Approaches to fraud and anomaly detection: Autoencoder and Isolation Forest

Channel	Publish Date	Thumbnail & View Count	Download Video
	Publish Date not found	0 Views	View on YouTube Download Video

An overview of fraud and anomaly detection via autoencoders and isolation forest.

"Experts estimate the federal government's losses from potential fraud at nearly $150 billion," and new data shows that the Federal Trade Commission received 2.8 million fraud reports from consumers in 2021. In this webinar, we want to demonstrate how to fight fraud with KNIME, a free low-code tool that can detect fraud and anomalies without a single line of code or fragile if-then rules!

In the first part of this webinar, we will work with labeled data to perform classical machine learning approaches to fraud detection such as the Random Forest. Then we will cover a deep learning technique, the Autoencoder, to find fraudulent data points.

In the second part of the webinar, we will focus on data without labels of fraudulent activity using visualizations, classical statistics and machine learning. You will learn how easy it is to create multiple visualizations, perform statistical analysis and use two machine learning algorithms – Isolation Forest and DBSCAN – to detect fraudulent activity in the free, open-source analytics platform KNIME.

In this session you will learn:
– How to detect fraud using various techniques such as visualizations, statistics and machine learning
– How to use machine learning and deep learning algorithms to detect fraud, regardless of whether you have labeled data or not

Table of contents:
00:00 Introduction
01:29 KNIME Analytics Platform
02:51 KNIME nodes and workflow
04:24 Objectives for the session
05:29 Fraud is all around us
07:07 Potentially fraudulent data
07:38 Fraudulent data could be flagged
09:14 Decision tree
11:53 Random Forest
16:05 Advanced: Sampling Strategies
17:58 Fraud detection through deep learning
19:59 A neural autoencoder in KNIME
20:55 Walk through the process of completing the same task with unlabeled data (Jinwei)
21:27 Fraud and outlier detection
25:01 Finding outliers: statistics
30:43 Demo IQR and Z-Score implementation in KNIME
34:59 DBSCAN
38:20 Summary
38:46 Useful links on the topic of fraud
39:01 Useful KNIME related links
40:06 Questions and answers

You can find more exciting community lectures with renowned speakers in this playlist: https://youtube.com/playlist?list=PL8eNk_zTBST-EBv2LDSW9Wx_V4Gy5OPFT

For more advanced machine learning tutorials, check out this exclusive playlist: https://youtube.com/playlist?list=PL8eNk_zTBST_SS_czCz6Do1yrUowhKBHI

—

At Data Science Dojo, we believe that data science is for everyone. Our data science training courses have been attended by more than 10,000 employees from over 2,500 companies worldwide, including many technology leaders such as Microsoft, Google, and Facebook. For more information, visit: https://hubs.la/Q01Z-13k0

Learn to build LLM-based apps in just 40 hours with our Large Language Models bootcamp: https://hubs.la/Q01ZZGL-0

Start your journey into the world of data with our world-class Data Science Bootcamp: https://hubs.la/Q01ZZDpt0

Master Python for Data Science, Analytics, Machine Learning and Data Engineering: https://hubs.la/Q01ZZD-s0

Explore, analyze and visualize your data with Power BI Desktop: https://hubs.la/Q01ZZF8B0

—

Unleash your data science potential for FREE! Dive into our tutorials, events and courses today!

Learn the basics of data science and analytics with our data science tutorials: https://hubs.la/Q01ZZJJK0

Stay up to date with the latest data science content and subscribe to our newsletter now: https://hubs.la/Q01ZZBy10

Connect with other data scientists and AI experts at our community events: https://hubs.la/Q01ZZLd80

Check out our free Data Science courses: https://hubs.la/Q01ZZMcm0

Get your daily dose of data science with our trending blogs: https://hubs.la/Q01ZZMWl0

—