Scaling Ride-Hailing with Machine Learning on MLflow - Databricks

Scaling Ride-Hailing with Machine Learning on MLflow

Download Slides

“GOJEK, the Southeast Asian super-app, has seen an explosive growth in both users and data over the past three years. Today the technology startup uses big data powered machine learning to inform decision-making in its ride-hailing, lifestyle, logistics, food delivery, and payment products. From selecting the right driver to dispatch, to dynamically setting prices, to serving food recommendations, to forecasting real-world events. Hundreds of millions of orders per month, across 18 products, are all driven by machine learning.

Building production grade machine learning systems at GOJEK wasn’t always easy. Data processing and machine learning pipelines were brittle, long running, and had low reproducibility. Models and experiments were difficult to track, which led to downstream problems in production during serving and model evaluation. In this talk we will cover these and other challenges that we faced while trying to scale end-to-end machine learning systems at GOJEK. We will then introduce MLflow and explore the key features that make it useful as part of an ML platform. Finally, we will show how introducing MLflow into the ML life cycle has helped to solve many of the problems we faced while scaling machine learning at GOJEK.

« back
About Willem Pienaar

Willem leads the Data Science Platform Team at GOJEK, the Southeast Asian super app. His main focus areas are building data and ML platforms, allowing organizations to scale machine learning and drive decision making. The GOJEK ML platform supports a wide variety of models that handle hundreds of million of orders every month. Models include recommendation systems, driver allocation, forecasting, anomaly detection, mapping, and more. In a previous life founded and sold a networking startup, and also worked as a control systems engineer in heavy industry.

About Md Jawad

Jawad is Senior Data Scientist at GOJEK, where he focuses on solving mission critical transportation and pricing problems for Southeast Asian markets. Jawad has wide ranging experiences in financial and telecommunication sectors in the past. His academic work involves using simulation and data science tools to model construction workers' safety and productivity. Jawad holds a masters in Intelligent Systems Design from the National University of Singapore.