Skip to content

Züri Machine Learning Meetup #7

Photo of Martin Jaggi
Hosted By
Martin J.
Züri Machine Learning Meetup #7

Details

This evening will be a joint event with the Zurich Semantic Web Meetup (https://www.meetup.com/Zurich-Semantic-Web-Meetup-com/). Furthermore, as a warm-up before our meetup, the ETH Industry Day 2014 (http://www.industryday.ethz.ch/programm/index_EN) (afternoon) is highly recommended, with some very relevant short presentations.

Our Program:

• A Statistician's View on Big Data and Data Science
Diego Kuonen (https://www.linkedin.com/in/diegokuonen), CEO of Statoo Consulting (http://www.statoo.com/)

Abstract: There is no question that big data have hit the business, government and scientific sectors. The demand for skills in data science is unprecedented in sectors where value, competitiveness and efficiency are driven by data. However, there is plenty of misleading hype around the terms 'big data' and 'data science'. This presentation gives a professional statistician's view on these terms and illustrates the connection between data science and statistics.
[ slides (http://www.statoo.com/BigDataDataScience/) (will be available from the day of the meetup) ]

• Big Data and High Quality Sentiment Analysis for Stock Trading and Business Intelligence
Sulkhan Metreveli (https://www.linkedin.com/in/metreveli) and Leo Keller (http://ch.linkedin.com/pub/leo-keller/14/578/508/en), Calfor Finance (http://www.calforfinance.com/)

Abstract: Recent years have seen an increasing interest in big data. This interest has been driven by regulatory challenges on the one hand (e.g., privacy, data theft issues), and the enormous potential to uncover and predict social behaviour on the other. Our presentation contributes to the latter: we examine the influence of media information on price changes in stock exchange and foreign exchange markets. We tests the possibility of forecasting price changes in international stock exchange and foreign exchange markets by uninterrupted processing and analysis of incoming data streams from media outlets, social media sources and news terminals. On this road, we face two major challenges: first, the amount of data we examine is enormous and second, the tools to understand the content of data are imperfect. The tools developed at Calfor Finance deal with the two challenges. We reduce the speed of information processing to the minimum and introduce a novel method of sentiment detection and reassessment that significantly improves the quality of information interpretation. Finally, our results demonstrate a major correlation between media sentiment and market prices.

• t.b.d.
t.b.d.

Photo of Zurich Machine Learning and Data Science group
Zurich Machine Learning and Data Science
See more events
ETH Zürich, CAB Building, Room G61
Universitätstrasse 6 · Zürich