Data science | Explaining Tree Ensembles and NLP

///// Data science meetup | Explaining Tree Ensembles and NLP /////

In the next Data Science meetup, we have two super interesting presentations. Gyuri Mora from Whitepages will talk about interpreting tree ensembles and Zoltán Kmetty and Júlia Koltai will talk about cultural choices analysed with NLP.

Live Stream: https://videosquare.ceu.edu/hu/live/details/388,Budapest_Data_Science_Meetup_Explaining_Tree_Ensembles_and_NLP

// SCHEDULE
6:30pm - Doors open
7:00pm - Talks
8:30pm - Networking

// VENUE
CEU - Auditorium B
1051 Budapest, Nádor u. 15., Auditorium B.

// TALKS

EXPLAINING THE UNEXPLAINABLE – HOW TO INTERPRET TREE ENSEMBLES by GYURI MORA
———————
Random forests and gradient boosted trees conquered Kaggle competitions but when it comes to applications the question of explainability often pops up. In order to harvest the greater predictive power of these models and still be able to provide explanations about the predictions and the models themselves, several solutions have been proposed. We will present two slightly different methods alongside with our in-house solution focusing on their applicability in real-life scenarios.

GYURI MORA
Whitepages is a global leader in digital identity verification providing services for businesses and consumers. Gyuri is a data scientist working on the machine learning solutions powering the Identity Check Confidence Score which helps merchants and other customers to fight fraud.

UNDERSTANDING CULTURAL CHOICES WITH NLP by ZOLTÁN KMETTY, JÚLIA KOLTAI
———————
Parallel with the rise of digital textual data, natural language processing methods developed rapidly in the last decade. In our presentation, we will focus on artificial neural network based word embedding methods, which became widespread in recent years. Different fields apply these methods, such as linguists for dictionary building; developers for music video recommendations systems; companies for the analysis of product reviews, etc. However, their application in the understanding of human behaviour and culture was limited so far, though the huge amount of available digital data (text) provide a lot of information about our preferences, choices and the way we think. We will show several examples of the utilization of word embedding methods in this field. The presentation also provides details about the methodology, the problems to be solved and the directions of further development.

ZOLTÁN KMETTY, JÚLIA KOLTAI
Zoltán Kmetty PhD and Júlia Koltai PhD are computational social scientists working as assistant professors at the Eötvös Loránd University, Faculty of Social Sciences and as researchers at the Hungarian Academy of Sciences, RECENS Research Center for Computational Social Sciences. Their research interest lies in network analysis and the application of NLP methods. They regularly publish in leading international scientific journals.

See you there!