Anomaly detection (or Outlier analysis) is the identification of items, events or observations which do not conform to an expected pattern or other items in a dataset. It is used is applications such as intrusion detection, fraud detection, fault detection and monitoring processes in various domains including energy, healthcare and finance.
In this workshop, we will discuss the core techniques in anomaly detection and discuss advances in Big Data and Deep Learning in this field.
Through case studies, we will discuss how anomaly detection techniques could be applied to various business problems including stock data analysis, fraud detection, credi risk etc.. We will also demonstrate, using R, Python, Apache Spark, Keras and Tensorflow applications to help reinforce concepts in anomaly detection and best practices in analyzing and reviewing results.
What you will learn
In this workshop, you will learn the core techniques used in Anomaly detection. Through examples in R, Python and Apache Spark,Keras and Tensorflow you will learn how to methodically apply various anomaly techniques. In addition, you will learn
- Exploratory data analysis techniques
- Statistical and Density based approaches
- Machine learning techniques for Anomaly detection
- Anomaly and Fraud Detection for Time Series Datasets
- Large scale anomaly detection using Apache Spark
- Using Autoencoders for anomaly detection with Keras and Tensorflow
- Practical Case studies with fully functional code
Data science techniques using supervised and unsupervised machine learning techniques are becoming increasing popular in identifying patterns in data and to build systems that can better predict the future. With increase in volume, variety and velocity of data, many big data techniques are being used to scale these techniques today.
However, Anomaly detection techniques focus on detecting the asymetric outliers in the data sets. Many techniques are used for anomaly detection and a comprehensive understanding of these techniques would help get a better understanding of the nature of the data and to detect and act upon these outliers.
In this workshop, we will discuss the various anomaly detection techniques that are practiced in the industry. Through practical case-studies, we will discuss how these techniques can be used to identify anomolies in cross-sectional and time-series datasets. Using Apache Spark, we will also illustrate how these techniques could be scaled to address the big data challenges in the enterprise.
In module one, we will review the core techniques in anomaly detection. Through examples we will understand the different outlier detection techniques and review evaluation criteria
- Anomaly Detection: An introduction
- Graphical and Exploratory analysis techniques
- Statistical techniques in Anomaly Detection
- Machine learning methods for Outlier analysis
- Evaluating performance in Anomaly detection techniques
- Case study 1: Anomalies in Freddie mac mortgage data
- Case study 2: Detecting anomalies in time series data
In module two, we will discuss advanced techniques in anomaly detection and use Apache Spark for anomaly detection. We will also discuss best practices in scaling and using anomaly detection techniques.
- Anomaly Detection: Advanced techniques
- Looking for anomolies in large and complex data sets
- Apache Spark: A brief introduction
- Anomaly Detection and Fraud Detection in Temporal datasets
- Case study 3: Using Apache Spark for Anomaly detection
- Deep Learning techniques in Anomaly detection
- Case study 4: Auto-encoder based Anomaly Detection for Credit risk with Keras and Tensorflow
SAMPLE FREE LECTURE
Past Attendees of QuantUniversity workshops include Assette, Baruch College, Bentley College, Bloomberg, BNY Mellon, Boston University, Datacamp, Fidelity, Ford, Goldman Sachs, IBM, J.P. Morgan Chase, MathWorks, Matrix IFS, MIT Lincoln Labs, Morgan Stanley, Nataxis Global, Northeastern University, NYU, Pan Agora, Philips Health, Stevens Institute, T.D. Securities and many more..