Bias and fairness can play a huge role in the success of AI systems like ranking and recommendation engines. Biased data can lead to biased — and sometimes disastrous — decisions. At this meetup we’ll look at real-world examples of how bias creeps in and how to neutralize the negative effects on AI performance.
Audience: This meetup will be relevant to ML engineers, researchers, data scientists, and anyone who interacts with AI. Content is geared toward an audience with an intermediate level of experience in ML.
Schedule:
18:00 Doors open
18:30 - 18:35 – Community Intro
18:35 - 19:05 – Defining and Measuring Algorithmic Fairness
19:05 - 19:35 – Overcoming position and presentation biases in search and recommendation systems
19:35 - 19:45 – Break + networking
19:45 - 20:30 – Panel discussion on bias in AI
Agenda:
Defining and Measuring Algorithmic Fairness
Gráinne McKnight, Founding Data Science Lead at Spoke.ai
What does it mean for an algorithm to be biased or unfair? To answer this question we will look at some infamous examples where most everyone has agreed the algorithm was unfair and some underlying causes of harmful bias. We will also cover some common approaches to quantifying and identifying biases in data or models.
Overcoming position and presentation biases in search and recommendation systems
Roman Grebennikov, CTO at Metarank Labs
People's behavior is full of implicit biases. We click on first items because they're first and not because they're relevant: Google has trained us to avoid scrolling. We prefer popular things because they're popular, thus making them even more popular.
In ML tasks, taking these biases into account is a key way to improve the quality of your model. In this talk we'll go over the most typical implicit biases in the data, and discuss different approaches to overcome it and make your model more stable. We will also do a live bias-removal demo with Metarank on an open movielens-based dataset.
Panel discussion on bias in AI
Gráinne McKnight, Spoke
Roman Grebennikov, Metarank
Evgeniya Sukhodolskaya, Toloka
Florian Hönicke, Jina AI
Dania Meira - Guild AI
and OLX Group
Grab a drink and ask our guest experts everything you ever wanted to know about bias and fairness in AI. We’ll explore questions like: Is bias just a human thing? Is unbiased data attainable? Does bias ever create a positive impact?
