Member-only story
Effective Approaches for Time Series Anomaly Detection
In the current situation of Covid19, the whole world is experiencing unprecedented scenarios everywhere, which often everyone is terming as the “new normal”. But before becoming the “new normal”, these abnormal or anomalous outcomes can result in positive or negative impact for any organization and are important to keep track of, for formulating a long term business strategy. So, anomaly detection in every domain will be an important topic of discussion and the knowledge about the effective ways to perform anomaly detection will be an important skill to have for any Data Scientist and Data Analyst.
Before we even deep dive, we must clarify, what exactly is an anomaly? The definition of Anomaly, can vary from one domain to another. In the cover picture that we see above, the lioness is an anomaly among the herd of zebras. So, technically in a generalized way, we can say that an anomaly is an outlier data point, which does not follow the collective common pattern of the majority of the data points and hence can be easily separated or distinguished from the rest of the data.
Now, coming to the topic in scope for today, Time Series Anomaly Detection. We will talk about the what, the why and the how part of time series anomaly detection in this article. For a detailed coding walk through, please visit my website.
YouTube video recording of a session of mine on a similar topic:
** Update ** If you like this article and want to support me more for my contributions for the community, please take a look at my book “Applied Machine Learning Explainability Techniques” and this is the GitHub repository which contains many hands-on tutorials on various chapters covered in the book: https://github.com/PacktPublishing/Applied-Machine-Learning-Explainability-Techniques. If you like the tutorials presented in the GitHub repository, please do fork and star the repository to show your support for this project! Please show your support by ordering a physical copy or electronic copy of the book.
