Call for Paper

DMF 2025 features three major themes and one special theme:

• Effective and efficient financial data mining

• Trustworthy data mining in finance, such as

  • Explainable financial data mining models (e.g., key feature recognition, predictive performance analysis)

  • Fairness-aware financial data mining (e.g., fairly treating customer accounts, shareholder equity)

  • Privacy-preserved financial data mining, simulation, and sharing

  • Market monitoring and auditing

  • Anomaly detection

• LLM-based financial data mining, such as

  • Data cleaning and collecting pipelines of pre-training large models

  • Financial LLMs training with reinforcement fine-tuning

  • Financial applications of LLMs (language models, vision models, audio models, and video models)

  • Application of large models under financial compliance constraints

  • Data privacy protection in financial large models

  • Inference acceleration and high-concurrency techniques for financial LLMs

• Special Track: Data mining in finance with agentic workflows

The realm of finance presents complex challenges and opportunities for data mining, particularly when enhanced by agentic workflows. This special track invites research that explores innovative frameworks and benchmarks for sophisticated reasoning in trading and financial analysis. We are interested in submissions that delve into agent-based modeling, automated trading systems, predictive analytics, and risk assessment, all within the context of financial data mining.

DMF 2025 runs three paper submission tracks: regular papers, short papers, and special track papers. The regular paper track and special track welcome submissions that emphasize theoretical foundations, algorithms, models, systems, and applications related to data mining in finance. Original research papers are particularly encouraged for these two tracks. The short paper track seeks papers focusing on applied research, industrial experience reports, demonstrations (e.g., showcasing toolkits for financial data mining), and vision papers that introduce challenges and open problems.

Submission Guidelines

Paper Length and Submission Requirements

Authors are encouraged to submit original, English-language research contributions that have not been concurrently submitted or published elsewhere. All submissions must adhere to the IEEE 2-column format. For the regular paper track, submissions should not exceed 8 pages of content, plus an additional 2 pages for references. For the short paper track, submissions should be limited to a maximum of 4 pages of content, plus 1 extra page for references. Other submission requirements are the same as ICDM 2025.

Review Guidelines

In alignment with the ICDM 2025 reviewing scheme, all submissions will undergo triple-blind reviews by the Program Committee, evaluating technical quality, relevance to the conference scope, originality, significance, and clarity. All accepted papers will be presented as oral presentations. By the unique ICDM tradition, all accepted workshop papers will be published in the dedicated ICDMW proceedings published by the IEEE Computer Society Press.

Attendance

At least one author of each accepted paper must complete the conference registration and present the paper at the conference for it to be included in the proceedings and program. In cases where an author is unable to attend the conference in person due to visa issues, a pre-recorded video presentation is allowed. The presenting author must still register for the conference.

Submission Website

Submit your paper via cyberchair: https://wi-lab.com/cyberchair/2025/icdm25/scripts/submit.php?subarea=S49&undisplay_detail=1&wh=/cyberchair/2025/icdm25/scripts/ws_submit.php   

Important Dates

Paper submission deadline: August 29, 2025

Notification of acceptance: September 15, 2025 September 19, 2025

Camera-ready deadline and copyright form: September 25, 2025 (TBD)

**All times are at 11:59PM AoE** unless otherwise stated

Contact

For queries regarding this call, please contact: zhangyuchen@efunds.com.cn.