Tampere University of Technology is the coordinator of the BigDataFinance Marie Skłodowska-Curie European Innovative Training Network. There are altogether 13 positions available for doctoral students, and currently we are seeking to fill 2 of those positions at Department of Industrial Management/Research Group on Financial Engineering and one at Department of Signal Processing.
Tampere University of Technology (TUT) is an active scientific community of 2,000 employees and more than 10,000 students. The University operates in the form of a foundation and has a long-standing tradition of collaboration with other research institutions and business life. Many of the fields of research and study represented at the University play a key role in addressing global challenges. Internationality is an inherent part of all the University’s activities. Welcome to join us at TUT!
We are looking for talented, creative and highly motivated researchers. A suitable background for these open positions includes Econometrics, Finance, Quantitative Finance, Data Engineering, Knowledge Engineering, Statistics, Signal Processing, Artificial Intelligence, Machine Learning, Physics and other related areas. Fluent written and spoken English and solid programming (C/C++/Python/R/Matlab) and sufficient data engineering skills (e.g. SQL, Hadoop or Spark) are required. Excellent skills in statistics, applied mathematics and data science are essential. Skills in financial analysis are acknowledged. If separately asked from a candidate, a suitable English language proficiency test may be required.
Three position available (each 36 months) at Tampere University of Technology in the following research projects.
Position 3 (ESR 8)
WP1: Data Science in Finance
Research project: Divide and Conquer Deep Learning for Big Data in Finance
Objectives: In the era of Finance Big Data, how can one conquer something so big and so vast? Management and learning in Finance Big Data should thus follow the holistic “Divide & Conquer” philosophy. We will develop a novel platform that supports all aspects of this philosophy, including workflow-based tools for content ingest and description, distributed storage, the management and preservation, self-data organisation (SDO) for partitioning large categories of finance data, user interaction models and visualisation, use of large evolving and self-adapting clouds of evolutionary feature synthesis (EFS) and classifier networks to learn hidden patterns in finance data, and services for different applications that can inherently use Cloud computing environments such as anomaly detection, new trends detection and prediction, and risk management. Furthermore, hashing or quantisation encoding methods are common tools exploiting the divide and conquer approach. We aim to design novel vector quantisation and hashing techniques, which will surpass the state of the art and use them for the first time in Big Data for finance. Our current solution using ranked 2nd in the 2014 MSR-Bing Image Retrieval Challenge. Smart subsampling in Big Data is naturally suitable for distributed computing environments. We will study several subsampling methods by inferring the properties of finance Big Data. The main goal is to achieve highly scalable algorithms.
Expected Results: The expected results comprise a novel platform that supports all aspects of this philosophy, including workflow based tools for finance data analysis; distributed storage; management of an expanding and evolving body of finance data; use of a large, evolving and self-adapting clouds of evolutionary feature synthesizers and classifier networks capable of “learning” important and relevant aspects of finance Big Data; development of novel hashing- and vector-quantisation-based techniques for data encoding and smart data sampling; and implementation of these techniques in a Grid/Cloud computing environment. The project will generate publications for top-tier journals (Data Science/Machine Learning/Finance). In addition, a PhD thesis will be completed.
For more information, please contact:
Professor Moncef Gabbouj
Signal Processing / Tampere University of Technology
+358 400 736 613
Fill application form by the 18th of December 2015
Position 1 (ESR 4) CALL CLOSED
(WP2) Complex Networks in Finance
Research project: Complex Network Analysis in Stock Markets
Objectives: This project aims to study investor behaviour and the dynamics of corporate ownership, especially during financial crises via complex network analysis and big data techniques. The researcher will study in depth large financial data sets, including a unique dataset of complete trading records from all Finnish investors on publicly traded domestic stocks along with background information on traders’ transactions and their attributes (e.g., individual/institutional, male/female, location, and size of the position with unique trader IDs) from 1995 to 2009 (covering the Millennium IT bubble and recent financial crises). The first part of this RP will provide solid empirical results on investor networks by linking traders with similar portfolio rebalancing and trading strategies. We aim to (i) study how empirical investor networks change during crises and to (ii) identify the determinants of different rebalancing and trading strategies (e.g., is it announcements or volatility that drives a certain group of investors to trade). The second part will analyse the determinants and dynamics of corporate ownership during financial crises.
Expected Results: We expect to provide empirical evidence on the determinants of ownership base and dynamics, behavioural differences between different investor groups (e.g., major institutional investors and individual small-scale investors), how ownership structure reflects the industrial sector of the stocks (e.g., energy sector vs IT during the Millennium IT bubble), and how different investors react to news announcement and process the public information. This data-intensive analysis is very essential to gaining an understanding of the empirical properties of the financial markets and the behaviour of investors. Financial supervisory bodies can benefit from the study to understand the impacts of macro variables on stock markets and to advise monetary policy makers. Private sectors can use the results to obtain insight into and advice on corporate strategies. Companies can use these results to understand how ownership base affects the dynamics of the underlying stock and investors to predict the nature of information diffusion in financial markets. Two journal publications in Finance and a PhD Manuscript will be completed (or at least submitted).
Position 2 (ESR 8) CALL CLOSED
(WP3) Financial Econometrics with High-Frequency Data and News Announcements
Research project: Order Books Dynamics and Announcement Effects during Financial Crisis
Information arrivals are of particular interest in finance. This project studies how announcements are related to the fundamental order book process. The objective is to provide empirical evidence and to model the determinants of order book dynamics and information asymmetry around information shocks and during a financial crisis. Secondly, given that there are investors who may take the advantage of inside information before its publication, the objective is to spot inside traders’ proactive actions from highfrequency order book data. These topics will be addressed by using extensive data sets over the recent financial crisis and by introducing a new class of limit order book models with infinite-activity time-changed Lévy processes that can capture variation in the business activity. Though some prominent researchers have recently addressed some questions about liquidity available in the Treasury order book markets at news arrivals (see Engle, R. F., M. Fleming, E. Ghysel and G. Nguyen (2012), “Liquidity, Volatility, and Flights to Safety in the U.S. Treasury Market: Evidence from a New Class of Dynamic Order Book Models.” Working Paper, Federal Reserve Bank of New York Staff Reports.), liquidity at information shocks has not been studied in depth with data from Equity markets–perhaps because of the technical challenges of managing massive stock order book data sets. This RP fills this gap by using ultra high-frequency limit order book data from Nordic and US Nasdaq.
Expected Results: This project provides a framework that can be used to (i) study the liquidity dynamics around information arrivals to help the scientific community to develop reliable and robust models and theories for order book markets and (ii) seek evidence of information leakage before public news announcement to identify abnormalities in the order flow caused by information leakage, which serves as a tool not only in trading and risk management but also in financial supervision. Two journal submissions (Finance/Operation Research) and a PhD manuscript will be carried out.
For more information, please contact:
Professor Juho Kanniainen
Financial Engineering Research Group/ Industrial Management
Tampere University of Technology
+358 407 074 532
Fill application form by the 15th of November 2015