Talk 1: Product recommendation and the Dutch movie world
This talk will discuss two product recommendation approaches, one in a "hobby-project" restaurant setting, and the other in a more serious web/app transactions setting. We'll finish off with an insight into the Dutch movieworld by using some simple graph techniques.
About Longhow Lam: Longhow Lam is a freelance data scientist. He has worked on several projects at different companies. Among others: Customer Churn at Parkmobile, text mining complaints at SVB, predicting customer mortgage default at ING, customer clustering and insights at Pearle.
Talk 2: Machine learning with limited labels: How to get the most out of your domain expertise?
The success of a machine learning project often relies on the availability of good-quality labeled data. Machine learning models learn by seeing examples of the data, and both the number of examples and their quality make a difference in how well the model learns. Therefore, putting effort into obtaining a large number of examples with corresponding labels can be of big help in training your machine learning model. This, however, can be quite difficult in practice.
Samantha will speak about how we can use active learning and weak supervision to turn an unsupervised problem into a supervised one when labeling is difficult.
About Samantha Biegel: Samantha is a Machine Learning Engineer at Xomnia. She graduated cum laude in MSc. Artificial Intelligence and worked on numerous machine learning projects within the energy sector, financial sector and commercial sector. She enjoys working on making machine learning accessible to real-world problems and is passionate about developing trustworthy AI systems for a positive societal impact. These are some reasons why she is also currently working on an object detection pipeline for drone imagery to findrhino poachers in South Africa.
Talk 3: Video Game Programming for Data Science