Date(s) - 28/01/2020
19:00 - 21:00
New York College
Κατηγορία(ες) Δεν υπάρχουν κατηγορίες
We are super excited to announce our next PyData Piraeus event with two exceptional speakers: Vissarion Fisikopoulos, Research Scientist at National and Kapodistrian University of Athens, Senior Software Engineer at Oracle and Vladimir-Vadim Iurcovschi, Data Scientist at wappier: Intelligent Revenue Management! Vissarion will give a tutorial on High Dimensional sampling, while Vladimir will talk about wappier’s approach to Customer Churn Prediction.
We are also thrilled announce our collaboration with New York College! We would like to thank all the awesome teachers for providing us a venue for our feature meetups!
Finally we would like to thank our sponsor: wappier: Intelligent Revenue Management! Thank you guys for your help and support!
-> At the end of the meetup we will hold a draw for the book: Bayesian Methods for Hackers by Cameron Davidson – Pilon!!
-> Also don’t forget to bring your laptops with you!
Program:[masked]: High dimensional sampling and volume computation, Vissarion Fisikopoulos, Research Scientist at National and Kapodistrian University of Athens, Senior Sofware Engineer at Oracle.
Sampling from multidimensional distributions is a fundamental operation that plays a crucial role across sciences including modern machine learning and data science. An impressive number of important problems such as optimization and integration can be efficiently solved via sampling.
This talk is a tutorial on open-source software volesti, a C++ package with an R interface. volesti offers efficient implementations of state-of-the-art algorithms for sampling and volume computation of convex sets in high dimensions. volesti provides the most efficient implementations for sampling and volume to date allowing users to solve problems in dimensions an order of magnitude higher than before.
We present the basic functionality of volesti and show how volesti can be used to provide approximate solutions to intractable problems in combinatorics, artificial intelligence, financial modeling, bioinformatics and engineering.
This work is done while the speaker was affiliated with National and Kapodistrian University of Athens.
[masked]: Machine Learning for Customer Churn Prediction, Vladimir-Vadim Iurcovschi, Data Scientist at wappier: Intelligent Revenue Management, Organiser of PyData Piraeus.
Churn Prediction is one of the most common problems in industry. The task is to predict whether a customer will leave, that is churn. It is an extremely complex problem and there are many ways to tackle it.
During this session we will discuss the difficulties of defining churn in a non-contractual setting. We will provide a comprehensive and structured overview of both statistical and machine learning-based Survival Analysis Methods.
Next, we will discuss different kinds of advanced machine learning algorithms that we use at wappier to predict churn.
Our ML models can handle recurrent events and time varying covariates. They can learn temporal patterns, perform well in presence of censored data and show promising predictive capabilities.
Finally, we will end the session with a discussion on commonly used Churn Evaluation Metrics.
See you all next Tuesday, 28 January at the New York College in Kallithea (Thessalonikis 286, room A1)!
The organising team,
Vladimir, Manos, Christos & Elina