2023-08-16 –, HS 120
From sensor data to epidemic outbreaks, particle dynamics to environmental monitoring, much of crucial real world data has temporal nature. Fundamental challenges facing data specialist dealing with time series include not only predicting the future values, but also determining when these values are alarming. Standard anomaly detection algorithms and common rule-based heuristics often fall short in addressing this problem effectively. In this talk, we will closely examine this domain, exploring its unique characteristics and challenges. You will learn to apply some of the most promising techniques for detecting time series anomalies as well as relevant scientific Python tools that can help you with it.
This talk will walk you through several most common and effective approaches for tackling anomaly detection in time series, while explaining why traditional anomaly detection techniques might not be very applicable here. Among these approaches we will discuss rule-based anomaly detection, Error-Trend-Seasonality decomposition, structural modelling approach, and short-term forecasting model solutions. Each time we will differentiate between different types of temporal anomalies and why each method may or may not be suited for them. Further, for each approach we will consider several open-source scientific Python tools such as scipy, statsmodels, Prophet, tensorflow / keras and more. At the center of our conversation will be a real-world dataset from the field of environmental monitoring, which can also be easily translated into other fields.
This talk will introduce you to Anomaly Detection in Time Series, from why this field is unique to how to applying some of the most promising detection techniques and which scientific Python tools can help you with that
Category [Data Science and Visualization] –Data Analysis and Data Engineering
Expected audience expertise: Domain –some
Expected audience expertise: Python –some
Vadim Nelidov is a Lead Data Science consultant at Xebia Data with diverse data & research experience in a variety of industries from energy sector to skincare and agriculture. He also has a research background in decision making sciences as well as several publications in this domain. Throughout his years in the data world, Vadim has been combining advanced data science with practical insights to make data work with an impact for the world. He aspires to see far beyond what is on the surface and get to the essence of the problems.
Vadim is passionate about sharing his knowledge and insights, believing that Data literacy should not be a privilege of a few. And his goal is to be there to make this a reality. Making the intricacies of data science intelligible and uncovering the regularities hiding in the data is a major source of inspiration for Vadim. With this goal in mind, he combines his years of experience in consulting with his background in statistics, research and teaching to make this knowledge accessible to businesses and individuals in need.