Complex & Intelligent Systems - Special Issue on

Data Science for Complex Decision-Making Problems- Recent Advances and Future Trends

One of the most important data science applications is to provide the required analysis to support and improve decision-making processes. Today, companies heavily invest in developing analytical and technological capabilities to enable the collection, storage, and analysis of data. Their data science roadmap typically contains applications falling under descriptive, predictive, and prescriptive analytics. These types of analytics are mainly relying on advanced statistical and machine learning algorithms to support complex decision making across various business domains and processes, including credit risk, customer retention, human resource management, finance, fraud detection, inventory management, fleet management, and digital marketing. However, investments in improving data science capabilities are not always reflected in additional revenues or decreased costs. Nowadays, companies are collecting a wide variety of information resulting in both high dimensional data in terms of the number of observations and variables, and a combination of structured and unstructured like text, audio, and image data. The prevalent focus on the data and technology has resulted in a strong emphasis on the data science practice itself while neglecting the interpretability, explainability, and actionability of the resulting outcomes to the business users. The recent researches in this field mainly focus on investigating the beneficial impact of data preprocessing methods, new data sources like text or audio, sophisticated and scalable algorithmic developments, or novel statistical evaluation metrics for complex systems and applications. Although these innovations are highly relevant in the front-end of the data science pipeline, we see a practical need and challenging opportunities for more research in bringing the outcomes of the data science pipeline closer to the needs of business decision-makers in complex environments. 

This special issue covers the novel research on enhanced decision making through interpretable data science. The topics of interest include, but are not limited to:

• Innovative visualization methods of preprocessing, processing and post-processing results
• Experimental field tests and applications of interpretable machine learning methods for complex decision making
• Innovative approaches for opening black-box models and/or applications in complex systems
• The development of new complex business-centric evaluation metrics
• The incorporation of (human) domain knowledge in preprocessing, processing or postprocessing methods 
• The alignment of analytical models and operational decision processes for complex system applications
• Informed feature engineering or feature learning
• Aspects of the data collection process that affect the interpretation

Important Dates 
Manuscript due by:     April 1, 2021
Notification of reviewers’ 1st feedback    June 1, 2021
Final manuscript submission    August 1, 2021
Notification of final decision    October 1, 2021

Submission 
The special issue seeks submission of papers that present novel original results and findings on “S.I.: DS for Complex Decision-Making Problems”. Solicited original submissions must not be currently under consideration for publication in other venue. Author guidelines and submission information can be found at https://www.springer.com/journal/40747. 

Guest Editors:
Dr. Noura Metawa 
University of New Orleans, New Orleans, Louisiana, USA 
Email: nmetawa@uno.edu 

Prof. M. Kabir Hassan 
University of New Orleans, New Orleans, Louisiana, USA 
Email: mhassan@uno.edu