Become a Data Science Superhero

Follow the path of Nathan from Symphony Post Acute Network
Nathan Patrick Taylor
Nathan Patrick Taylor
Data Science Superhero at Symphony Post Acute Network

Data Scientist Nathan Patrick Taylor worked tirelessly, building model after model to improve the lives of healthcare patients.

Nathan is a Data Scientist with years of experience in healthcare analytics. With an in-depth knowledge of healthcare informatics and health insurance, he also understands how to optimize legacy processes that link the old world to the new - Nathan is extremely savvy when it comes to applying machine learning to healthcare.

Like any good Data Scientist, Nathan uses data to complete previously impossible tasks. For example, he builds models that predict which patients are likely to fall after their care ends, or might develop infections, allowing Symphony to head off complications before they happen. Nathan’s deep insights help Symphony provide the best level of care to their patients while reducing overall healthcare costs.


Prior to DataRobot, the machines were holding Nathan back.

However traditional modeling methods prevented Nathan from attacking as many predictive challenges as he would like.

Manually building predictive models was time-consuming, resulting in persistent issues, such as:

  • Lengthy trial and error testing with each model update
  • Difficulty keeping up with the latest open-source machine learning algorithms
  • Introducing the possibility of coding errors when deploying models to production
  • An inability to address all of the requests for modeling projects from other groups at Symphony

This manual process seemed flawed to Nathan. Surely these problems could be solved with technology?

Data Science Superhero Reference Card
See How Data Science Superheroes Differ from Mere Mortals!
Traits & Capabilities
Traits & Capabilities Data Scientist Mortal Data Scientist Superhero
Enterprise Readiness
Bottom Line Business Impact
Bottom Line Business Impact $100K+ per year $M's+ / Year
Model Engine Tested
Model Engine Tested No 200,000,000+ times
Model Sharing
Model Sharing No Yes
Enterprise Readiness
Enterprise Readiness Manual Automatic
Security Manual Automatic
Standardization When there's time Every time
Multitasking Single model Multiple models
Package installation and dependency management
Package installation and dependency management Manual Not needed
Risk of coding errors
Risk of coding errors Substantial None
Model Accessibility
Popularity with business users
Popularity with business users
 Somewhat Very
Business user engagement
Business user engagement
 Too busy Always available

Helped with guardrails
Helped with guardrails None Yes
Skills Needed
Skills Needed Significant - PhD-level
 PhD not required
Model Operationalizing
Model deployment effort
Model deployment effort Significant Effortless
Model Quality
Model iteration
Model iteration
 Manual & slow Automated
Accuracy Time consuming Guaranteed
Helped by other Data Scientists
Helped by other Data Scientists No 85+
Workflow Manual Automatic
Tuning Manual Automatic
Ensembled models
Ensembled models Manual Automatic
Algorithms and libraries
Algorithms and libraries A comfortable few Many
Feature engineering
Feature engineering
 Manual Automatic

Model Quantity
Number of models / month
Number of models / month
 Very Few
Speed Sometimes Blisteringly Fast
Model Transparency
Model Transparency
Model Transparency None X-Ray Vision
Explainable Models
Explainable Models
 'Black Box'

After years of being hampered by manual processes, Nathan yearned for a better way. In 2016, he activated the distress signal that summoned DataRobot.

After seeing a DataRobot demo, Nathan realized he found the answer to his technology challenges. Seamless integration with Alteryx, and the ability to connect to historical data in lots of different ways, removed any doubt and sealed the deal. He became an official DataRobot user in December 2016 — and by pushing productivity through the roof, he became a Data Science Superhero!

The DataRobot machine learning automation platform captures the knowledge, experience and best practices of the world’s leading data scientists to deliver unmatched levels of automation and ease-of-use for Symphony’s machine learning initiatives. DataRobot enables Nathan to build and deploy highly accurate machine learning models in a fraction of the time he spent with traditional, manual modeling methods.

DR Superhero Uncovers

With DataRobot at his side, Nathan is driving a far more ambitious predictive analytics agenda at Symphony Post Acute Network. He now:

  • Quickly builds predictive models in hours or days (instead of weeks)
  • Deploys models through an easy-to-use, enterprise-ready deployment API
  • Delivers more accurate results that drive cost savings and generate revenue, while offering the transparency to explain these models to his colleagues

Next steps for Nathan? He’s going to tackle even bigger challenges,

like lowering malpractice insurance rates to help lower healthcare costs and helping to prevent opioid addictions for patients who require painkillers. By delivering better predictions for Symphony, Nathan is impacting the company’s bottom line performance — and boosting his reputation in the process. Best of all, with DataRobot, Nathan has achieved his personal goal of leveraging machine learning to solve problems that affect real people and improve their lives!

DR Superhero
DR Logo

“DataRobot’s platform makes my work exciting, my job fun, and the results more accurate and timely — it’s almost like magic.”

Nathan Patrick Taylor VP Analytics Strategy, Symphony Post Acute Network

Want to become a Data Science Superhero like Nathan?

Educate Yourself

Educate Yourself

Attend DataRobot University
See Automated Machine Learning in Action

See Machine Learning Automation in Action

Join a live Webinar
Find out how DataRobot can help meet your unique requirements

Find out how DataRobot can help meet your unique requirements

Request a demo