AI For Fraud Detection – The RE•WORK Panel



Original Source Here

AI For Fraud Detection – The RE•WORK Panel

This week as part of the RE●WORK AI For Fraud detection Summit we are organizing a panel titled “Opportunities & Challenges in Using AI to Detect Fraud Across Industry Verticals” — A multi-talented panelists and an interesting topic, what else can one ask for ? Here is a quick overview (BTW, I was able to get a nice link http://bit.ly/ai-fraud !):

The agenda is very simple — 1st : Introductions, 2nd : A quick page set on the context to think about AI in the Fraud Domain and then the main event — we will hear from our esteemed panelists.

The nuances of Fraud and AI

  1. Class imbalance — The class imbalance in fraud (small number of fraud transactions w.r.t non-fraud transactions) makes it interesting. We do have to do things like different sampling techniques, sub-set visualization, select appropriate data slices to analyze and so forth
  2. Dynamic — A more interesting challenge is the fact that we are against human ingenuity (value judgement aside) and fast changing behaviors. So we need to pay more attention to things like monitoring data drift, model degradation and model refresh
  3. Varied — The fraud domain is varied and each sub-domains like have their own interesting twists — think of fraud models in e-commerce vs AML vs Credit Card vs Identity Theft vs Anomaly Detection
  4. Weak Signals — Tied to #2 above, any signal from the outside world about fraud is weak at best. Which in turn requires more advanced model architectures and can result in inscrutable models which i n turn necessitates explainability

Questions:

  1. How does AI improve fraud detection — in a broader perspective ?
  2. Do they differ in different verticals ?
  3. What are the interesting/effective opportunities of AI in your space ?
  4. What does the future look like ? Transformers in Fraud ? New Algorithms ? New platforms ?
  5. Questions from Audience

Panel Updates:

I will update the notes from the panel here, later tomorrow …

Cheers & See you all there …

AI/ML

Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot

%d bloggers like this: