AWS Media and Entertainment Japan

SmartNews

Application Refactoring

SmartNews has been using AWS to power its application but wanted to optimize its costs as it grew.

Read the original story Explore all use cases

15% decrease in latency from 190 ms to 60 ms

By using Spot Instances, SmartNews cut costs for the main compute workload by up to 50 percent.

For some of its backend service workloads, the company uses a mix of 70 percent Spot Instances and 30 percent other payment plans.

Now, SmartNews uses AWS Graviton for 60–70 percent of its ML workloads and is migrating its data pipelines to AWS Graviton as well.

Reported impact

Business outcome

Combining AWS Graviton and Spot Instances, SmartNews has significantly lowered monthly costs and improved performance with no negative impact on customers. Those cost savings contribute directly to future innovation as the company uses them to improve its product and ML models. Key reported metrics include cost savings on main workload using Spot Instances 50%; cost savings on ML workloads using AWS Graviton 15%; 15% decrease in latency from 190 ms to 60 ms.

Solution

Learn how news and media application SmartNews improved performance while cutting costs using AWS Graviton and Spot Instances. News aggregator SmartNews uses machine learning (ML) algorithms to deliver relevant news to its readers. One of the key goals of the company is to help readers break out of information bubbles by showing news from trusted publishers on all sides of an issue—not only the sources that reflect the user’s viewpoint or that the user has shown interest in. To accomplish its mission, SmartNews uses Amazon Web Services (AWS) to meet its infrastructure needs. In 2023–2024, SmartNews migrated to new instance types and alternate pricing models on AWS to optimize costs without interrupting service to customers. It implemented best practices to make use of Amazon Elastic Compute Cloud (Amazon EC2) Spot Instances , a pricing plan to run fault-tolerant, stateless workloads at up to 90 percent discount compared to Amazon EC2 On-Demand pricing.

Data flow

Source data enters the SmartNews workflow through its application services, processed with AWS Graviton processors, Amazon EKS, Amazon EC2 C7g Instances.

Solution architecture

5 components · 1 layer

Compute
- AWS Graviton processors Improve price performance for compute workloads running on Arm-based instances.
- Amazon EKS Runs containerized workloads and Kubernetes-based application services.
- Amazon EC2 C7g Instances Runs cost-efficient compute workloads on AWS Graviton processors.
- Amazon EC2 R6g Instances Runs memory-intensive workloads on AWS Graviton processors.
- Amazon EC2 R7g Instances Runs memory-intensive workloads on AWS Graviton processors.

Architecture clues

By using Spot Instances, SmartNews cut costs for the main compute workload by up to 50 percent.
For some of its backend service workloads, the company uses a mix of 70 percent Spot Instances and 30 percent other payment plans.
Nearly all of its Spark workloads are running on both AWS Graviton and Spot Instances, using Amazon EC2 R6g Instances , powered by AWS Graviton2 processors, and Amazon EC2 R7g Instances , memory-optimized instances power
Now, SmartNews uses AWS Graviton for 60–70 percent of its ML workloads and is migrating its data pipelines to AWS Graviton as well.
Using AWS Graviton–based instances, the company also reduced latency for these workloads from 190 milliseconds to 60 milliseconds, a 68 percent decrease.
“Using Spot Instances has been a success story for the company,” says Singhal.

Evidence from the source

15% decrease in latency from 190 ms to 60 ms

By using Spot Instances, SmartNews cut costs for the main compute workload by up to 50 percent.

For some of its backend service workloads, the company uses a mix of 70 percent Spot Instances and 30 percent other payment plans.

Now, SmartNews uses AWS Graviton for 60–70 percent of its ML workloads and is migrating its data pipelines to AWS Graviton as well.

SmartNews has been using AWS to power its application but wanted to optimize its costs as it grew.

Using AWS Graviton–based instances, the company also reduced latency for these workloads from 190 milliseconds to 60 milliseconds, a 68 percent decrease.

Transparency Evidence & methodology 87/100 reference value · 87% confidence · 1 source

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

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 value87/100

Problem clarity12/20
Measures whether the customer's operational problem is specific enough to compare.
Implementation depth20/25
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
6 metrics describe measurable impact.
Deployment scale10/10
Rewards evidence of a live or scaled deployment and meaningful integration scope.

Evidence confidence87%

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
6 direct source quotes retained.
Date provenance8/10
The publication date comes from publisher-controlled metadata.
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.

Traceability

Sources & provenance

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

AWS
SmartNews customer story

First-party
https://aws.amazon.com/solutions/case-studies/smartnews-graviton-case-study/

Source type
Vendor-published customer story

Published
Dec 19, 2024
Supports
- Customer
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- technical area
- use case category
- Business outcome
- outcome category
- Metrics
- Architecture
- evidence quotes
- Publication date

Date evidence

Publisher catalog date Dec 19, 2024 · AWS · First-party
Open date source

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Similar use cases

See all like this

OpenAI Oct 8, 2026 CyberAgent Media and Entertainment Asia-Pacific & Oceania CyberAgent needed a secure, governed way to spread AI across advertising, media, gaming, and development teams so employees could work faster and make better decisions without risking uncontrolled data use or fragmented… 93% monthly active usage of ChatGPT Enterprise Application RefactoringIT Operations Automation ChatGPT Enterprise · Codex

Google Cloud Archived · Jul 19, 2026 Picsart Media and Entertainment United States Picsart democratizes visual content with intuitive, AI-powered photo and video editing tools for billions. Leveraging Google Cloud, Gemini platform, and Gemini models, they seamlessly scale and rapidly deploy advanced… "With Gemini Omni, we're thrilled to bring this powerful, granular technology to 130 million Picsart users… Application Refactoring Cloud Storage · Compute Engine · Gemini Flash

Google Cloud Modified · Jul 2, 2026 Nextory Media and Entertainment Sweden Nextory is one of Europe’s largest sources for audiobooks, ebooks, and digital magazines. Working with hundreds of publishers across the world, the streaming platform aims to provide readers with everything from the… Cuts large-book processing from 80 minutes to two Application Refactoring Antigravity · Cloud Run · Gemini CLI