Lessons Learned Scaling Machine Learning at Go-Jek on Google Cloud (Cloud Next ’18)

Kelvion New Plate Heat Exchanger


Go-Jek, Indonesia’s first billion-dollar startup, has seen an incredible amount of growth in both users and data over the past two years. Many of the ride-hailing company’s services are backed by machine learning models hosted on Google Cloud Platform. Models range from driver allocation, to dynamic surge pricing, to food recommendation, and process millions of bookings every day, leading to substantial increases in revenue and customer retention.

By embracing Google Cloud, Go-Jek has overcome many of the technical challenges brought on by its rapid growth. BigQuery has become the cornerstone of their data foundation, scaling seamlessly to meet their immense data storage and processing needs. Using Pub/Sub as an event stream and Dataflow for unified batch and stream processing has prevented inconsistencies in production data, while simultaneously reducing costs through intelligent resource allocation. Together, these technologies allow Go-Jek to react immediately to real world events, whether by retraining models with ML Engine, or refreshing data in a low latency data store like BigTable.

Find out how Go-Jek leverages Google Cloud and other lessons they have learned scaling machine learning.

Event schedule → http://g.co/next18

Watch more Machine Learning & AI sessions here → http://bit.ly/2zGKfcg
Next ‘18 All Sessions playlist → http://bit.ly/Allsessions

Subscribe to the Google Cloud channel! → http://bit.ly/NextSub


Duration: 44:52
Publisher: Google Cloud
You can watch this video also at the source.