This year we'll pay special attention to technologies and applications in the area of fintech. For more information, please visit the links below.
There are many software and systems dealing with big data, but data mining models and machine learning methods are usually difficult to be directly applied to those software and systems. To make the research model or method support the operation of the big data systems, it is necessary to adaptively reconstruct the method, or propose data processing methods suitable for specific needs. We welcome research papers on *every* topic related to the principles and theory of data mining in the big data system, provided that there is a clear connection to foundational aspects. This includes papers exploring existing or identifying new connections between data mining in the big data system and other areas, such as the areas of:
| Name | Affiliate | |
|---|---|---|
| Kun Liu | Advanced Institute of Big Data, Beijing | liukun@aibd.ac.cn |
| Yi Liu | Advanced Institute of Big Data, Beijing | liuyi@aibd.ac.cn |
The financial field is considered one of the most data-intensive fields, representing a unique opportunity to process, analyze, and leverage the data in useful ways. Recent advances in data mining are nurturing an increasing number of financial products, services, and opportunities. Data mining is used in many financial companies, which is making a significant impact on financial services. With the increasing complexity of financial transaction processes, data mining can reduce operational costs through process automation which can automate repetitive tasks and increase productivity. After witnessing several promising achievements of data mining for finance, this special session is proposed to collect the latest advancements in financial data analysis driven by data mining techniques. We encourage original research papers of high quality that focus on novel data mining methods to solve financial problems including:
| Name | Affiliate | |
|---|---|---|
| Tao Ma | World Quant, Shanghai | pku_mark@pku.edu.cn |
| Zhihan Yue | Peking University, Beijing | zhihan.yue@pku.edu.cn |
In the big data era, with the development of data analysis, data mining, multi-media technologies and internet technologies, the methods and techniques used for handling complex problems have witnessed great changes. Big data-driven models and data mining serve as paradigm shifts in solving modern complex and large-scale problems. At the same time, swarm intelligence-based black-box optimization algorithms gradually become the one of the engines due to their ability to deal with complex structures, noise handling capability, robustness, universal applicability, etc. As an established swarm intelligence algorithm, the Fireworks Algorithm(FWA) stands out for its simplicity and effectiveness in dealing with multi-modal, discrete, multi-objective, multi-scale problems. In this special session, we aim to highlight both theoretical and application oriented works that involve the combination of FWA and data mining/big data. We hope this session can help the advancements in both areas.
| Name | Affiliate | |
|---|---|---|
| Shaoqiu Zheng | The 28th Research Institute of China Electronics Technology Group Corporation, Nanjing | zhengshaoqiu1214@foxmail.com |
| Maiyue Chen | Peking University, Beijing | mychen@pku.edu.cn |
With the rapid expansion of the data scale of various terminals and systems, the potential points and hidden vulnerabilities of data risk continue to increase. It is difficult to fully cover the whole system by manual means, and it is difficult to establish a good ecological environment that promotes defense through attack. There is a lack of systematic automatic network security defense solutions. Machine learning is bringing great changes to various fields due to its excellent learning and data representation capabilities. The research of intelligent algorithm based on machine learning is of great significance to the technical improvement of data security. This special meeting aims to collect the latest progress in data security (text, image, video, multimodal data, etc.). We encourage high-quality original research papers and focus on methods to solve data security problems, including:
| Name | Affiliate | |
|---|---|---|
| Jiwei Zhang | Beijing University of Posts and Telecommunications | jwzhang666@bupt.edu.cn |
| Lukun Wang | Shandong University of Science and Technology | wanglukun@gmail.com |
| Ziyu Jia | Beijing Jiaotong University | ziyujia@bjtu.edu.cn |
| Zelei Cheng | Purdue University | cheng473@purdue.edu |
With the explosion of the Internet and social media technologies, a large amount of data is generated from various devices, systems and applications.Big data is being used to better understand consumer habits, target marketing campaigns, improve operational efficiency, lower costs, and reduce risk. However, challenges, including both data management and data analysis exist in large-scale pratical applications with few solutions to handle processing large amounts of data. Especially, big data analytic problems are rather difficult to solve due to their large-scale, high-dimensional, and dynamic properties, while the problems with small data are usually hard to handle due to insufficient data samples and incomplete information. Recently, many machine learning paradigms have been proposed and developed, such as deep neural network (DNN), ensemble learning (EL), and reinforcement learning (RL). However, designing disirable architecture with optimal hyperparameters for machine learning system requires human expert knowledge and high computation cost. In fact, this posts a significant challenge to the development of machine learning in large-scale practical applications. The automatic design of machine learning has become an increasingly popular research trend. Meanwhile, evolutionary computation (EC), as an excellent heuristic search technique, shows significant merits in the automatic design of machine learning. It is of great interest to investigate the role of EC-based machine learning (i.e., evolutioanry machine learning) techniqures in solving large scale big data analytic problems. This special session aims to bring together both experts and new-comers from either academia or industry to discuss new and existing issues concerning evolutionary machine learning and big data, in particular, to the integration between academic research and industry applications, and to stimulate further engagement with the user community.
| Name | Affiliate | |
|---|---|---|
| Lianbo Ma | College of Software, Northeastern University | malb@swc.neu.edu.cn |
| Shangce Gao | Faculty of Engineering, University of Toyama | gaosc@eng.u-toyama.ac.jp |
| Shi Cheng | School of Computer Science, Shaanxi Normal University | cheng@snnu.edu.cn |
| Weifeng Gao | School of Mathematics and Statistics, Xidian University | gaoweifeng2004@126.com |
DMBD 2022 technical program will include special sessions. Their aim is to provide a complementary flavor to the regular sessions and should include hot topics of interest to the swarm intelligence community that may also go beyond disciplines traditionally represented at DMBD.
Prospective organizers of special sessions should submit proposals indicating:
Proposals are due on or before August 20th, 2022 and should be sent via e-mail (in either pdf or plain ASCII text form) to the special sessions chair (to be announced) and forward to DMBD 2022 secretariat at dmbd2022@iasei.org.
Proposals will be evaluated based on the timeliness of the topic, the qualifications of the organizers and the authors of the papers proposed in the session. In its decision, the committee will try to realize a balance of the topics across the technical areas represented in swarm intelligence.
Notification of acceptance will be sent to the organizers no later than August 20th, 2022. Authors of papers included in approved special sessions should submit their manuscript on or before June 30th, 2022. Manuscripts should conform to the formatting and electronic submission guidelines of regular DMBD papers (Springer’s CCIS format).
When they submit papers, there is a choice to indicate that their papers are special session papers which will also undergo peer review. It is the responsibility of the organizers to ensure that their special session meets the DMBD quality standards. If, at the end of the review process, less than four papers are accepted, the session will be canceled and the accepted papers will be moved to regular sessions.
A Quantitative Trading Competition of DMBD'2022 will be held during July 1st - August 31st, 2022. Attractive prizes will be awarded to the top participants. Please visit the link below for more information.