Get your team up to speed with our deep training on Anti-Spam / Anti-Fraud. Based on the materials presented at top academic conferences.
Over the last decade research on adversarial machine learning has gained a lot of interest both from academia and industry. In this training, we present a systematic review of web and social spam detection techniques with the focus on algorithms and underlying principles. We categorize all existing algorithms into groups based on the type of information they use (content-based methods, link-based methods, and methods based on non-traditional data such as user behaviour, clicks, HTTP sessions) and based on the type of application scenario they address (web spam, social spam, financial services fraud). We also define the concept of spam numerically, present a detailed overview of the spam ecosystem, and quantify the economic impact of spam.
While this training is primarily based on the academic publications and recent advancements in the field of adversarial machine learning, we share unique insights and practical guidelines on how to combat the spam/fraud problem, how to design a content quality team, and how to involve users into the spam/fraud detection process based on the interviews with the heads of the anti-spam and security departments at major companies. The combination of the theoretical background and the practical lessons will prepare the team for execution of the protection policies and algorithms right after the training.