News and Events
"Machine Learning Methods and Data Analytics in Risk and Insurance", Vienna TU, Austria, 9-13 July
- Prof. Dr. Gareth W. Peters, Heriot-Watt University, Edinburgh, United Kingdom
- Prof. Dr. Pavel V. Shevchenko, Macquarie University, Sydney, Australia
Machine learning and data analytics is an emerging field that is beginning to have a strong influence on the field of actuarial science practice. The onset of big data applications in insurance has driven the profession to explore new ways to understand data and modelling. Unlike in Google and Facebook type technology applications where huge data bases of labelled data are available, in the insurance context we are often considering unsupervised learning methods. This course will address core methodology to tackle supervised and unsupervised problems of relevance to insurance applications.
For more information, see https://fam.tuwien.ac.at/events/viss2018/
Optimal decision making for risk mitigation of natural hazards
CSIRO DUCA PhD scholarships 2018
Faculty of Business and Economics
Actuarial Studies and Business Analytics
Optimal decision making for risk mitigation of natural hazards
31 August 2018 for international students
31 October 2018 for domestic students
for commencement in Semester 1, 2019
two top up scholarships (top-up or full PhD scholarships)
International or Domestic
international or domestic
Australia faces substantial risks from changes in frequency and severity of natural hazards such as flooding, storm surges, bushfires, sea level rise and climate change that are further exacerbated by population and economic growth in risk-prone areas. While there exist a number of software tools such as TuFlow, Mike flood, C-Fast and SWIFT (the latter two developed by researchers from CSIRO Data61 and will be provided for the project purposes) that can model the physical impact of natural hazards, there is a lack of models that allow for the economic quantification of potential damages, as well as approaches for taking optimal decisions on risk mitigation investments and land use planning. This project aims to fill this important gap by developing a decision making framework that will consider real options and optimal stochastic control methodologies with rare event probabilistic methods.
Other important information
CSIRO Data61 offers top up PhD scholarships under DUCA (Data61 University Collaborative Agreement) with Macquarie University: typically $10,000 per student per annum for up to three years. CSIRO Data61 also offers full PhD scholarships of value approximately $37,000 per annum for up to three years. For more information, see https://www.csiro.au/en/Careers/Student-and-graduate-opportunities/Form-Data61-scholarship
It is expected that students have discussed their interest and secured support from university and CSIRO Data61-based supervisors prior to submitting an application to the scholarship program. Applicants should therefore contact Prof Shevchenko email@example.com in the first instance.
Prof Pavel Shevchenko
These top up scholarships are available to eligible current PhD domestic or international candidates already enrolled and in receipt of a main stipend.
Behavioral Finance driven Investment Strategies
Swissôtel Sydney, Friday 16 March 2018
Financial Risk Day 2018: Investment and Risk in a Low Interest Rate Environment
The Centre for Financial Risk in the Faculty of Business and Economics is hosting the 8th annual Financial Risk Day on Friday 16 March 2018 at Swissôtel Sydney. This one-day conference brings together experts from industry, academia and regulatory bodies to discuss topics related to financial risk. This year, the conference theme is the impact of the current low interest rate environment on investment and risk in banking, insurance and superannuation.
