Seldon Case Studies How Exscientia reduced the time it takes to monitor and prepare models from days to hours

Edit This Case Study Record

	How Exscientia reduced the time it takes to monitor and prepare models from days to hours Seldon

How Exscientia reduced the time it takes to monitor and prepare models from days to hours

Seldon

Technology Category	Analytics & Modeling - Machine Learning Application Infrastructure & Middleware - API Integration & Management
Applicable Industries	Healthcare & Hospitals Pharmaceuticals
Applicable Functions	Product Research & Development
Use Cases	Machine Condition Monitoring Predictive Quality Analytics
Services	Data Science Services System Integration
Challenge	Exscientia plc is an AI-powered drug discovery organization that relies heavily on the accuracy and stability of its models. The company's model deployment process is unique as it is entirely automated, resulting in thousands of models being delivered, monitored, and retrained without human interaction. However, as Exscientia expanded its reach and goals, it needed an enterprise-grade scale solution. The team was looking for additional operational efficiencies and other ways to debug and stabilize models. The existing open-source deployment solution and inference platform were no longer sufficient for their growing needs. Read More
About Customer	Exscientia plc is an AI-powered drug discovery organization. The company's mission is to design and develop novel, precision-engineered drugs with an improved probability of clinical success for the benefit of patients. AI is at the heart of their business and is the determining factor in the success or failure of projects. The company has grown and expanded its reach and goals, necessitating the need for enterprise-grade scale solutions. The company's unique model deployment process is entirely automated, resulting in thousands of models being delivered, monitored, and retrained without human interaction. Read More
Solution	Exscientia decided to implement Seldon Deploy to assist with monitoring and managing models in production, enabling them to scale and speed up the debugging process. The team had to decide whether to change their model code when moving to a new MLOps platform. Changing the code could have slowed down the entire project, so they decided to keep the same code and port over all their existing models. One of the benefits of implementing Seldon was that the code didn't matter to Seldon, and they were able to fit the architecture to the model code. This decision saved a lot of time and allowed Exscientia to maintain the stability and reliability of the many models now in production. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Application Infrastructure & Middleware - API Integration & Management

Applicable Industries

Healthcare & Hospitals

Pharmaceuticals

Applicable Functions

Product Research & Development

Use Cases

Machine Condition Monitoring

Predictive Quality Analytics

Services

Data Science Services

System Integration

Challenge

Exscientia plc is an AI-powered drug discovery organization that relies heavily on the accuracy and stability of its models. The company's model deployment process is unique as it is entirely automated, resulting in thousands of models being delivered, monitored, and retrained without human interaction. However, as Exscientia expanded its reach and goals, it needed an enterprise-grade scale solution. The team was looking for additional operational efficiencies and other ways to debug and stabilize models. The existing open-source deployment solution and inference platform were no longer sufficient for their growing needs.

About Customer

Exscientia plc is an AI-powered drug discovery organization. The company's mission is to design and develop novel, precision-engineered drugs with an improved probability of clinical success for the benefit of patients. AI is at the heart of their business and is the determining factor in the success or failure of projects. The company has grown and expanded its reach and goals, necessitating the need for enterprise-grade scale solutions. The company's unique model deployment process is entirely automated, resulting in thousands of models being delivered, monitored, and retrained without human interaction.

Solution

Exscientia decided to implement Seldon Deploy to assist with monitoring and managing models in production, enabling them to scale and speed up the debugging process. The team had to decide whether to change their model code when moving to a new MLOps platform. Changing the code could have slowed down the entire project, so they decided to keep the same code and port over all their existing models. One of the benefits of implementing Seldon was that the code didn't matter to Seldon, and they were able to fit the architecture to the model code. This decision saved a lot of time and allowed Exscientia to maintain the stability and reliability of the many models now in production.

Impact #1	With Seldon Deploy now in play, Exscientia has reduced the time to debug and resolve a trivial issue from hours to minutes.
Impact #2	A serious issue can now be resolved anywhere from 24 hours up to just an hour on average.
Impact #3	The impact doesn't just stop at the Data Science and Machine Learning teams. Drug chemists can now make decisions in the design cycle much faster.

Impact #1

With Seldon Deploy now in play, Exscientia has reduced the time to debug and resolve a trivial issue from hours to minutes.

Impact #2

A serious issue can now be resolved anywhere from 24 hours up to just an hour on average.

Impact #3

The impact doesn't just stop at the Data Science and Machine Learning teams. Drug chemists can now make decisions in the design cycle much faster.

Benefit #1	Reduced the time to debug and resolve a trivial issue from hours to minutes.
Benefit #2	Reduced the time to resolve a serious issue from 24 hours to just an hour on average.
Benefit #3	Accelerated decision-making in the design cycle for drug chemists.

Benefit #1

Reduced the time to debug and resolve a trivial issue from hours to minutes.

Benefit #2

Reduced the time to resolve a serious issue from 24 hours to just an hour on average.

Benefit #3

Accelerated decision-making in the design cycle for drug chemists.

Download PDF Version

Overview

How Exscientia reduced the time it takes to monitor and prepare models from days to hours

Operational Impact

Quantitative Benefit