OML Usage Highlight: ML on SailGP data: Predicting the best sailing direction
Join us on this Office Hours for Oracle Machine Learning on Autonomous Database, where Jeroen Kloosterman, Product Strategy Director for Analytics and AI in Oracle Digital in EMEA, will show how to use machine learning to solve a very common challenge in sailing: finding the best direction to sail. Using OML, he will identify the optimal angle to the wind that a SailGP boat must sail to obtain the highest boat speed in the target direction, given a particular wind speed. He will then visualize the results using Oracle Analytics Cloud.
SailGP is like Formula 1 on the water: the boats race over the water at speeds of up to 50 knots (60 m/h, 90 km/h). SailGP offers the perfect playground for you to learn about analytics and Machine Learning. Why? It’s a data intensive sport; each boat has over 800 IoT sensors that provide more than 12,000 data points. To deliver game-changing insights from the data, SailGP employs “Data Athletes” who analyse all this data to help the teams make the best decisions on the water and stay ahead of the game.
The Oracle Machine Learning product family supports data scientists, analysts, developers, and IT to achieve data science project goals faster while taking full advantage of the Oracle platform.
The Oracle Machine Learning Notebooks offers an easy-to-use, interactive, multi-user, collaborative interface based on Apache Zeppelin notebook technology, and support SQL, PL/SQL, Python and Markdown interpreters. It is available on all Autonomous Database versions and Tiers, including the always-free editions.
OML includes AutoML, which provides automated machine learning algorithm features for algorithm selection, feature selection and model tuning, in addition to a specialized AutoML UI exclusive to the Autonomous Database.
OML Services is also included in Autonomous Database, where you can deploy and manage native in-database OML models as well as ONNX ML models (for classification and regression) built using third-party engines, and can also invoke cognitive text analytics.
Video Highlights
00:55 Topics for today
01:31 Announcing OML4Py is now available for Oracle Database 21c on Linux
02:28 ML on SailGP data: Predicting the best sailing direction
04:41 Video highlight: What is SailGP is and their use of the Oracle Cloud
05:42 What is SailGP?
07:58 Products used in the project
09:57 What's in the workshop?
13:08 Definition of the problem to solve
15:22 Definition of "foiling"
16:44 Wind Angle vs Boat Speed
18:42 How to find Wind Angle and Wind Speed for best Boat Speed
19:24 Machine Learning for Predicting Boat Speed
20:58 Overview of the Architecture with Oracle products
21:51 Demo description
22:30 Demo: Explore data in Oracle Analytics Cloud
26:05 Demo: Build machine learning model in Oracle Machine Learning (AutoML UI)
27:10 Request predictions directly from Oracle Analytics Cloud
29:51 Visualize the results in Oracle Analytics Cloud
35:04 Try it yourself! Workshop
35:40 Q&A