FinanceCom 2022

Speakers, Bios and Abstracts

  • Prof. Dr. Ali Hirsa, Columbia University, US
    Do we need more GANs in the Zoo of GANs? Why not? 
    TAGAN & TTGAN for simulating financial time series
  • Bob Chakravorti, CEO Chakra Advisors, US
    The Impact of FinTech and Big Tech Firms on the Way We Pay
  • Kerem Tomak, Global Chief Analytics Officer, ING, Netherlands
    Building an Effective Analytics Organisation in Financial Services 
  • Prof. Dr. Wolfgang Karl Härdle, Humboldt University Berlin, Germany
     DAI the Digital Art Index
  • Rik Goslinga, Corporate Strategy Director Europe at Paypal, Netherlands
    tbd
  • Prof. Dr. Branka Hadji Misheva, Bern University of Applied Sciences, Switzerland
    A Time Series Approach to Explainability for Neural Nets with Applications to Risk-Management and Fraud Detection
  • Prof. Dr. Joerg Osterrieder, University of Twente, Netherlands
    The European COST Action Fintech and Artificial Intelligence in Finance
  • Prof. Dr. Vijaya B Marisetty, University of Twente, Netherlands
    Workshop on Blockchain for Finance
  • Dr. Abhishta Abhishta, University of Twente, Netherlands
    Workshop on Internet Measurements for Cost Accounting
  • Prof. Dr.  Petre Lameski, SS. Cyril and Methodius University, Skopje, North Macedonia
    An empirical analysis of predictive approaches on low volume stock exchanges – a case study of the Macedonian Stock Exchange

Conference Chairs

universiteit-jos-hillegersberg-u-today-5-1-2
Fethi

Speakers

Kerem-2
wkh-1
Lameski
Abhishta

Programme Committee and Organizers

universiteit-jos-hillegersberg-u-today-5-1-1
28254 Ania Zalewska SoM Portrait Feb 2014.  Staff Portrait School of Management. ID. Client:  Liz Alvey - School of Management
Ronald-1
Ronald-K-1
jonas
vijay_profile-photo-3
Reportage, Portretten
Hirsa-6
Lameski-2
Vasile-Alecsandru-STRAT-1
Photo_Pele-1
6ae2bc20377f6facb3619e7f6083af9e-1
employee-photo-Huang_20211026-1
oste-1
Gea-pasfotoformaat

Bob Chakravorti, CEO, Chakra Advisors

Bob, CEO of Chakra Advisors, advises senior leaders at financial institutions, central banks, investment firms, payment networks, and FinTech companies about competitive, technological and regulatory forces shaping the financial system. Some of his clients include Ripple, Visa, the World Bank and fintech startups. He also manages the Incumbents and Disruptors Blog focusing on the financial services industry. His research focuses on the impact of new entrants to financial markets with an eye towards improving efficiency and access while maintaining financial stability and resiliency. Prior to his current role, Bob was the Chief Economist at the Clearing House (TCH) where he oversaw all quantitative studies for TCH members—the largest 24 banks operating in the U.S.—focusing on analyzing proposed regulations to make the financial system safer after the crisis. He also testified in front of the U.S. Congressional Financial Services Committee regarding financial reforms addressing Too Big To Fail. Before joining TCH, Bob was an economist at the Chicago and Dallas Federal Reserve Banks focusing on financial market structure and competition. He advised the Bank of Mexico, Bank of England, De Nederlandsche Bank (the Dutch central bank), and the IMF about financial markets. 

In addition, Bob is a frequent presenter at academic and industry conferences around the world. He has published over 45 articles in academic and industry journals. He received his PhD in economics from Brown University and his BA in economics and genetics from University of California, Berkeley.

The Impact of FinTech and Big Tech Firms on the Way We Pay

New technologies, new payment providers especially non-bank ones, and new regulations have impacted the way we pay for goods and services along with accessibility of financial services more broadly. Studies have shown that digital payments increase economic growth and enable greater access to credit and investment opportunities. In addition, digital payments allow governments to deliver social benefits more efficiently to its residents. In this talk, how various forces have enabled greater adoption of digital payments, what obstacles remain, which public policies have worked, and which payment segments are still resistant to digitization will be discussed. Furthermore, how data analytics tools such as machine learning tools can provide analysis of the impact of policies will be discussed. Finally, the impact of cryptocurrencies and central bank digital currencies on payments and financial services broadly will be discussed.

