IGI Global Book: EMPA 2013 : Call for Chapters - Emerging Methods in Predictive Analytics: Risk Management and Decision Making
Call For Papers
FINAL Call for Chapters: Emerging Methods in Predictive Analytics: Risk Management and Decision Making
William H. Hsu (Kansas State University, USA)
Call for Chapters
Proposals Submission Deadline: June 28, 2013
Full Chapters Due: June 30, 2013
Submission Date: July 15, 2013
The “holy grail” of information in the present age is prescience -- accurate, comprehensive situational awareness in real time to enhance decision making. One critical piece of this expanded perception and understanding in an age of information collection is to identify the particular points of leverage where critical decisions may be made (and systems influenced), where the future may be predicted, and where the decision makers’ abilities to manage their environments may be enhanced.
Key technical advances in the state of predictive analytics include methods for forecasting, modeling, and understanding time series, detecting anomalies and emerging issues, inferring causality over time, presenting identified patterns interactively, and finally validating analytical models using real-world historical data.
These are cornerstone technologies for a range of applications ranging from intelligent alarms to monitoring and interpretation of trends in markets and geopolitical systems. Recent advances in representing temporal patterns and coping with the computational complexity of analyzing heterogeneous data have helped to meet the challenge of analyzing complex time series. The kinds of detectable anomalous patterns have expanded to include contextual (e.g., sequential) and collective anomalies. Causal inference is an active area of research that continues to yield new methodologies for explaining observed phenomena in both predictive and forensic modes.
Similarly, representations and algorithms for interactive analysis of time series are emerging from research on text analytics, visualization, and intelligent systems. Finally, recent work in statistics, machine learning, and economics has led to development of more robust validation approaches. This convergence of interdisciplinary techniques for attuning adaptive models to specific application domains has brought the state of practice closer to the goal of developing models that are both predictive and explanatory.
Objectives of the Book
This text will address various technologies, cases, and techniques used in machine learning for predictive analytics. This text will focus on the mathematical and scientific rigor underlying such systems. This text will go beyond the current literature which focuses on business applications and a few works on risk management to a broader, cutting-edge application of predictive analytics to number of fields, ranging from machine learning to information security.
More precisely, the book will:
• Introduce current techniques for machine learning, pattern recognition, and data mining that are applicable to predictive analytics
• Provide an overview of the various types of information that is available in the world today and how that information is plumbed for value
• Enhance practices in the design of predictive analytics systems for real-world tasks
• Enhance information collection for more accurate predictive analytics
• Explore ways to enhance the understandings of those using predictive analytics to understand the limits of the systems and collected information (in terms of the designs of various user interfaces) to enhance human decision-making
• Describe various strategies in mining mixed data for predictive analytics
• Depict the various types of predictive analytics systems in use today (in terms of a range of fields—such as national security, public health, law enforcement, higher education and learning analytics, and other fields)
• Describe the various types of predictive analytics systems being designed in computer science today
• Improve the design of predictive analytics tools
The scholarly value of this work is to bring to the fore the role of predictive analytics in the decision-making and maintenance of systems in a variety of contexts. This will take two basic approaches: a computer engineering and information design approach, and a user approach—so there are two audiences that are brought together around shared interests. This work will show how information is plumbed to give indicators of what may happen in the near or far futures. Bringing together these audiences would be helpful because the builders have to know the needs of the users, and users can better use systems with a deeper understanding of the systems themselves and the intentions and technologies of the builders.
The potential audiences are twofold. One group consists of computer scientists and engineers who design various systems for predictive analytics. This work will highlight effective practices in predictive analytics. Another audience will be users of predictive analytics systems for situational awareness, decision-making, base-lining, and other applications such as anticipation of future events, planning, expenditure forecasting, and policy-making. So much information is available electronically, and to actually make sure of that data, it is critical that that data may be mined and visualized by users.
Recommended topics include, but are not limited to the following:
Data Collection for Predictive Analytics
Applications in Predictive Analytics
Agro-, Bio- and other Potential Terrorism
Various Models and Algorithms
Modeling and simulations
The Extraction of Hidden Information
Combining various types of research
Setting up systems and queries to extract invisible or hidden information
Visualization of Predictive Analytics Data
Decision Supports using Predictive Analytics Data
Verifying Predictive Analytics Systems / Mapping such Systems to the World
Calibrating systems for accuracy
Adding in variables
Testing for endogenity
Anomaly Detection: Multi-Disciplinary Fields for Predictive Analytics
Law enforcement: fraud prevention, crime tracking and mapping
Public health and epidemiology
Emerging industrial issues
Market manipulation and other anomalies
Researchers and practitioners are invited to submit a page-long chapter proposal clearly explaining the mission and concerns of his or her proposed chapter. Authors of accepted proposals will be notified about the status of their proposals and sent chapter guidelines. Full chapters are expected to be submitted by November 30, 2012. All submitted chapters will be reviewed on a double-blind review basis. Contributors may also be requested to serve as peer-reviewers for this project. Original figures (especially data visualizations) are encouraged.
This book is scheduled to be published by IGI Global (formerly Idea Group Inc.), publisher of the “Information Science Reference” (formerly Idea Group Reference). Please visit www.igi-global.com. This book is anticipated to be released in 2013.
June 28, 2013 Proposal Submission Deadline
June 30, 2013 Full Chapter Submission
July 5, 2013 Review Results Returned
July 12, 2013 Final Chapter Submission
July 15, 2013 Final Deadline
Editorial Advisory Board (members to date):
* Dr. Praveen Koduru - Chief Technology Officer, IQ Gateway, Inc. (USA)
* Dr. Abel Rodríguez - Department of Applied Mathematics and Statistics, University of California Santa Cruz (USA)
* Dr. Terran Lane - Google (USA)
* Mr. Stephan Spiegel - Distributed Artificial Intelligence Laboratory, Technische Universität Berlin (Germany)
* Dr. Weixing Song - Department of Statistics, Kansas State University (USA)
* Dr. Jinyan Li - Centre for Quantum Computation and Intelligent Systems / Advanced Analytics Institute / Centre for Health Technologies, University of Technology Sydney (Australia)
Inquiries and submissions can be forwarded electronically (as PDF or Word documents) to:
Dr. William H. Hsu