Oct 24, 2013 · 6:30 PM
This location is shown only to members
6.30 Say Hi, free pizza+beer
“Geo-Spotting: Mining Online Location-based Services for Optimal Retail Store Placement” by Dmytro Karamshuk, Researcher @ Kings College. In this talk Dymtro will show the predictive power of various machine learning features on the popularity of retail stores in the city through the use of a dataset collected from Foursquare in New York. The features datamined are based on two general signals: geographic and user mobility. He’ll show that the best performing features are common across the three different commercial chains considered in his analysis, and that performance improves signiﬁcantly when combining multiple features in supervised learning algorithms. Dymtro is a Researcher in computer science and engineering at King's College London. Currently doing research in data mining, complex networks, human mobility, mobile networks.
Beer break + community update
“Scalable scraping with machine learning” by Eddie Bell & Jonathan Heusser, Data Scientists @Lyst. Web scraping is an integral part of modern data acquisition. At Lyst we run hundreds of scrapers in parallel and scrape millions of pages each day. In this talk we will explain how we built a robust and scalable scraping architecture with the help of machine learning. Eddie and Jonathan are ex finance people who saw the light and joined the start-up community. They are data scientists at Lyst and run the team responsible for data acquisition, monitoring and analysis.
9.30 meetup ends