Partner Success with AWS / Media & Entertainment / Israel

December 2024
LSports
CloudZone

CloudZone Streamlines and Adapts Machine Learning Model Lifecycles in the Cloud for LSports

Learn how CloudZone and AWS helped LSports accelerate delivery of sports betting data.

75%

reduction in model deployment time

50%

reduction in the model development cycle time

10x

training data upscaled

Overview

LSports is a sports data company that provides an innovative API for the sports betting industry, providing high-quality live sports data feeds to clients worldwide. The company had a large repository in their data warehouse and wanted to use this data to provide advanced features to their customers. AWS Partner CloudZone developed an end-to-end machine learning (ML) pipeline. It was designed and built on top of a robust ML foundational service, delivering a training pipeline that controls data preparation, model training, and model deployment for more efficient model training as well as improved performance thanks to better cloud compute power.

High-Tech Betting Station with Multiple Screens Displaying Live Sports and Data in a Modern Gaming Environment

Opportunity | Betting on the Benefits of Machine Learning

LSports had a large data repository in its data warehouse and wanted to create ML models from this data to improve the accuracy of its largely human-driven predictions. The company also wanted to streamline operations so it could scale up to meet increasing demand for its services. The company’s in-house approach to training ML models was slow and took large amounts of processing power that its team’s individual laptops struggled to handle, making it nearly impossible to leverage the large data sets required to improve accuracy. Much like the athletes at the heart of its business, LSports hoped to move faster, stronger, and smarter. And it planned to achieve this by moving to a cloud-powered ML platform.

The challenge was finding an ML platform that could efficiently handle the complexities of pre-processing, training, and deploying models at scale, while also simplifying the ML development lifecycle with a unified system for managing models, tracking versions, and ensuring transparency in model evolution. To address these challenges and capitalize on the opportunities in the rapidly evolving sports betting industry, LSports engaged CloudZone to take its sports betting game to the next level.

kr_quotemark

The Data team at CloudZone has been a pleasure to work with. They are quick and responsive, and always follow through on commitments. The development process for our machine learning pipeline was seamless and now we have a working ML platform with Amazon SageMaker.”

Daniel Netzer
VP of R&D, LSports

Solution | A New Way to Crunch the Numbers

To help LSports meet its goals for efficiency and accuracy, CloudZone developed a full ML pipeline which was designed and built on top of Amazon SageMaker, a fully managed service that brings together a broad set of tools to perform various ML tasks like data processing, training, evaluation and inference on high volumes of data at low cost. With Amazon SageMaker, you can build, train and deploy ML models at scale using tools and strategies like notebooks, debuggers, profilers, pipelines, MLOps, and more—all in one platform.

CloudZone’s solution implemented MLOps methodologies, defining the responsibility of each team that has a hand in the model lifecycle, and delivered a training pipeline that controls data preparation, model training, and model deployment. All stages were implemented on Amazon SageMaker Pipeline, and the pipeline was wrapped in Amazon Web Services (AWS)-native tools to control triggers and manual approvals. The data science team also integrated Amazon SageMaker Studio as an integrated development environment (IDE) to leverage purpose-built tools for ML development, like managing experiments, explainability capabilities, data visualization, and more. Leveraging the power of AWS helped the organization’s data science teams move faster as they were no longer limited by the computational power of their laptops.

Key steps in the CloudZone’s ML pipeline include:

  1. Triggering the CI pipeline: Users can initiate the pipeline using a schedule, webhook, or manual trigger, which starts the continuous integration (CI) process.
  2. Lambda function execution: An AWS Lambda function is executed to trigger the Amazon SageMaker pipeline and waits for it to be complete.
  3. Amazon SageMaker pipeline processing:
    1. Processing Step (Data Wrangler): Prepares and processes the data for training.
    2. Training Step (Model Training): Trains the ML model using the prepared data.
    3. Processing Step (Model Evaluation): Evaluates the trained model's performance.
    4. Condition Step (Model Accuracy): Checks if the model meets the accuracy requirements.
  4. Model registration and approval:
    1. If the model meets the accuracy criteria, it proceeds to the Create Model Step and Register Model Step, where the model is packaged and registered.
    2. The process then waits for manual approval before proceeding further.
  5. Model deployment:
    1. Once approved, the process triggers AWS EventBridge, which is connected to the continuous deployment (CD) pipeline.
    2. The CD pipeline deploys the model first to a staging environment using a Lambda function and AWS CloudFormation.
    3. After another manual approval, the model is deployed to the production environment.

 

Outcome | LSports Gives Their New ML Pipeline a High Score

The initial data migration and subsequent MLOps project enabled LSports to train models on larger datasets, experiment with new central processing unit/graphic processing unit (CPU/GPU) architectures, and significantly enhance its ML capabilities. This not only improved the efficiency of its predictive models but also freed its data scientists from hardware limitations, enabling them to focus on innovation rather than infrastructure. The success of this project has led LSports to expand its use of AWS, further developing its machine learning platform and continuing its digital transformation. Confirming the value that CloudZone brought to the table, Daniel Netzer, VP of R&D at LSports expressed that, “The Data team at CloudZone has been a pleasure to work with. They are quick and responsive, and always follow through on commitments. The development process for our machine learning pipeline was seamless and now we have a working ML platform with Amazon SageMaker. It’s amazing how much we’ve progressed in just a few weeks!”

