Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Complete Outlier Detection Algorithms A-Z: In Data Science
Rating: 3.8 out of 5(54 ratings)
674 students

Complete Outlier Detection Algorithms A-Z: In Data Science

Outlier Detection Algorithms in Data Science, Machine Learning, Deep Learning, Data Analysis, Statistics with Python
Created bySaurav Singla
Last updated 9/2020
English

What you'll learn

  • Understand the fundamentals of Outliers
  • You will learn outlier algorithms used in Data Science, Machine Learning with Python Programming
  • You will learn both theoretical and practical knowledge, starting with basic to complex outlier algorithms
  • You will learn approaches to modelling outliers / anomaly detection
  • Determine how to apply a supervised learning algorithm to a classification problem for outlier detection
  • Apply and assess a nearest-neighbor algorithm for identifying anomalies in the absence of labels
  • Apply a supervised learning algorithm to a classification problem for anomaly and outlier detection
  • Make judgments about which methods among a diverse set work best to identify anomalies

Explore related topics

Course content

3 sections • 18 lectures • 1h 40m total length

  • Introduction of outlier7:30

    Covers importance, delete or no delete, and investigation of outliers

  • Application of outlier detection6:40

    Covers application of outlier detection in different sectors

  • Cause and impact of outlier2:36
  • Type of outliers8:42

    Covers outlier detection vs anomaly detection and novelty detection vs outlier detection and a different flavor of outliers and type of outliers

  • Methods for outlier detection3:18

    Elaborate on the methods for outlier detection

  • Outlier detection in univariate4:10

    Covers extreme value analysis of outliers with the Interquartile Range Method (IQR), Standard Deviation Method

  • Outlier detection in multivariate20:11

    Covers multivariate analysis of outliers with KNN, DBSCAN, Local Outlier Factor, Clustering Based Local Outlier Factor, Isolation Forest, Minimum Covariance Determinant, One-Class SVM, Histogram-Based Outlier Detection, Feature Bagging, Local Correlation Integral algorithms

  • Outlier detection in high dimension4:04

    Covers high dimension analysis of outliers with Angular Based Outlier Detection algorithm

  • Outlier detection in deep learning5:03

    Covers outlier detection with autoencoders algorithm

  • Best practices of outlier detection2:01

    Covers best practices of outlier detection

  • How to remove outliers?4:43

    Covers strategy in removing outliers

Requirements

  • It is assumed that you have completed and you have a solid understanding of the following topics prior to starting this course: Fundamental understanding of Linear Algebra; Understand sampling, probability theory, and probability distributions; Knowledge of descriptive and inferential statistical concepts; General understanding of machine learning techniques and best practices; Practiced understanding of Python and the packages commonly used in data science: NumPy, Pandas, Matplotlib, Scikit-learn
  • Familiarity with the Python is needed since support for Python in the tutorial is limited
  • You should be familiar with basic supervised and unsupervised learning techniques

Description

Welcome to the course "Complete Outlier Detection Algorithms A-Z: In Data Science".

This is the most comprehensive, yet straight-forward, course for the outlier detection on UDEMY!

Are you Data Scientist or Data Analyst or Financial Analyst or maybe you are interested in anomaly detection or fraud detection? The course is designed to teach you the various techniques which can be used to identify and recognize outliers in any set of data.

The process of identifying outliers has many names in Data Science and Machine learning such as outlier modeling, novelty detection, or anomaly detection. Outlier detection algorithms are useful in areas such as Machine Learning, Deep Learning, Data Science, Pattern Recognition, Data Analysis, and Statistics.

I will present to you very popular algorithms used in the industry as well as advanced methods developed in recent years, coming from Data Science. You will learn algorithms for detection outliers in Univariate space, in Low-dimensional space and also learn the innovative algorithms for detection outliers in High-dimensional space.

I am convinced that only those who are familiar with the details of the methodology and know all the stages of the calculation, can understand it in depth. Anyone who interested in programming, I developed all algorithms in PYTHON, so you can download and run them.

List of Algorithms:

  • Interquartile Range Method (IQR), Standard Deviation Method

  • KNN, DBSCAN, Local Outlier Factor, Clustering Based Local Outlier Factor, Isolation Forest, Minimum Covariance Determinant, One-Class SVM, Histogram-Based Outlier Detection, Feature Bagging, Local Correlation Integral

  • Angular Based Outlier Detection

  • Autoencoders

Why wait? Start learning today! Because Everyone, who deals with the data, needs to know ‘Complete Outlier Detection Algorithms A-Z: In Data Science’, a necessity to recognize fraudulent transactions in the data set. No matter what you need outlier detection for, this course brings you both theoretical and practical knowledge, starting with basic and advancing to more complex algorithms. You can even hone your programming skills because all algorithms you will learn have an implementation in PYTHON. You will learn how to examine data with the goal of detecting anomalies or abnormal instances or outlier data points.

For the code explained in the tutorials, you can find a GitHub repository hyperlink.

At the end of this course, you will have understood the different aspects that affect how this problem can be formulated, the techniques applicable for each formulation, and knowledge of some real-world applications in which they are most effective.

Who this course is for:

  • Data Scientist or Data Analyst or Financial Analyst or Business Analyst or Software Engineers or Technical Managers
  • People interested in outlier detection, anomality detection, fraud detection, unseen pattern in data
  • People who want a career in Data Science or Data Analytics
  • This course targets existing data science practitioners that have expertise building machine learning models, who want to deepen their skills on outlier detection and anomality detection

Report abuse