Singapore Machine Learning Season 1 Episode 1
09.05.2023 - Singapore Machine Learning - ~4 Minutes
When?
- Tuesday, May 9, 2023 from 7:00 PM to 10:00 PM (Singapore Time)
Where?
- In-person event: DataRobot, 11th Floor, 11-01, 5 Temasek Boulevard, Suntec Tower 5, Singapore.
The page of the event on Meetup: SGML S1E1
Data science in Football: from Hoax to Game Changer
Abstract: How did football data science start as a hoax and in recent years become the literal “game changer”?
- History of data science in football – where it started, how it evolved.
- Current development directions of data science in football – how do players, coaches, teams, clubs and fans use analytic in different areas?
- Observations from this history – how is data science and machine learning being industrialized?
- Lesson learned – how to take the lead in the game?
Bio: Dean is a data scientist based out of Singapore. He obtained his PhD in operation research in Nanyang Technology and has been working in the field of advanced analytic, data science, machine learning and artificial intelligence (in this order). He used to played R&D roles in Apple and SAP, before joining McKinsey & Co as a consultant. He transitioned from a developer to AI delivery lead in his subsequent stint in QuantumBlack, Google and DataRobot. He is currently the lead data scientist in DataRobot. Dean enjoys solving data related business problem in various industries. He has experience across telecommunication, banking, retail, manufacturing, mining, oil&gas and sports. He also has 7 patents for data/analytics related solutions. In his spare time, he enjoys watching and playing football – which explains the topic of this talk.
Feature Ideation
Abstract: Data is a finite resource, and you want to get the most out of it. So feature engineering becomes vital for machine learning success. Yet we often lose important signals in our data when our data extracts are limited to the same old boring COUNT and SUM aggregations. We propose a new approach to feature engineering ideation, based upon a structure using data semantics and signal types, yet with the freedom to apply domain knowledge.
Bio: Colin Priest is the Chief Evangelist at FeatureByte. He is a seasoned business leader with more than 30 years of experience across various industries, including finance, healthcare, security, oil and gas, government, telecommunications, and marketing. With a focus on data science initiatives, he has held several CEO and general management roles, while also serving as a business consultant, data scientist, thought leader, behavioral scientist, and educator. Colin’s passion for exploring the synergy between humans and AI has led him to contribute to projects on AI ethics, governance, and the future of work. He has gained global recognition from the World Economic Forum and Singapore government for his work on AI governance and ethics. Additionally, Colin is a passionate healthcare advocate who does pro-bono work for cancer research.
Transforming Feature Ideas into Machine Learning Inputs
Abstract: We will explore how to transform feature ideas into valuable inputs for Machine Learning using FeatureByte’s free and source available platform. FeatureByte’s versatile declarative framework allows for seamless translation of feature concepts into a logical plan, regardless of your data platform. We will discuss the five distinct ways features can be declared within the framework: Lookup Features, Aggregate Features, Cross Aggregate Features, Feature Transforms, and Feature Aggregations. Through concrete examples using a grocery dataset, we will demonstrate how to declare features effectively. We will show that by associating features with a logical plan, they can be effortlessly materialized as modeling and prediction data, capitalizing on your data warehouse capabilities without the need to move data.
Bio: Xavier’s vision for FeatureByte is to simplify and democratize feature engineering for every data scientist. Xavier’s passion for data spans 25 years, first as an actuary in the Insurance industry, and then as a visionary Data Scientist, including being the top ranked (#1) on Kaggle. Prior to starting FeatureByte, Xavier was the Chief Data Scientist of DataRobot. He built a world-class R&D data science team from day one, and was responsible for the ideation and execution of the Data Science roadmap.