Kerem Tomak, Global Chief Analytics Officer, ING

Kerem Tomak is ING’s Global Chief Analytics Officer since Jan 2021. Dr. Kerem Tomak studied mathematics, economics and information systems in Turkey and the USA. He embarked on his professional career as an assistant professor at the University of Texas, Austin. Dr. Tomak brings more than 15 years of experience as a data scientist and an executive. Prior to his current appointment as the Global Chief Analytics Officer at ING Group, he was the founder and head of Big Data, Advanced Analytics and AI division at Commerzbank AG in Frankfurt. He has expertise in the areas of hybrid-multi-cloud architectures for scaling data driven products, AI/Machine learning applications in retail and financial services, digital transformation, omnichannel and cross-device attribution, price and revenue optimization, promotion effectiveness, yield optimization in digital marketing and real time analytics. He has managed mid and large-size analytics and digital marketing teams in Fortune 500 companies including Google and Yahoo and delivered large scale analytics solutions for marketing and merchandising departments for retailers like Walmart and Macy’s in the USA. His out-of-the box thinking and problem solving skills led to 4 patent awards and numerous academic publications. He is also a lecturer at the Frankfurt School of Finance and Management in the Applied Data Science Masters program as well as a sought after speaker in Big Data and AI.

Building an Effective Analytics Organisation in Financial Services 

 In this presentation, Kerem Tomak – ING’s global chief analytics officer – is going to share valuable insights on the optimal ways of integrating analytics to business. How can you leverage data science to achieve AI scalability in financial products and services? What is the importance of the analytics translator role and how can you help business adopt it at scale? How do we use the cloud to empower our clients and employees? What is the difference between a data driven and a fast-fail and learn culture? Kerem answers to all these questions and more. 

Prof. Dr. Wolfgang Karl Härdle, Humboldt University Berlin, Germany

Wolfgang Karl Härdle completed his Dr. rer. nat. in Mathematics at Heidelberg University and received his habilitation in Economics at Bonn University. He was the founder and Director of Collaborative Research Center CRC 373 “Quantification and Simulation of Economic Processes” (1994 – 2003), Director of CRC 649 “Economic Risk” (2005 – 2016) and also of C.A.S.E. (Center for Applied Statistics and Economics) (2001 – 2014). He is currently heading the Sino-German Graduate School (洪堡大学 + 大学) IRTG1792 on “High dimensional non stationary time series analysis”. He is the Ladislaus von Bortkiewicz Professor at Humboldt-Universität zu Berlin and director of the BRC the joint Blockchain Research Centre with Zurich U.

His current research focuses on modern machine learning techniques, smart data analytics and the cryptocurrency eco system. He has published more than 40 books and more than 350 papers in top statistical, econometrics and finance journals. He is highly cited, and among the top scientist registered at REPEC and has similar top notch rankings in other scales, such as the Handelsblatt ranking. 

He has professional experience in financial engineering, structured product design and credit risk analysis. His recent research extends nonparametric paradigms into machine learning, decision analytics and data science for the digital economy. He is the Editor in Chief of the Springer Journal „Digital Finance“. He supervised more than 60 PhD students and has long-term research relations to research partners in the USA, Singapore, Prague, Warsaw, Paris, Cambridge, Beijing, Xiamen, Taipei among others.

 DAI the Digital Art Index

The DAI Digital Art Index has been developed to reflect the increasing activities on the the Digital Art market. Based on the most liquid exchanges, NFT data and prices are collected in cooperation with artnet.com, NYC . The NFT art market has risen sharply recently and is competing with traditional arts market. The observed transactions are analysed and an index is developed on a hedonic regression framework. We present an introduction into NFTs, explain their construction and “huberize” the hedonic regression context.

vProf. Dr. Ali Hirsa, Columbia University, US

Ali Hirsa is a professor, director of financial engineering program at IEOR, and director of Center for AI in business analytics & Financial technology at Columbia University in the City of New York. He is also Managing Partner at Sauma Capital, LLC a New York Hedge Fund and CSO at ASK2.ai. Ali has worked at both sell-side and buy-side for 25 years.

