States Machina Sports needed to deliver low-latency live-sports experiences to large concurrent fan audiences while staying flexible enough to swap models, ground answers in fresh information, and expand multimodal features… Expanded market presence to 1.6M sports fans in Brazil Marketing PersonalizationReal-time Analytics Cloud Storage · Gemini Enterprise Agent Platform · Gemini Flash Lite PwC Aug 31, 2026 Seattle Mariners Media and Entertainment United States The Mariners wanted to grow fan engagement and ticket sales, but their marketing still relied on six broad segments, annual survey responses from about 50,000 fans, and disconnected CRM, ticketing, and engagement… 1.15 million fans tracked across disparate data sources Marketing PersonalizationReal-time Analytics Anthropic · Mariners Intelligence · Microsoft Azure