Your First Machine Learning Project - Crash Course - Why mahalanobis distance is incredibly powerful for outlier detection

Welcome to the thirteenth video of the series "Build your First Machine Learning Project". In this, we'll see how to detect Multi variate outliers with Mahalanobis Distance. Notebook link: https://github.com/machinelearningplus/Build-Your-First-ML-Project/tree/main/13b_Mahalanobis%20Distance%20for%20Multivariate%20Outlier%20Detection The Mahalanobis distance is one of the most powerful distance measures in multivariate statistics. It can be used to determine whether a sample is an outlier, whether a process is in control or whether a sample is a member of a group or not. So let's understand it. Chapters 0:00 Intro 2:42 What is Mahalanobis Distance 4:22 Difference between Euclidean and Mahalanobis Distance 8:02 Formula behind Mahalanobis Distance 12:11 Code behind Mahalanobis Distance In order to make the best out of this, please watch this series in the order in playlist: Build Your First ML Model Playlist: https://www.youtube.com/watch?v=KSsjPbowHQ0&list=PLFAYD0dt5xCymcvacfR4CLB9Pk_9L50gz Previous Lesson: How to Detect Outliers with Z Score : https://youtu.be/Qv2vCviL4iU Earlier Lessons: 1. Build your first ML Project: https://youtu.be/KSsjPbowHQ0 2. How to Formulate ML Problem: https://youtu.be/ygayqatDEDk 3. Setup Python Environment: https://youtu.be/Yk9BFMO6QXE 4. Jupyter Notebook Tutorial: https://youtu.be/4yuo96HtTw8 5. What is ML Modeling: https://youtu.be/Bcfk4HKgC5E 6. Reduce the size of Pandas Dataframe: https://youtu.be/Xa26NB75htg 7. What is EDA: https://youtu.be/rqCZZBrfNak 8. How to impute missing Data: https://youtu.be/Qir0Qi_CD2o 9. Mice Imputation Algorithm: https://youtu.be/BjyUbk258o4 10. How to impute missing data in categorical Variables: https://youtu.be/dm7YNsN_Nwo 11. Detect Outliers with IQR and Boxplot?: https://youtu.be/xiBslXuZ0Rw Let me know in the comments section if you have any questions! If you enjoyed this video, be sure to throw it a like and make sure to subscribe to not miss any future videos! Thanks for watching! #mlmodeling, #python, #machinelearning, #artificialintelligence, #pandas, #datascience