The DMO-FinTech Workshop


May 7, 2024, co-located with PAKDD 2024, Taipei, Taiwan

Introduction

Decision making is a cognitive process that involves selecting a course of action or choice from among multiple alternatives. It's a fundamental aspect of human life and is present in various contexts, ranging from everyday situations to complex professional, personal, and strategic scenarios, such as resource allocations, risk management, strategic planning, cybersecurity, supply chain management, Web information systems (e.g., information retrieval and recommender systems), and so forth. Factors influencing decision making may include cognitive biases (mental shortcuts that can lead to errors in judgment), emotions, cultural and social influences, personal experiences, time constraints, and the availability of information. Optimization, on the other hand, is a systematic process that aims to find the best possible solution based on specific criteria. It involves mathematical and computational techniques to minimize or maximize an objective function while adhering to a set of constraints. Optimization seeks to identify the globally optimal solution, which is the best solution achievable according to the defined criteria. Multiple optimization techniques have been proposed and applied in machine learning and AI, such as convex optimization, non-linear optimization, evolutionary algorithms, multi-objective optimization, game theories, etc.

Both decision making and optimization have been widely applied in multiple domains, including business strategies, supply chains, fintech, etc. There are several scenarios in financial areas where decision making and optimization play an important role, such as portfolio optimization, risk managements and predictions, sustainability and ESG optimization, financial time-series forecasting, financial fraud detections, customer churn predictions, financial news and reports, large language models for financial services, financial information retrieval and recommender systems, and so forth.

Call For Papers

The primary objective of this International Workshop on Decision Making and Optimization in Financial Technologies (DMO-FinTech) is to facilitate the integration of decision-making and optimization principles within the area of financial technologies and services. Broadly speaking, we welcome submissions from both academia and industry to discuss their latest progress or findings in related areas.

Topics of Interest in DMO-FinTech include but are not limited to:

  • Decision Making and Optimization Methods (within FinTech Applications)
    • Group Decision Making and Negotiation Analysis
    • Multi-Criteria Decision Making
    • Multi-Objective Decision Making and Optimization
    • Linear/Non-Linear Optimization
    • Time-Series Decision Making and Optimization
    • Evolutionary Algorithms
    • Applied Optimization Technologies
    • Deep Learning, Transfer Learning, Reinforcement Learning
    • Human factor-based Decision Making, e.g., personality, trust, emotional analysis
    • Visualization and Interface Design to Assist Decision Making and Optimization

  • Data Mining and Machine Learning Tasks (within FinTech Applications)
    • Classification, Regressions
    • Time-Series Predictions
    • Clustering
    • Association Rule Mining
    • Outlier Detection
    • Feature Engineering

  • FinTech Tasks and Applications
    • Business or Financial Analysis
    • Financial Portfolio Optimization
    • Risk Management and Predictions
    • Financial News or Reports
    • Sustainability/ESG in Financial Investments
    • Financial Large Language Models (FinLLM / FinNLP)
    • Scalability and Efficiency in Financial Services
    • Multilingual Challenges in Financial Services
    • Conversational Systems/ChatBots for Finance
    • Multi-Modal Financial Knowledge Discovery
    • Financial Time-Series Forecasting
    • Financial Fraud Detections
    • Customer Churn Predictions
    • Privacy-Preserving AI for Finance
    • Financial Information Retrieval and Recommender Systems

    Submission Instructions

    Authors should prepare their manuscripts by using the Springer template for conference proceedings.
    We accept the following submissions:
    • Long papers (up to 12 pages, including references and appendix) from academia or industries, to present comprehensive research work, including in-depth analysis, methodologies, results, and discussions.
    • Short papers (up to 8 pages, including references and appendix) from academia or industries, to discuss innovative ideas, work in progress and key findings.
    • Industry papers (up to 8 pages, including references and appendix), to share practical insights, experiences, theoretical contributions or research methodologies, and innovations relevant to relevant fields. Note that industry submissions could be industry preliminary results, or technical abstracts/reports.

    Please submit your paper via EasyChair System.

    To maintain the technical quality of the accepted papers, our workshop uses the double-blind review for all categories of submission. Authors should anonymize author names and identities in the paper submission. The steps for anonymizing your manuscript before submission include:
    • Remove authorship information (name, institution, titles) from the anonymized version of your manuscript file. ...
    • Don't mention grants or acknowledgements — those can be added to the manuscript prior to publication. ...
    • Avoid, or try to minimize, self-citation.
    • Avoid using terms like "our previous work", "our earlier work", etc.

    Program at the DMO-FinTech Workshop @ PAKDD 2024

    Invited Speeches

    Keynote: Enhancing portfolio optimization with machine learning
    Invited Speaker: Yongjae Lee
    Bio: Prof. Yongjae Lee is an associate professor in the department of industrial engineering at Ulsan National Institute of Science and Technology (UNIST). Dr. Lee utilizes quantitative techniques such as ML/AI and optimization to analyze financial data and derive optimal decisions. He is particularly interested in analyzing individual and household financial activities to draw useful insights and design customized services. Dr. Lee has published more than 30 papers in international journals and conferences including Quantitative Finance, European Journal of Operational Research, Annals of Operations Research, Journal of Portfolio Management, AISTATS and ICAIF. He is an advisory editorial board member for the Journal of Financial Data Science and has applied ML/AI techniques to develop financial services through projects with several financial and IT companies. He received his B.S. degree in computer science and mathematical sciences and Ph.D. degree in industrial and systems engineering from KAIST.

    Keynote: FinGPT Forecaster: Leveraging Large Language Models for Enhanced Robo-Advising in Finance
    Invited Speaker: Bruce Yang
    Bio: Mr. Bruce Yang, the founder and President of AI4Finance Foundation, is an expert with profound insights in the fields of artificial intelligence and finance. He has held key positions in investment banking on Wall Street. He is best known for creating the FinGPT project, a renowned open-source initiative focused on financial large language models. Mr. Yang's research interests primarily lie at the intersection of deep learning, reinforcement learning, large language models (LLMs), and open-source AI technologies in the financial sector. He has published 18 academic papers at top-tier conferences such as NeurIPS, IEEE BigData, ICAIF AI in Finance, IJCAI, and AAAI, with a total citation count exceeding 800, demonstrating his significant impact in the academic community.


    Workshop Programs

    09:00 - 09:05, Openning remarks

    Session 1: Portfolio Optimization 10:30 - 10:50, Coffee Breaks

    Session 2: Financial Applications 12:20 - 13:40, Lunch

    Post-Workshop Publication: Journal Special Issue

    The accepted workshop papers will be invited to submit their extensions to a
    Special issue on AI for Financial Services and Applications to be published
    in Discover Data, Springer. Note that the submission deadline is March 31,
    2025, and we also welcome other authors from "AI for Finance" to submit
    their papers to this journal special issue.