Track 9

Track 9: Data Science

Track Chair:
Fernando Chirigati, New York University, USA

• Issam Al Azzoni, Al Ain University of Science and Technology, UAE
• Yazeed Ghadi, Al Ain University of Science and Technology, UAE


Given our increasing ability to collect, transmit, and store data, coupled with the growing trend towards openness, massive and heterogeneous datasets have been collected and made publicly available in a variety of domains, including finance, transportation, mobility, air quality, energy, telecommunications, social media, and healthcare, to name a few. Within such context, Data Science aims to address the underlying scientific challenges associated to the task of extracting knowledge and insights from a large number of datasets, thus helping develop data-driven techniques and tools that are trustworthy and that improve the lives of citizens. Examples of scientific challenges include mining and visualizing massive data, predictive modeling, dataset search, provenance capture and transparency for complex data analyses, data cleaning, and large-scale computation. In that sense, Data Science is naturally interdisciplinary and includes disparate fields such as machine learning, mathematical and computational statistics, optimization, information retrieval, data management and analytics, and visualization.

The purpose of this track is to bring together researchers who develop, investigate, or apply data science approaches in the context of real-world applications.

We welcome both research papers and system and application papers. Research papers describe innovative research on all aspects of data science, from theoretical foundations work to novel models and algorithms. System and application papers describe applied work addressing real-world problems and systems demonstrating tangible impact in their respective domains.


Topics of interest include, but are not limited to:

• Data mining
• Machine learning and statistics
• Modeling and forecasting
• Dataset retrieval and search
• Data cleaning
• New visualization techniques for massive data
• Business analytics
• Large-scale data analytics
• Large-scale computation
• Optimization for big data
• Provenance management and analytics
• Reproducibility and transparency

Examples of application areas include, but are not limited to:

• Finance
• Marketing and advertising
• Bioinformatics
• Healthcare
• Social sciences
• Recommender platforms
• Logistics
• Transportation
• Urban planning
• Public safety and crime prevention
• Resource management (energy, water, air quality, waste management)
• Smart cities
• Environmental protection
• Telecommunications
• Security