Ali’s research interests are algorithmic trading, machine learning, deep learning, data mining, optimization, computational and quantitative finance.

Ali is author of “Computational Methods in Finance”, Chapman & Hall/CRC 2012 and co-author of “An Introduction to Mathematics of Financial Derivatives”, third edition, Academic Press and is Editor-in-Chief of Journal of Investment Strategies. He has several publications and is a frequent speaker at academic and practitioner conferences.

Ali received his PhD in Applied Mathematics from University of Maryland at College Park under the supervision of Professors Howard C. Elman and Dilip B. Madan.

Do we need more GANs in the Zoo of GANs? 
Why not? 
TAGAN & TTGAN for simulating financial time series

Realistic simulation of financial time series is very essential and important since it extends the limited real data for training and evaluation of trading strategies. It is also challenging because of the complex statistical properties of the financial data. We introduce two new generative adversarial networks (GANs), which utilize the convolutional networks with attention and transformers. The proposed GANs are called temporal attention GAN (TAGAN) & temporal transformer GAN (TTGAN). They learn the statistical properties in a data driven manner and the attention mechanism helps to replicate the long range dependencies. 

TAGAN & TTGAN are tested on the S&P 500 index and its option surface, examined by scores based on the stylized facts and are compared with the pure convolutional GAN. The attention-based GANs not only reproduce the stylized facts, but also smooth the autocorrelations of both levels and returns.

Rik Goslinga, Corporate Strategy Director Europe at Paypal

Prof. Dr. Branka Hadji Misheva, Bern University of Applied Sciences

Branka Hadji Misheva is senior researcher at ZHAW Zurich University of Applied Sciences, working on AI applications in finance, XAI methods, network models and fintech risk management. She holds a PhD in Economics and Management of Technology with a specific focus on network models as they apply to the operation and performance of P2P lending platforms, from the University of Pavia, Italy. At her position at ZHAW, she leads several research and innovation projects on Artificial Intelligence and Machine Learning for Credit Risk Management. She is a research author of 15 papers in the field of credit risk modeling, graph theory, predictive performance of scoring models, lead behavior in crypto markets and explainable AI models for credit risk management.

 

A Time Series Approach to Explainability for Neural Nets with Applications to Risk-Management and Fraud Detection

Artificial intelligence (AI) is creating one of the biggest revolution across technology-driven application fields. For the finance sector, it offers many opportunities for significant market innovation and yet broad adoption of AI systems heavily relies on our trust in their outputs. Trust in technology is enabled by understanding the rationale behind the predictions made. In other words, we need to make sure that values and domain knowledge are reflected in the algorithms’ outcomes. To this end, the concept of eXplainable AI (XAI) emerged introducing a suite of techniques attempting to explain to users how complex models arrived at a certain decision. Even though many of the classical XAI approaches can lead to valuable insights about the models’ inner workings, in most cases these techniques are not tailored for time series applications due to the presence of possibly complex and non-stationary dependence structure of the data. In this paper, we propose a generic XAI-technique for deep learning methods (DL) which preserves and exploits the natural time ordering of the data by introducing a family of so-called explainability (X-)functions. This concept bypasses severe identifiability issues, related among others to profane numerical optimization problems, and it promotes transparency by means of intuitively appealing input-output relations, ordered by time. We illustrate the generic concept based on financial time series and we derive explicit expressions for two specific X-functions for tracking potential non-linearity of the model and, by extension, for tracking non-stationarity of the data generating process. Our examples suggest that this natural extension of the original XAI-prospect, namely inferring a better understanding of the data from a better understanding of the model, might provide added value in a broad range of application fields, including risk-management and fraud detection. 

Joerg Osterrieder is Associate Professor of Finance and Artificial Intelligence at the University of Twente, Netherlands. He has been working in the area of financial statistics, quantitative finance, algorithmic trading, and digitisation of the finance industry for more than 15 years.

Joerg is the Action Chair of the European COST Action 19130 Fintech and Artificial Intelligence in Finance, an interdisciplinary research network combining 200+ researchers and 38 European countries as well as five international partner countries. He is the director of studies for an executive education course on “Big Data Analytics, Blockchain and Distributed Ledger”, co-director of studies for “Machine Learning and Deep Learning in Finance” and has been the main organizer of an annual research conference series on Artificial Intelligence in Industry and Finance since 2016. He is a founding associate editor of Digital Finance, an editor of Frontiers Artificial Intelligence in Finance and frequent reviewer for academic journals.

