The Seventh Workshop on MIning DAta for financial applicationS

September 23, 2022 - Grenoble, France - Hybrid Event

in conjunction with


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

September 19-23, 2022 - Grenoble, France - Hybrid Event



We invite submissions to the 7th MIDAS Workshop on MIning DAta for financial applicationS, to be held in conjunction with ECML-PKDD 2022 - 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.


MIDAS 2021

MIDAS 2020

MIDAS 2019

MIDAS 2018

MIDAS 2017

MIDAS 2016



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

- Forecasting financial time series
- 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
- Discovering patterns and correlations in financial data
- Text mining and NLP for financial applications
- Sentiment analysis for finance
- Financial network analysis
- Time series analysis
- Pitfalls identification
- Financial knowledge graphs
- Reinforcement learning in the financial domain
- Explainable AI in financial services
- Quantum Computing for Finance




The ECML-PKDD 2022 conference and all its satellite events -- including MIDAS 2022 -- will take place according to a hybrid modality.
This means that anyone can attend the conference (and MIDAS 2022) either in-person (using the standard registration fee) or online (using the videoconference registration fee): see here.

However, for speakers, face-to-face interactions and discussions are much more effective.
So, we strongly encourage in-person attendance at least for the presenters of the accepted papers.


Speaker: Jose A Rodriguez-Serrano, Esade Business School

Title: Modernizing Banking and Finance with Machine Learning: techniques, successes and challenges 



Machine learning (ML) adoption in the banking and fintech industry is accelerating and recently demonstrating success beyond the old-school applications of e.g. risk and fraud. This leads to a modernization of the industry with interesting advances such as more interactive apps, proactive advice, or shift in customer relation models. But adoption still feels slow-paced, opportunistic, and unevenly distributed, not systemic;  and the sector is still undergoing a learning process.

This talk will review how ML has the potential to become an horizontal enabling layer in several non-traditional domains of banking and finance (such personalization, personal and corporate customer relations, or process optimization). This will include a review of relevant ML techniques (e.g. forcasting with uncertainty, or graph-based methods), real examples of known success cases, and also discussions of relevant challenges and cultural shifts that need to happen in this industry. The talk will also draw from the speaker’s personal experience in research and applied data science in an AI banking lab during the last 7 years.



10:30 - 10:40 OPENING

10:40 - 11:00
Braulio Blanco Lambruschini, Mats Brorsson, Maciej Zurad.
Auto-Clustering of Financial Reports Based on Formatting Style and Author's Fingerprint

11:00 - 11:20
Syrielle Montariol, Matej Martinc, Andraž Pelicon, Senja Pollak, Boshko Koloski, Igor Lončarski, Aljoša Valentinčič, Katarina Sitar Šuštar, Riste Ichev, Martin Žnidaršič.
Multi-Task Learning for Features Extraction in Financial Annual Reports

11:20 - 11:40
Niken Prasasti Martono, Hayato Ohwada.
Financial Distress Model Prediction using Machine Learning: A Case Study on Indonesia’s Consumers Cyclical Companies

11:40 - 11:50 BREAK

11:50 - 12:50  
INVITED TALK: Jose Antonio Rodríguez-Serrano, Esade Business School.
Forecasting with Uncertainty for Financial Health Insights

12:50 - 13:10
Julian Tritscher, Daniel Schlör, Fabian Gwinner, Anna Krause, Andreas Hotho.
Towards Explainable Occupational Fraud Detection

13:10 - 14:30 LUNCH BREAK

14:30 - 14:50
Sravani S, Mridula Verma.
InFi-BERT 1.0: Transformer-based language model for Indian Financial Volatility Prediction

14:50 - 15:10
Bumho Son, Hyungjin Ko, Yunyoung Lee, Jaewook Lee.
Latent Factor Model for Empirical Asset Pricing via Graph Convolutional Network

15:10 - 15:30
Thomas Dierckx, Wim Schoutens, Jesse Davis.
Towards Data-Driven Volatility Modeling with Variational Autoencoders

15:30 - 15:50
Stefano Piersanti.
Improve default prediction in highly unbalanced context

15:50 - 16:10
Klismam Pereira, Joăo Vinagre, Melânia Carvalho, Ana Nunes Alonso, Fábio Coelho.
Privacy-preserving machine learning in life insurance risk prediction

16:10 - 16:30
Hyungjin Ko, Son Bumho, Yun Young Lee, Jaewook Lee.
Examining the Spillover and Diversification Effect of Non-Fungible Token Market

16:30 - 17:00 COFFEE BREAK

17:00 - 17:20
Argimiro Arratia.
What to do with your sentiments in finance

17:20 - 17:40
Sergio Consoli, Marco Colagrossi, Francesco Panella, Luca Barbaglia.
On the development of an European tracker of societal issues and economic activities using alternative data