- Antje Berndt – Head of Finance at ANU Research School of Finance, Actuarial Studies & Statistics
- Guy Debelle - Deputy Governor, Reserve Bank of Australia
- Simon Elimelakh - Head of Investment Risk and Portfolio Analysis, NAB Asset Management
- Stephen Kirchner – Program Director, Trade and Investment at United States Studies Centre at the University of Sydney
- John Pearce - Chief Investment Officer, UniSuper
- Alastair Sloan – Former Head of Asset Allocation at Sunsuper
- Nigel Wilkin-Smith - Director, Portfolio Strategy, Future Fund
Organizers: Prof Jeffrey Sheen, Prof Pavel Shevchenko, Prof Stefan Trueck
For further information please visit www.mq.edu.au/research/financial-risk-day
27-28 February 2018, Institute of Statistical Mathematics, Tokyo, Japan
2018 International Workshop on Spatial and Temporal Modeling from Statistical, Machine Learning and Engineering Perspectives
The analysis of complex and massive data sets which display attributes of spatial and temporal characteristics is a growing field of research. Traditionally the two fields have been treated predominantly via a range of different approaches, depending on the discipline in which the applications are under study. There has been a range of recent developments in characterizing multivariate spatial and temporal processes which are either discrete (branching and counting processes) or continuous (heavy tailed processes such as Levy processes) and their sub-families the stable processes and Gaussian processes. In addition the study of such processes in practical applications has advanced significantly and the intention of the workshops is to present some recent developments in specification, estimation in high dimensional and complex structured models formed from such processes and application. The workshop aims to introduce these theory and methodology for a range of real applications in areas of machine learning, wireless communications, sensor networks, finance, insurance, earthquake dynamic modeling, environmental modeling, signal processing and speech and audio processing.
UNSW-Macquarie University workshop "Risk: Modelling, Optimization and Inference with applications in Finance, Insurance and Superannuation" was held on 7-8 December 2017 in Sydney.
Risk: Modelling, Optimization and Inference with applications in Finance, Insurance and Superannuation
- School of Mathematics and Statistics, UNSW, represented by Associate Professor Spiridon Penev
- Department of Applied Finance and Actuarial Studies, Macquarie University, represented by Professor Pavel Shevchenko
- School of Risk and Actuarial Studies, UNSW, represented by Associate Professor Benjamin Avanzi
OpRisk Award 2017, best paper of the year G.W. Peters, P.V. Shevchenko, B. Hassani and A. Chapelle (2016). “Should the advanced measurement approach be replaced with the standardized measurement approach for Operational Risk?”, Journal of Operational Risk 11(3), pp. 1-49.
OpRisk Award 2017, best paper of the year
G.W. Peters, P.V. Shevchenko, B. Hassani and A. Chapelle (2016). “Should the advanced measurement approach be replaced with the standardized measurement approach for Operational Risk?”, Journal of Operational Risk 11(3), pp. 1-49
received Operational Risk Award 2017 from Incisive Media, UK for the best paper of the year announced recently http://www.opriskawards.com/static/2017-winners. An article about this was published on Risk.Net after interview with the paper authors http://www.risk.net/awards/5296601/paper-of-the-year-peters-shevchenko-hassani-and-chapelle.
We prepared this paper last year regarding the Basel proposal to change approach for quantification of operational risk capital for banks. The Basel proposal was to remove the Advanced Measurement Approach (AMA) and replace it with the Standardized Measurement Approach (SMA).
We uploaded our shorter comments http://ssrn.com/abstract=2789006 to the Basel website https://www.bis.org/bcbs/publ/comments/d355/suefu.pdf during a formal call for comments from the Basel Committee in 2016 and published white paper on Risk.Net http://www.risk.net/risk-management/operational-risk/2451089/discarding-the-ama-could-become-a-source-of-op-risk, and then we wrote the journal paper.
The Journal of Operational Risk is highly regarded by industry practitioners, and the award we received is very prestigious and strong recognition by the industry and profession.
Professor Youri Kabanov visited Macquarie University during 1-20 November 2017
7 November 2017, 10am-1pm, Short Course, E4A. Level 5, room 523, Macquarie University.
Title: Markets with Transaction Costs: Mathematical Theory
Abstract: Classical Arbitrage Theory for frictionless financial markets relates economically meaningful property of absence of arbitrage with the fundamental probabilistic concept of equivalent martingale measure. Densities processes of equivalent martingale measures plays a role of stochastic deflators. To compare the present values of assets with their future values one needs to use not the prices but the prices multiplied by stochastic deflators. The theory of markets with proportional transaction costs treats portfolios as vectors of assets without assigning to them a scalar - its monetary value. It happens that in the case of proportional transaction costs the fundamental concept is a consistent price system, a martingale evolving in the dual to the solvency cones (in physical units). In the absence of friction all such martingales can be obtained by multiplying prices by stochastic deflators. For markets with transaction costs there are several possible formalizations of absence of arbitrage and the available criteria involve consistent price systems. Surprisingly, the passage from the model with a finite number of states of the nature to the general case goes not so smoothly as in the classical theory. Several examples will be discussed in the lecture course. From mathematical point of view, the theory for market with transaction costs is a vector analog of the classical theory. It is a blend of finite dimensional geometry, geometric functional analysis and stochastic calculus. On the other hand, it feels the gap between mathematical finance and mathematical economics showing how these two disciplines are related.