In addition, he serves as an expert reviewer for the European Commission on the “Executive Agency for Small & Medium-sized Enterprises” and the “European Innovation Council Accelerator Pilot” programmes.

Previously he worked as an executive director at Goldman Sachs and Merrill Lynch, as quantitative analyst at AHL as well as a member of the senior management at Credit Suisse Group. Joerg is now also active at the intersection of academia and industry, focusing on the transfer of research results to the financial services sector in order to implement practical solutions.

Artificial Intelligence in Finance – The European COST research network

Joerg will give an overview of the European COST Action Fintech and Artificial Intelligence in Finance. COST stands for Cooperation in Science and Technology and the is the longest running research funding agency in Europe. He is the Action Chair of this COST Action, a network of more than 200 researchers from 38 European countries and 5 international partner countries. The research is broadly focusing on Artificial Intelligence in Finance, with a specific emphasis on transparent financial markets, methods and products.

Prof. Vijaya B Marisetty has more than 20 years of experience in finance teaching and research. Before moving the University of Twente, he worked at Monash University, RMIT University, IIM Bangalore and the University of Hyderabad. He received several research grants to do research and implement blockchain application for financial inclusion. He runs a blockchain initiative called “inclusive growth chain” that tried to democratize wealth distribution through blockchain technology. He holds a PhD in finance from Monash University and Post-Doc from Wharton Business School and the Indian School of Business. 

Blockchain in Finance

Blockchain is an emerging technology with high potential in Fintech industry. The workshop introduces blockchain and the business case for using blockchain in Fintech industry. The workshop will explore various stages of blockchain evolution, the role and mechanics of smart contracts, blockchain potential in banking and insurance industries. The speaker will share his own experiences of building blockchain platforms in banking and financial services industries.

Abhishta

Abhishta is an assistant professor at the Industrial Engineering and Business Information Systems group at University of Twente. His research focuses on empirically measuring the economic/financial impact of cyber attacks. In order to do so he devices/adapts data-driven economic impact assessment techniques. He looks to help organisations make well-measured investments in security.His doctoral research was funded under NWO project D3 – Distributed Denial-of-Service Defense: protecting schools and other public organizations. Other than finding (un)cool methods of finding the “devil” in financial details he is also involved in teaching and guiding students. From time to time he also delivers lectures to executives and collaborates with companies to help them with security decision making. He is also a member of behavioural data science incubator at the faculty of BMS at the university, where he contributes to solving social science problems using data science.

Internet Measurements for Cost Accounting

Cyber attacks can cause considerable financial damage to firms. Traditionally, survey based methodologies have been used to account for direct and indirect costs of these attacks. In this talk, I will discuss the short comings of some survey based methodologies and introduce novel empirical techniques that can be used to account for these costs.

Petre Lameski Ph.D. is an Assistant Professor and Vice-dean for academic affairs at the SS. Cyril and Methodius University in Skopje, Faculty of Computer Science and Information Technologies. He has finished his university studies with highest honours. Petre has participated in over ten national research projects and has been lead researcher in eight national research projects. He has participated in over six International research projects. He has over one hundred publications in national and international conferences and journals. Petre has received the Successful Youth award for 2020, in the category of best young scientist in natural sciences, mathematics and technology, in North Macedonia, awarded by the president of the country. For the last fifteen years, he has also been actively engaged as consultant for industrial research and development of products, applications and POCs, that leverage the latest advancements of machine learning and artificial intelligence in companies in N. Macedonia, Europe, USA and Canada. Petre’s main research interests include deep learning, time series data analysis, transfer learning, explainable artificial intelligence and application of machine learning algorithms for solving various problems in finance, healthcare and agriculture.

Empirical analysis of predictive approaches on low volume stock exchanges – a case study of the Macedonian Stock Exchange 

Prediction of future values is a challenging task, especially for stock markets that have a low number of stock listings and trades. In this work we apply several machine learning algorithms to predict the ROI and volatility of stocks in the Macedonian Stock Exchange (MSE) in order to evaluate the efficiency of machine learning algorithms for this task and select the most important indicators. We also evaluate several external factors that influence the MSE