Guest Editors:
Bart Baesens
KU Leuven Belgium
Wouter Verbeke
Vrije Universiteit Brussel, Belgium
Cristian Bravo
University of Southampton, United Kingdom
Deadline for Submission: September 15, 2017
Special Issue Publication date: March 2018
**Please include the special issue title in your cover letter when submitting your manuscript.
Businesses are gathering an unprecedented amount of data to gain deeper insights into customer behavior and markets with the bottom line in mind. Popular analytical applications are: churn prediction, response modeling, credit risk modeling, sales forecasting and anomaly detection. Several analytical techniques have been developed to address such problems, where the focus has typically been on algorithmic complexity, statistical significance or detection power. However, to be successful from a business standpoint, analytical models need to do much more, namely, add business value, provide interpretability, enhance operational efficiency, and keep business compliant in following correct practices.
The objective of this special issue is to publish high-quality papers that address the added value of an analytical model from a business perspective. The issue will focus on methods, measurement, and practices that demonstrate business value. In addition to the usual technical evaluation criteria such as mean squared error, cross-entropy error, R-squared, lift curves, AUC, p-values, etc., the methods should make the connection to business value through the top or bottom line. The resulting findings and insights should help to further catalyze the impact of Big Data & Analytics in practical business applications.
Topics of interest include, but are not limited to:
• Profit driven model evaluation and implementation
• Cost-sensitive learning for classification
• Cost-sensitive learning for regression
• Cost-sensitive learning for segmentation
• Cost-sensitive forecasting
• Uplift modeling
• Customer Lifetime Value modeling
• Economical aspects of analytical models: Return on Investment (ROI), Total Cost of Ownership (TCO), etc.
• Business value of big data technologies and models
• Applications in marketing analytics, risk analytics, insurance analytics, HR analytics, supply chain analytics, customer journey analytics, text analytics, process analytics, healthcare analytics, etc.
Submitted papers must contain new, unpublished, original, and fundamental work relating to the Big Datajournal’s mission statement. Purely theoretical papers, simple surveys, incremental contributions, and/or journalistic descriptions are not encouraged. Similarly, purely algorithmic development without practical applications and/or solely benchmarking exercises using test bed data sets are not part of the intended focus. All submissions will be reviewed using rigorous scientific criteria focusing on novelty and business impact.
Deadline for Submission: September 15, 2017
Special Issue Publication date: March 2018
Big Data is a highly innovative, peer-reviewed journal, providing a unique forum for world-class research exploring the challenges and opportunities in collecting, analyzing, and disseminating vast amounts of data, including data science, big data infrastructure, and pervasive computing.
Advantages of publishing in Big Data include:
• Fast and user-friendly electronic submission
• Rapid, high-quality peer review
• Maximum exposure: accessible in 170 countries worldwide
• Open Access options available
BIO
Professor Bart Baesens is a professor at KU Leuven (Belgium), and a lecturer at the University of Southampton (United Kingdom). He has done extensive research on big data & analytics, customer relationship management, web analytics, fraud detection, and credit risk management. His findings have been published in leading international journals including Machine Learning, Management Science, IEEE Transactions on Neural Networks, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Evolutionary Computation, and the Journal of Machine Learning Research. He has authored several books including Credit Risk Management: Basic Concepts, Analytics in a Big Data World, and Fraud Analytics using Descriptive, Predictive and Social Network Techniques. He teaches E-learning courses on Advanced Analytics in a Big Data World and Credit Risk Modeling. His research is summarized at www.dataminingapps.com. He also regularly tutors, advises and provides consulting support to international firms with respect to their big data, analytics, and credit risk management strategy.
Wouter Verbeke is assistant professor and head of the Data Analytics Lab at Vrije Universiteit Brussel (Belgium). His research is situated in the field of predictive analytics and network analytics with a focus on value centric evaluation and learning. His work is driven by real-life business problems that require a data driven solution including applications in marketing, finance, fraud and cybersecurity, mobility and human resources. Wouter teaches several courses on information systems and advanced modeling for decision making to business students, and he regularly tutors workshops on fraud analytics, credit risk modeling and customer analytics to business professionals. His work has been published in international scientific journals such as IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Software Engineering, European Journal of Operational Research, Journal of Forecasting, and Decision Support Systems. In 2014, he won the EURO award for best article published in the European Journal of Operational Research in the category Innovative Applications of O.R. He is author of the book Fraud Analytics using Descriptive, Predictive and Social Network Techniques. His research and current projects are summarized at https://www.data-lab.be/.
Dr. Cristián Bravo is Lecturer (assistant professor) in Business Analytics at The University of Southampton. Previously he served as Instructor Professor at University of Talca, Chile; Research Fellow at KU Leuven, Belgium; Research Director at the Finance Centre, Universidad de Chile, and Head of Business Intelligence at one of the largest insurance companies in Chile. His research focuses on the development and application of predictive, descriptive and prospective analytics to the problem of credit risk in micro, small and medium enterprises; covering diverse topics and methodologies, such as semi-supervised techniques, social networks analytics, fraud analytics, reject inference, and multiple modelling methodologies. His work has been published in well-known international journals, he has edited two special issues in business analytics in reputed scientific journals, and he regularly teaches courses in Credit Risk and Analytics in academia and for companies worldwide.
We would love to receive your contribution!
