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

We invite submissions to the 5th MIDAS Workshop on MIning DAta for financial applicationS, to be held in conjunction with ECML-PKDD 2020 - 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

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

- Discovering patterns and correlations in financial data

- Text mining and NLP for financial applications

- Financial network analysis

- Time series analysis

- Pitfalls identification

WORKSHOP FORMAT

The COVID-19 pandemic has made a traditional conference format impossible for ECML-PKDD 2020. To allow all members of ECML-PKDD and the wider research community at large to participate, ECML-PKDD 2020, and all its satellite events, including the MIDAS workshop, will thus be organized as a fully-fledged virtual event. A draft of the ECML-PKDD 2020 virtual format can be found here. In particular, MIDAS 2020 will follow a live-mode format, where presentations of accepted papers will happen in real-time, with the speakers remotely joining the event.

INVITED SPEAKER

Dr. Luigi Bellomarini, Banca d'Italia

Title: "Neither in the Programs Nor in the Data: Mining the Hidden Financial Knowledge with Knowledge Graphs and Reasoning"

Abstract: Vadalog is a logic-based reasoning language for modern AI solutions, in particular for Knowledge Graph (KG) systems. It is showing very effective applicability in the financial realm, with success stories in a vast range of scenarios, including: creditworthiness evaluation, analysis of company ownership and control, prevention of potential takeovers of strategic companies, prediction of hidden links between economic entities, detection of family businesses, smart anonymization of financial data, fraud detection and anti-money laundering. In this work, we first focus on the language itself, giving a self-contained and accessible introduction to Warded Datalog+/-, the formalism at the core of Vadalog, as well as to the Vadalog system, a state-of-the-art KG system. We show the essentials of logic-based reasoning in KGs and touch on recent advances where logical inference works in conjunction with the inductive methods of machine learning and data mining. Leveraging our experience with KGs in Banca d'Italia, we then focus on some relevant financial applications and explain how KGs enable the development of novel solutions, able to complement the knowledge mined from the data and the domain awareness of the business experts.

ACCEPTED PAPERS

David Saltiel, Eric Benhamou, Rida Laraki, and Jamal Atif
Trade Selection with Supervised Learning and OCA

Frederico G. Monteiro, and Diogo R. Ferreira
How much does Stock Prediction improve with Sentiment Analysis?

Matteo Greco, Michele Spagnoletta, Annalisa Appice, and Donato Malerba
Applying Machine Learning to Predict Closing Prices in Stock Market: a case study

Daniel Schlor, Markus Ring, Anna Krause, and Andreas Hotho
Financial Fraud Detection with Improved Neural Arithmetic Logic Units

Luca Barbaglia, Sergio Consoli, and Sebastiano Manzan
Exploring the predictive power of news and neural machine learning models for economic forecasting

Sergio Consoli, Luca Tiozzo Pezzoli, and Elisa Tosetti
Information extraction from the GDELT database to analyse EU sovereign bond markets

Nikita Kozodoi, and Stefan Lessmann
Multi-Objective Particle Swarm Optimization for Feature Selection in Credit Scoring

Vipula Rawte, Aparna Gupta, and Mohammed Zaki
A comparative analysis of Temporal Long Text Similarity: Application to Financial Documents

Giuseppe Santomauro, Daniela Alderuccio, Fiorenzo Ambrosino, and Silvio Migliori
Ranking Cryptocurrencies by Brand Importance: A Social Media Analysis in ENEAGRID

Christoph Scholz, Malte Lehna, Katharina Brauns, and Andre' Baier
Towards the Prediction of Electricity Prices at the Intraday Market Using Shallow and Deep-Learning Methods

PROGRAM

9:00 - 10:30 SESSION I
----------------------
9:00 - 9:10 OPENING
9:10 - 10:00 [INVITED TALK] Luigi Bellomarini, "Neither in the Programs Nor in the Data: Mining the Hidden Financial Knowledge with Knowledge Graphs and Reasoning"
10:00 - 10:30 [FULL PAPER] Sergio Consoli, Luca Tiozzo Pezzoli, and Elisa Tosetti, "Information extraction from the GDELT database to analyse EU sovereign bond markets"
10:30 - 11:00 Coffee break

11:00 - 12:30 SESSION II
------------------------
11:00 - 11:30 [FULL PAPER] David Saltiel, Eric Benhamou, Rida Laraki, and Jamal Atif, "Trade Selection with Supervised Learning and OCA"
11:30 - 12:00 [FULL PAPER] Daniel Schlor, Markus Ring, Anna Krause, and Andreas Hotho, "Financial Fraud Detection with Improved Neural Arithmetic Logic Units"
12:00 - 12:30 [FULL PAPER] Luca Barbaglia, Sergio Consoli, and Sebastiano Manzan, "Exploring the predictive power of news and neural machine learning models for economic forecasting"
12:30 - 14:00 Lunch break

14:00 - 15:20 SESSION III
-------------------------
14:00 - 14:20 [SHORT PAPER] Giuseppe Santomauro, Daniela Alderuccio, Fiorenzo Ambrosino, and Silvio Migliori, "Ranking Cryptocurrencies by Brand Importance: A Social Media Analysis in ENEAGRID"
14:20 - 14:50 [FULL PAPER] Frederico G. Monteiro, and Diogo R. Ferreira. "How much does Stock Prediction improve with Sentiment Analysis?"
14:50 - 15:20 [FULL] Vipula Rawte, Aparna Gupta, and Mohammed Zaki, "A comparative analysis of Temporal Long Text Similarity: Application to Financial Documents"
15.20 - 15.40 Coffee break

15:40 - 17:00 SESSION IV
------------------------
15:40 - 16:10 [FULL PAPER] Christoph Scholz, Malte Lehna, Katharina Brauns, and Andre' Baier, "Towards the Prediction of Electricity Prices at the Intraday Market Using Shallow and Deep-Learning Methods"
16:10 - 16:30 [SHORT PAPER] Matteo Greco, Michele Spagnoletta, Annalisa Appice, and Donato Malerba, "Applying Machine Learning to Predict Closing Prices in Stock Market: a case study"
16:30 - 16:50 [SHORT PAPER] Nikita Kozodoi, and Stefan Lessmann, "Multi-Objective Particle Swarm Optimization for Feature Selection in Credit Scoring"
16:50 - 17:00 CONCLUDING REMARKS