9 November 2017, 12pm-2pm, Public Lecture. Macquarie City Campus, Level 24, 123 Pitt Street Sydney NSW 2000
Title: Clearing in Financial Networks
Abstract: Clearing of financial system, i.e. of a network of interconnecting banks, is a procedure of simultaneous repaying debts to reduce their total volume. The vector whose components are repayments of each bank is called clearing vector. In simple models considered by Eisenberg and Noe (2001) and, independently, by Suzuki (2002), it was shown that the clearing to the minimal value of debts accordingly to natural rules can be formulated as a fixpoint problem. The existence of their solutions, i.e. of clearing vectors, is rather straightforward and can be obtained by a direct reference to the Knaster–Tarski or Brouwer theorems. The uniqueness of clearing vectors is a more delicate problem which was solved by Eisenberg and Noe using a graph structure of the financial network. We discuss the modern state of art of the theory and, in particular, algorithmic aspects of solving clearing equations in relations with those arising in the theory of optimal stopping.
13 November, 2017 10:30am-12pm, CFR Seminar in Macquarie University, room 523
Title: Ruin probabilities with investments in a risky asset with the price given by a geometric Lévy process
Abstract: We consider a model describing the evolution of capital of a venture company selling innovations and investing its reserve into a risky asset with the price given by a geometric Lévy process. We find the exact asymptotic of the ruin probabilities. Under some natural conditions it decays as a power function. The rate of decay is a positive root of equation determined by characteristics of the price process. When the price follows a gBm the results are reduced to those of our previous works where we used the method of ODEs assuming exponentially distributed jumps. Our proofs are based on the theory of distributional equations, in particular, on a recent result by Guivarc'h and Le Page.
7 December 2017, Lecture for the UNSW-Macquarie risk workshop in UNSW 7-8 December.
Title: Hedging in Markets with Small Transaction Costs
Abstract: We discuss the concepts of approximate replication and super-replication inthe context of markets with friction. We consider a class of models where the transaction costs coefficients depend on the number n of transactions, decreasing to zero as n^(-1/2), and show that the impact of transaction costs on the super-replication price has a similar effect as a proportional increase of volatility.
Prof Pavel Shevchenko visited ISM Tachikawa during 2-30 October 2017
Prof Pavel Shevchenko was awarded a visiting Professor position in the Institute of Statistical Mathematics in Tachikawa, Japan for 2-30 October 2017.
During the visit, Prof Shevchenko collaborated with colleagues in Japan on projects: pricing commodity futures and modelling optimal mitigation climate change policy. During the visit, collaborative links were established with researchers from the Institute of Statistical Mathematics and Centre for Global Environmental Research, and with financial risk/financial mathematics groups in Hitotsubashi University, Osaka University and Ritsumeikan University.
Special Issue Editor: Prof Pavel Shevchenko, Deadline for manuscript submissions: closed
Special Issue Editor: Prof Pavel Shevchenko
Deadline for manuscript submissions: closed
An ageing population is a major challenge for many countries, arising from a declining fertility rate and an increasing life expectancy. A longevity risk (the adverse outcome of people living longer than expected) exacerbated by declining equity returns, coupled with the record low interest rate environments, have significant implications for societies, and manifests as a systematic risk for providers of retirement income products. Accurate mortality and population projections have become critical for policymakers and industry. The aim of this Special Issue is to highlight advances in empirical results and numerical methods for quantitative modeling of risks related to ageing population problems.