Pachyderm > Case Studies > Epona Science: Revolutionizing Horse Racing with Pachyderm

Epona Science: Revolutionizing Horse Racing with Pachyderm

Pachyderm Logo
Product
  • Pachyderm
Tech Stack
  • Python
  • Docker
  • Kubernetes
Implementation Scale
  • Enterprise-wide Deployment
Impact Metrics
  • Innovation Output
  • Productivity Improvements
Technology Category
  • Analytics & Modeling - Machine Learning
  • Platform as a Service (PaaS) - Data Management Platforms
Applicable Industries
  • Agriculture
Applicable Functions
  • Product Research & Development
  • Quality Assurance
Use Cases
  • Machine Condition Monitoring
  • Predictive Maintenance
Services
  • Data Science Services
  • System Integration
About The Customer
Epona Science is a company that specializes in the horse racing industry. They focus on buying, breeding, and identifying the best racehorses in the world. With every thoroughbred being a multi-million dollar investment, the stakes are high. Epona Science aims to revolutionize the traditional horse racing industry by using machine learning, statistical analysis, and science. They believe that factors such as the horse's entire genetic profile and lineage, its height and gait, and even the size of its heart can make a significant difference in its performance. Epona Science is committed to providing buyers and breeders with the best information possible to give them an edge in picking the next legendary champion.
The Challenge
Epona Science is a company that specializes in buying, breeding, and identifying the best racehorses in the world. The racehorse business is a traditional industry where buyers often rely on pedigree or trusted breeders' instincts to choose horses. However, Epona Science believes that these are not the best predictors of success. They aim to revolutionize the industry by using machine learning, statistical analysis, and science. They have discovered that factors such as the horse's entire genetic profile and lineage, its height and gait, and even the size of its heart can make a significant difference in its performance. However, gathering all this data, cleaning it, standardizing it, and getting it into a consistent format that their machine learning models can train on is a significant challenge. The data comes from various sources worldwide, including x-rays, genetic profiles, and track records from previous races.
The Solution
Epona Science chose Pachyderm to help them deal with their data challenges. Pachyderm stood out for its ability to handle everything from data lineage, data transformation and versioning, to containerization. The platform's versioning and provenance tools allow Epona's team to roll backwards and forwards, looking at what changed, when, and why. This is crucial for their sensitive models, as they often need to conduct a detailed forensic analysis to figure out where the model went wrong so they can fix it quickly. Pachyderm also offers more flexibility than alternatives like Airflow, which are more rigid and not designed for Kubernetes first. The platform allows Epona to easily string together a series of independent and isolated tools into a smooth pipeline. This has changed the way they do business, as they had to run everything in isolation in the past. Now, their model development throughput is effectively continuous. Every single model they have and every sample, especially genetics samples, runs through the pipeline, gets tested, and uploaded to the website in minutes.
Operational Impact
  • Epona Science's model development throughput is now effectively continuous. Every single model they have and every sample, especially genetics samples, runs through the pipeline, gets tested, and uploaded to the website in minutes.
  • In 2020, they processed 10,000 new photos in a month, a significant increase from the previous year when it took a year to process that many pictures.
  • With autoscaling, they can leave a cluster on stand up and build it up as needed. They no longer need to launch a mega instance, run the job, debug it, and remember to turn it down.
Quantitative Benefit
  • Increased model development throughput to effectively continuous.
  • Processed 10,000 new photos in a month in 2020, compared to a year for the same number of pictures in the previous year.
  • Significant cost savings through autoscaling, eliminating the need for launching and maintaining a mega instance.

Case Study missing?

Start adding your own!

Register with your work email and create a new case study profile for your business.

Add New Record

Related Case Studies.

Contact us

Let's talk!
* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.