Service management has been increasingly challenging for IT enterprises that create, deploy, and maintain services and infrastructure for a variety of customers and produce data at a large volume and velocity. At any given point, these enterprises need to know a myriad of information regarding the status, risk/compliance, business objectives, and operational health of the services involved. Further, business goal alignment and customer experience need to be prioritized and, accordingly, managed in an agile and optimized manner. To do so, enterprises are constantly seeking novel technologies and solutions in cognitive platforms, advanced analytics and learning, and interactive frameworks. With the proliferation of cloud computing, microservice architectures and IoT data fabrics, the enterprises face new challenges in operating their business with increased efficiency, reduced cost, faster time-to-market, and enhanced customer experience. For example, enterprises such as Amazon and Google can create, deploy and market new features/capabilities multiple times within the same day.

The problem of rapid change in enterprises demands the exploration of new directions and possible innovations. To be successful in this endeavor, we require forums of both academic and industry researchers, and practitioners. We propose this workshop to combine research efforts on eight timely challenges with immediate industry applications:

• AI for service operations
• Cognitive service frameworks
• Data mining platform and application for services
• Conversational IT services
• Cognition and learning in process management
• Cognitive solutions for cloud management
• Cognitive solutions for Internet of Things (IoT)
• IT service analytics
• Security, risk, and compliance
• Social aspects in microservice ecosystem

Important Dates

Papers Submission: September 3, 2018

Authors Notification: September 21, 2018

Early Registration: September 24, 2018

Camera Ready Paper & Copyright: TBD

Workshop: November 12, 2018

Submission and Publication

We invite authors to submit papers in four separate tracks.

1. Full paper track (maximum 15 pages) : This track focuses on significant research contribution.

2. Short paper track (maximum 8 pages): This highlights visionary ideas

3. PhD Thesis Presentation (15-20 slides): This allows PhD students to discuss early ideas about their PhD thesis with a broader audience

4. Demonstration (maximum 4 pages): This allows participants to submit their research contributions in the form of a demo

For all the tracks, authors must use the Springer LNCS format. For submitting their papers, authors must use EasyChair. If there is a problem while submitting papers, please contact kaliaanup@gmail.com.

Organizing Committee

1. Anup Kalia, IBM T. J. Watson Research Center, NY, US
2. Jin Xiao, IBM T. J. Watson Research Center, NY, US
3. Fanjing Meng, IBM Research Lab, Beijing, China
4. Larisa Shwartz, IBM T. J. Watson Research Center, NY, US
5. Ying Li, Peking University, Beijing, China

Technical Program Committee

1. Aditya Ghose, University of Wollongong, Australia
2. Chunqiu Zeng, Google, US
3. Jingmin Xu, IBM Research, China
4. Liang Tang, Google, US
5. Munindar Singh, North Carolina State University, US
6. Maja Vukovic, IBM T. J. Watson Research Center, NY, US
7. Peng Fei Chen, Sun Yat-sen University, China
8. Qi Yu, Rochester Institute of Technology, US
9. Rahul Pandita, Phase Change Software, US
10. Samir Tata, LG Silicon Valley Lab, US
11. Schahram Dustdar, TU Vienna, Austria

Keynote Speakers

1. Maja Vukovic (IBM T.J. Watson Research Center). Towards AI infused Service Management: Challenges and Opportunities

Accepted Papers

Full Papers:

1. Fast Nearest-Neighbor Classication using RNN in Domains with Large Number of Classes

Authors: Gautam Singh (IBM Research-India), Gargi Dasgupta (IBM Research-India), and Yu Deng (IBM T.J. Watson Research Center)

2. TaxiC: A Taxi Route Recommendation Method based on Urban Traffic Charge Heat Map

Authors: Yijing Cheng (Xiamen University), Qifeng Zhou (Xiamen University), and Yongxuan Lai (Xiamen University)

3. Event Log Reconstruction Using Autoencoders

Authors: Hoang Thi Cam Nguyen (Ulsan National Institute of Science and Technology), Marco Comuzzi (Ulsan National Institute of Science and Technology)

4. MLE: a General Multi-Layer Ensemble Framework for Group Recommendation

Authors: Xiaopeng Li, Bin Xia (Nanjing University of Posts and Telecommunications)

Short Papers:

1. Does your accurate process predictive monitoring model give reliable predictions?

Authors: Marco Comuzzi (Ulsan National Institute of Science and Technology), Alfonso E. Marquez-Chamorro (Universidad de Sevilla), and Manuel Resinas2 (Universidad de Sevilla)

Tentative Program