MIDAS

The Sixth Workshop on MIning DAta for financial applicationS

September 17, 2021 - Virtual


in conjunction with


ECML-PKDD 2021

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases

September 13-17, 2021 - Virtual

https://2021.ecmlpkdd.org



HOME     SUBMISSION     ORGANIZATION



We invite submissions to the 6th MIDAS Workshop on MIning DAta for financial applicationS, to be held in conjunction with ECML-PKDD 2021 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases.


Like the famous King Midas, popularly remembered in Greek mythology for his ability to turn everything he touched with his hand into gold, we believe that the wealth of data generated by modern technologies, with widespread presence of computers, users and media connected by Internet, is a goldmine for tackling a variety of problems in the financial domain.


Nowadays, people's interactions with technological systems provide us with gargantuan amounts of data documenting collective behaviour in a previously unimaginable fashion. Recent research has shown that by properly modeling and analyzing these massive datasets, for instance representing them as network structures it is possible to gain useful insights into the evolution of the systems considered (i.e., trading, disease spreading, political elections).


Investigating the impact of data arising from today's application domains on financial decisions may be of paramount importance. Knowledge extracted from data can help gather critical information for trading decisions, reveal early signs of impactful events (such as stock market moves), or anticipate catastrophic events (e.g., financial crises) that result from a combination of actions, and affect humans worldwide.


The importance of data-mining tasks in the financial domain has been long recognized. Core application scenarios include correlating Web-search data with financial decisions, forecasting stock market, predicting bank bankruptcies, understanding and managing financial risk, trading futures, credit rating, loan management, bank customer profiling.


The MIDAS workshop is aimed at discussing challenges, potentialities, and applications of leveraging data-mining tasks to tackle problems in the financial domain. The workshop provides a premier forum for sharing findings, knowledge, insights, experience and lessons learned from mining data generated in various application domains. The intrinsic interdisciplinary nature of the workshop constitutes an invaluable opportunity to promote interaction between computer scientists, physicists, mathematicians, economists and financial analysts, thus paving the way for an exciting and stimulating environment involving researchers and practitioners from different areas.


PAST EDITIONS


MIDAS 2020


MIDAS 2019


MIDAS 2018


MIDAS 2017


MIDAS 2016


 

TOPICS OF INTEREST

We encourage submission of papers on the area of data mining for financial applications. Topics of interest include, but are not limited to:

 
- Forecasting the stock market
- Trading models
- Discovering market trends
- Predictive analytics for financial services
- Network analytics in finance
- Planning investment strategies
- Portfolio management
- Understanding and managing financial risk
- Customer/investor profiling
- Identifying expert investors
- Financial modeling
- Measures of success in forecasting
- Anomaly detection in financial data
- Fraud detection
- Data-driven anti money laundering
- Discovering patterns and correlations in financial data
- Text mining and NLP for financial applications
- Financial network analysis
- Time series analysis
- Pitfalls identification
- Financial knowledge graphs
- Reinforcement learning in the financial domain
- Explainable AI in financial services

 



WORKSHOP FORMAT

 

The COVID-19 pandemic has made a traditional conference format impossible for ECML-PKDD 2021. To allow all members of ECML-PKDD and the wider research community at large to participate, ECML-PKDD 2021, and all its satellite events, including the MIDAS workshop, will thus be organized as a fully-fledged virtual event.

Further details will be provided later.



INVITED SPEAKER

 

Dr. Gianmarco De Francisci Morales, ISI Foundation

Title: "How I learned to stop worrying and love the risk"

Abstract: Risk is one of the fundamental concepts in finance, and it appears in several forms such as market risk, credit risk, liquidity risk, and many others. This talk will present two examples of applied research projects which deal with risk in the context of a real-world bank.
We will first illustrate how graph mining techniques improve models for estimating credit risk, by allowing to take trade credit into account via relational features from the trade network and the supply chain of the firms considered. We will then show how reinforcement learning techniques can be used to tackle a complex, multi-period portfolio allocation problem in a life insurance context, which includes liability management.
Finally, we will talk about another facet of risk: What are the risks when running an applied science project? Such a project requires managing the expectations and trust of the stakeholders, and a careful balance between ambition, novelty, disruption, and feasibility. We will discuss the main obstacles to overcome, and the lessons learned while working on risky projects.




ACCEPTED PAPERS

 

Luca Barbaglia, Sergio Consoli and Susan Wang.
Financial forecasting with word embedding extracted from news: a preliminary analysis


Eric Benhamou, David Saltiel, Serge Tabachnik, Corentin Bourdeix and Francois Chareyron.
Adaptive Supervised Learning for Financial Markets Volatility Targeting Models


Hamish Hall, Pedro Baiz and Philip Nadler.
Efficient Analysis of Transactional Data Using Graph Convolutional Networks


Jorge M. Bravo.
Forecasting longevity for financial applications: A first experiment with deep learning methods


Sergio Consoli, Matteo Negri, Amirhossein Tebbifakhr, Elisa Tosetti and Marco Turchi.
On neural forecasting and news emotions: the case of the Spanish stock market


Luigi Bellomarini, Livia Blasi, Rosario Laurendi and Emanuel Sallinger.
A Reasoning Approach to Financial Data Exchange with Statistical Confidentiality


Edoardo Vittori, Martino Bernasconi de Luca, Francesco Trov˛ and Marcello Restelli.
Dealing with Transaction costs in Online Portfolio Optimization




PROGRAM


Workshop Day: September 17th,  2021

9:00 - 10:30 SESSION I
-----------------------------------
9:00 - 9:10 OPENING

9:10 - 10:00 [INVITED TALK]  Gianmarco De Francisci Morales, ISI Foundation, Turin.
How I learned to stop worrying and love the risk!

10:00 - 10:30 [SHORT PAPER] Luca Barbaglia, Sergio Consoli and Susan Wang. Financial forecasting with word embedding extracted from news: a preliminary analysis


-----------------------------------

10:30 - 11:00 Coffee break
-----------------------------------


11:00 - 12:30 SESSION II
-----------------------------------

11:00 - 11:30 [FULL PAPER] Eric Benhamou, David Saltiel, Serge Tabachnik, Corentin Bourdeix and Francois Chareyron.
Adaptive Supervised Learning for Financial Markets Volatility Targeting Models

11:30 - 12:00 [FULL PAPER] Hamish Hall, Pedro Baiz and Philip Nadler.
Efficient Analysis of Transactional Data Using Graph Convolutional Networks

12:00 - 12:30 [FULL PAPER] Jorge M. Bravo.
Forecasting longevity for financial applications: A first experiment with deep learning methods

-----------------------------------

12:30 - 14:00 Lunch break
-----------------------------------


14:00 - 15:30 SESSION III
-----------------------------------

14:00 - 14:20 [SHORT PAPER]  Sergio Consoli, Matteo Negri, Amirhossein Tebbifakhr, Elisa Tosetti and Marco Turchi.
On neural forecasting and news emotions: the case of the Spanish stock market

14:20 - 14:50 [SHORT PAPER] Luigi Bellomarini, Livia Blasi, Rosario Laurendi and Emanuel Sallinger.
A Reasoning Approach to Financial Data Exchange with Statistical Confidentiality

14:50 - 15:20 [SHORT PAPER]  Edoardo Vittori, Martino Bernasconi de Luca, Francesco Trov˛ and Marcello Restelli.
Dealing with Transaction costs in Online Portfolio Optimization

15.20 - 15.30 CONCLUDING REMARKS