Special Issue on Predictive Analytics
Submission Deadline: 10 May 2014
Publication: January/February 2015
Predictive analytics is the use of statistical or machine learning methods to make predictions about future or unknown outcomes. While predictive modeling techniques have been researched by the data mining community for several decades, they have become increasingly pervasive in real-world settings in recent years, impacting every facet of our lives. Novel methods are being applied in areas such as homeland security, infrastructure management, intelligent transportation, healthcare and bioinformatics, text mining, and social media. In organizational settings, predictive analytics has gained widespread adoption over the past ten years as firms look to "compete on analytics."
In the era of Big Data, the volume, velocity, variety, and veracity of data generated by sensors, surveillance, transactions, clickstreams, and communication technologies precipitates the need for predictive analytics to run faster (in real-time), more accurately, and using larger heterogeneous information sources of varying data quality and complexity. For instance, new forms of predictive analytics are being developed to anticipate human behavior, social dynamics, and security-related outcomes at the individual, group, and community levels. State-of-the-art healthcare analytics incorporates open data, social media, and multimedia content to predict health outcomes. Additionally, organizations effectively detect financial fraud using real-time anomaly detection engines capable of efficiently perusing through millions of daily transactions.
This special issue is intended to explore innovative methods and systems pertaining to this exciting area. The topics of interest include, but are not limited to, cutting-edge research in various domains such as:
- Novel applications of predictive analytics, including areas such as homeland security, cyber-security, crime, infrastructure, transportation, healthcare, bioinformatics, social media, text mining, e-commerce, web analytics, fraud detection, etc.
- Foundational aspects of predictive methods, including learning theories
- Learning paradigms, including meta-learning, transfer learning, online learning, active learning, kernel-based methods, distributed learning, etc.
- Spatial-temporal predictive analytics
- Network predictive analytics
- Multimedia predictive analytics
Submissions should be 3,000 to 5,400 words (counting a standard figure or table as 200 words) and should follow IEEE Intelligent Systems style and presentation guidelines (www.computer.org/intelligent/author). The manuscripts cannot have been published or be currently submitted for publication elsewhere.
We strongly encourage submissions that include audio, video, and community content, which will be featured on the IEEE Computer Society Website along with the accepted papers.
- Donald E. Brown, University of Virginia, USA
- Ahmed Abbasi, University of Virginia, USA
- Raymond Y. K. Lau, City University of Hong Kong, China