The implementation of these advancements has yielded significant accomplishments in enhancing the customer’s machine learning initiatives. The solution has reduced the overall time it takes to train a new model and then deploy it—from about three weeks to one week, reflecting a 50 percent reduction. Additionally, the increase in the number of models trained and deployed after implementing the solution showcases the scalability of the Amazon SageMaker platform, allowing for more models to be developed and utilized. In fact, model deployment times were reduced by up to 75 percent. Finally, working with a managed platform allowed CloudZone to create an environment that facilitates the development of improved models. This is achieved through the ability to test, model, and experiment on vast amounts of data. Training data in this instance was upscaled by up to ten times, which helps ensure higher-quality models.

About LSports

LSports is a high-profile sports betting company. Working with key sports industry clients since 2012, the company empowers sportsbooks and media companies with high-quality sports data on a wide range of events, so they can build the best product possible for their business. Thanks to a passionate team working hard to perfect the tech, LSports can offer you a wide range of sports data services and solutions.

About AWS Partner CloudZone

CloudZone is an AWS Premier Tier Services Partner offering best-in-class consulting, operational, and professional services for every aspect of cloud technologies.

AWS Services Used

AWS Lambda

Run code without provisioning or managing servers, creating workload-aware cluster scaling logic, maintaining event integrations, or managing runtimes.

Learn more »

Amazon SageMaker

Amazon SageMaker is a unified platform for data, analytics, and AI. Bringing together widely-adopted AWS machine learning and analytics capabilities, Amazon SageMaker delivers an integrated experience for analytics and AI with unified access to all your data.

Learn more »

AWS CloudFormation

Speed up cloud provisioning with infrastructure as code with AWS CloudFormation

Learn more »

More Media & Entertainment Success Stories

Showing results: 1-4
Total results: 42

no items found 

  • Media & Entertainment

    CloudZone Streamlines and Adapts Machine Learning Model Lifecycles in the Cloud for LSports

    LSports is a sports data company that provides an innovative API for the sports betting industry, providing high-quality live sports data feeds to clients worldwide. The company had a large repository in their data warehouse and wanted to use this data to provide advanced features to their customers. AWS Partner CloudZone developed an end-to-end machine learning (ML) pipeline. It was designed and built on top of a robust ML foundational service, delivering a training pipeline that controls data preparation, model training, and model deployment for more efficient model training as well as improved performance thanks to better cloud compute power.

    2024
  • Media & Entertainment

    Dyn Media Launches to Millions of Sports Fans in One Year with AWS and Stripe

    Germany-based Dyn Media wanted to bring more choice to sports fans in Germany, Austria, and Switzerland. After acquiring the media rights to broadcast high-profile leagues, Dyn Media had one year to create a new, subscription-based, stream-ready platform. To do this—and launch smoothly—Dyn Media needed a reliable cloud platform and a robust subscription management service. By building on Amazon Web Services (AWS) and implementing solutions from AWS Partner Stripe to manage payment and billing, Dyn Media was able to scale subscribers, sell subscriptions, and manage payment as well as billing—all while providing an excellent customer experience.

    2024
  • Media & Entertainment

    AWS and Ironside Help Burn Boot Camp Build a Healthier Relationship With its Data

    Burn Boot Camp is dedicated to transforming lives through fitness. As a rapidly growing franchise with over 350 locations nationwide in over 43 US states, the company needed a better way to manage the massive amounts of data generated by its mobile app, point of sale (POS) system, and other sources. Without a centralized platform, there was a lack of trust in company data that made it difficult to leverage for critical business insights. The company worked with AWS Partner Ironside to build a solution on Amazon Web Services (AWS) that repaired the trust issues that had arisen with their prior data solutions. Burn Boot Camp’s data can now be used for reporting and analytics that drive business insights and growth.

    2024
  • Media & Entertainment

    Throwback Brands Creates a New Industry Standard with AWS and Radio.Cloud

    Throwback Brands, a radio and content production company, faced challenges with outdated technology that hindered creativity, localization, and content distribution. By collaborating with AWS Partner Radio.Cloud, Throwback Brands transformed the rendering and distribution of content and reduced processing time from 30 minutes to 90 seconds. As a result, the company can now render and distribute 600 segments daily and offer cost-effective services like real-time weather updates to more than 70 affiliates. Building on its relationship with Radio.Cloud and AWS, Throwback Brands is now helping affiliate stations migrate to Radio.Cloud.

    2024
1 11

Get Started

Organizations of all sizes across all industries are transforming their businesses and delivering on their missions every day using AWS. Contact our experts and start your own AWS journey today.