Augmenting Web Scraping With Machine Learning

Machine Learning and web scraping are growing to be closely related, especially when it comes to scraping public data at scale. This presentation will reveal what challenges occur when scraping at scale and how they can be solved by applying machine learning algorithms.

Oxylabs’ Machine Learning Engineer Jurijus will discuss how his team solves problems that inevitably come up within the web scraping workflow. Jurijus will talk about block detection and content classification as some of the solutions. If you, or your team, is scraping public information at scale and run into issues, this presentation is an excellent opportunity to find the answer to your questions.

Join this session, if you:

• Run large-scale web scraping projects

• Want to apply Machine Learning algorithms to web scraping

• Are interested in the future of web scraping

Jurijus is a Machine Learning engineer at Oxylabs. He works in a team that solves technical and business problems by applying machine learning techniques. Before starting this role, he worked at various companies and multiple positions ranging from Big Data to Technical Operations.

At Oxylabs, his responsibilities include data analytics and transformation, followed by the creation of Machine Learning models that improve either in functionality, performance, or time and financial costs. His hobbies are basketball, football, and Marvel comics.