May 2nd, 2019

Hortifrut uses AI to Determine the Freshness of Blueberries

Category: Community, Customer, Data Science, Driverless AI, Manufacturing, Use Cases

Who doesn’t love sweet, delicious blueberries?

Providing a steady supply of beautiful, tasty berries to the market is no small effort and Hortifrut, based in Chile, has been growing and distributing berries for the last 30 years. Today, they are using AI to provide fresh berries to the world everyday.

Hortifrut, the largest global producer and distributor of blueberries requires a large worldwide network of farms and a flexible and reliable supply chain that can deliver fresh berries all year. As both the grower and the supplier, Hortifrut wanted to better understand how to deliver the highest quality of fruit at the final destination. In other words, prior to shipping, Hortifrut wanted to predict freshness or spoilage upon receipt at the final destination. They wanted to save on shipping costs and resulting claims if models predicted that the fruit based on a set of variables including the varietal, the weather, the shipping container, the method of shipping, etc determined that the quality was poor upon arrival.

By using H2O Driverless AI, the data scientists at Hortifrut devised ways to predict product yield upon delivery using data about the berry combined with shipment method and time. “Data about the specific varietal and field that produced it are important to understanding how the berries will fair in transit,” explains Wei Shao, data scientist, Hortifrut.

“We are building hundreds of models to ensure a quality product arrives at its destination. H2O Driverless AI is and will be instrumental in saving Hortifrut time and costs associated with growing and shipping quality blueberries to all points of the world,” explains Gonzalo Bustos, head of data analytics at Hortifrut. “We are getting great results with H2O Driverless AI. What once took us 3 to 5 months using traditional data science methods, can now be done in 3 to 5 weeks without having to add any additional data scientists to the team.”

Specifically, Hortifrut uses Driverless AI to be able to scale their data science efforts and improve their ability to predict the quality of blueberries based on information such as variety, farm origin, packaging, shipping time and vessel. Hortifrut is also using Driverless AI to predict future production of the blueberries dependent on the origin, weather, variety, and more.

Who knew that sweet juicy blueberry you had for breakfast is the result of data scientists at a Chilean company using AI to predict the quality and best delivery of their fruit. This is just one example of how Driverless AI is helping to improve business outcomes. Better blueberries mean better business.

 

 

 

 

 

About the Author

Ingrid Burton
Ingrid Burton

Ingrid Burton is CMO at H2O.ai, the open source leader in AI. She has several decades of experience leading global marketing teams to build brands, create demand, and engage and grow communities. She also serves as an independent director on the Aerohive board. Prior to H2O.ai she was CMO at Hortonworks, where she drove a brand and marketing transformation, and created ecosystem programs that positioned the company for growth. At SAP she co-created the Cloud strategy, led SAP HANA and Analytics marketing, and drove developer outreach. She also served as CMO at Silver Spring Networks and Plantronics after spending almost 20 years at Sun Microsystems, where she was head of Sun marketing, led Java marketing to build out a thriving Java developer community, championed and led open source initiatives, and drove various product and strategic initiatives. A developer early in her career, Ingrid holds a BA in Math with a concentration in Computer Science from San Jose State University.

Leave a Reply

H2O.ai Automatic Machine Learning on Red Hat OpenShift Container Platform Delivers Data Science Ease and Flexibility at Scale

Last week at Red Hat Summit in Boston, Sri Ambati, CEO and Founder, demonstrated how

May 14, 2019 - by Vinod Iyengar
6 Tips to Having it All

I posted this blog on Medium two years ago, thought I'd share a slight rework

May 12, 2019 - by Ingrid Burton
AI/ML Projects — Don’t get stymied in the last mile

Data Scientists build AI/ML models from data, and then deploy it to production – in

May 3, 2019 - by Karthik Guruswamy
Fallback Featured Image
Can Your Machine Learning Model Be Hacked?!

I recently published a longer piece on security vulnerabilities and potential defenses for machine learning

May 2, 2019 - by Patrick Hall
Fallback Featured Image
H2O Driverless AI Updates

We are excited to announce the new release of H2O Driverless AI with lots of improved

April 25, 2019 - by Venkatesh Yadav, VP Customer Success
Fallback Featured Image
H2O World Explainable Machine Learning Discussions Recap

Earlier this year, in the lead up to and during H2O World, I was lucky

April 16, 2019 - by Patrick Hall and Navdeep Gill

Join the AI Revolution

Subscribe, read the documentation, download or contact us.

Subscribe to the Newsletter

Start Your 21-Day Free Trial Today

Get It Now
Desktop img