Description:

Classified ad sites routinely process hundreds of thousands to millions of posted ads, and only a small percentage of those may be fraudulent. E-commerce platforms face the challenge of efficiently and accurately detecting fraudulent activity every day. Online scammers often go through a great amount of effort to make their listings look legitimate. Examples include copying existing advertisements from other services, tunneling through local proxies, and even paying for extra services using stolen account information. The success of e-commerce platforms strongly depends on the trust that customers have in it. If a platform is home to fraudulent offerings, customers are less likely to interact with that platform. Hence, minimizing the number of fraudulent advertisements is crucial for every e-commerce company. In this session we will apply three approaches to classify fraud: logistic regression and decision tree-based models in the form of Random Forests and XGBoost

The session will focus on the following agenda

• Understanding fraudulent ads
• Preparing Data, gathering data from online classified sites
• Strategies for modeling fraud
• Introduction to Logistic Regression, Random Forest
• Feature Engineering
• Live Demo of the application

Prerequisites:

• Python basics
  • Understanding of Machine Learning

Speaker Info:

Rahul has total of 8+ years of industry experience in Cloud Services, REST APIs, Web Development, BI Analytics & ML. He is currently working with OSI Digital as a Tech Lead.

Speaker Links:

• LinkedIn • GitHub