Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore data-efficient solutions for making robust business decisions with sparse data in this conference talk from ODSC Europe 2019. Delve into real-world examples from supply chain management, addressing challenges such as forecasting quantities with mismatched input and prediction data types. Learn about applying VUKU to complex, dynamic systems with limited available data. Gain insights into moving from data deficit to data deluge, understanding Gaussian processes, and certifying uncertainty. Discover why uncertainty should be viewed as a feature rather than a bug, and examine the concept of robust decision-making through objective functions and maximum reward. Investigate the Problem of Pallets and the speaker's approach to solving it. Bridge the gap between research, software engineering, and product teams in data science applications.
Syllabus
Intro
Moving from a data deficit to a data deluge
Challenge #1
Gaussian processes
Certifying uncertainty
Uncertainty is a feature, not a bug
What is a robust decision?
Objective function, maximum reward
The Problem of Pallets
Our approach
Taught by
Open Data Science