Monday, March 26, 2012

Correlating Financial Time Series with Micro-Blogging Activity


"Correlating Financial Time Series with Micro-Blogging Activity"


We study the problem of correlating micro-blogging activity with stock-market events, defined as changes in the price and traded volume of stocks. Specifically, we collect messages related to a number of companies, and we search for correlations between stock-market events for those companies and features extracted from the micro blogging messages. The features we extract can be categorized in two groups. Features in the first group measure the overall activity in the micro-blogging platform, such as number of posts, number of re-posts, and so on. Features in the second group measure properties of an induced interaction graph, for instance, the number of connected components, statistics on the degree distribution, and other graph-based properties.
We present detailed experimental results measuring the correlation of the stock market events with these features, using Twitter as a data source. Our results show that the most correlated features are the number of connected components and the number of nodes of the interaction graph. The correlation is stronger with the traded volume than with the price of the stock. However, by using a simulator we show that even relatively small correlations between price and micro-blogging features can be exploited to drive a stock trading strategy that outperforms other baseline strategies.

get the paper here.

IEEE Network March 2012

IEEE Network March 2012's topic on optical networks.

Next-Generation Optical Access Networks: Dynamic Bandwidth Allocation, Resource Use Optimization, and QoS Improvements


Network Operator Requirements for the Next Generation of Optical Access Networks


NG-PONs 1&2 and Beyond: The Dawn of the Über-FiWi Network


Next Generation Optical-Wireless Converged Network Architectures


Energy Efficiency in the Extended-Reach Fiber-Wireless Access Networks


Energy-Efficient PON with Sleep-Mode ONU: Progress, Challenges, and Solutions


Adaptable Access System: Pursuit of Ideal Future Access System Architecture


Medium Access Control for the Next-Generation Passive Optical Networks: The OLIMAC Approach

Saturday, March 24, 2012

Friday, March 23, 2012

Optimizing for video storage networking

"Optimizing for Video Storage Networking With Recommender Systems"


Driven mainly by its adoption as a new media distribution platform for content providers and its ubiquitous availability for the end user’s media production and consumption, the Internet is rapidly reshaping. In particular, the stakeholders in the content distribution market are considering exploiting content delivery networks (CDNs) to play a key enabling role allowing them  to become part of related value chains. In this paper we discuss how such CDNs rely on autonomous algorithms to optimally use the storage resources, i.e., reducing bandwidth on feeder links, while providing quality of experience (QoE) to the end user.

get the paper here.