Informs 2015

123 / 552

INFORMS Philadelphia – 2015
121
SD05
05-Room 305, Marriott
Tutorial: Collecting and Analyzing Twitter
Data with Python
Cluster: Social Media Analytics
Invited Session
Chair: Chris Marks, MIT, 50 Memorial Drive, Cambridge, MA, 02139,
United States of America,
1 - Tutorial: Collecting and Analyzing Twitter Data with Python
Chris Marks, MIT, 50 Memorial Drive, Cambridge, MA, 02139,
United States of America, , Tauhid Zaman
We present a few methodologies and working libraries in Python that enable an
analyst to retrieve information through the Twitter API and provide quick-turn
exploratory analyses. These analyses include spatial analyses of data with geo-
location, network analyses, and analyses of the timeline and scale of information
cascades.
SD06
06-Room 306, Marriott
Asset Returns and Portfolio Management
Sponsor: Financial Services
Sponsored Session
Chair: Xianhua Peng, Assistant Professor, Hong Kong University of
Science and Technology, Department of Mathematics, Hong Kong,
Hong Kong - PRC,
1 - Three Fund Portfolio Rules and the
Mean-variance-skewness Frontier
Luis Chavez-bedoya, Professor, ESAN University,
Alonso de Molina 1652, Surco, Lima, Lima 33, Peru,
, John Birge
Assuming that asset returns follow a generalized hyperbolic (GH) distribution, we
study the optimal solution of a particular portfolio optimization problem and
relate it to common three-fund rules and to the mean-variance-skewness frontier
of Mencia and Sentana (2009). Finally, we describe the optimal portfolio in terms
of the location, dispersion and skewness parameters of the GH distribution.
2 - Jumps in Equity Returns Before and During the Recent Financial
Crisis: A Bayesian Analysis
Haowen Zhong, Department of Industrial Engineering and
Operations Research, Columbia University, 500 West 120th
Street, New York, United States of America,
Cindy Yu, Steven Kou
We attempt to answer two questions in this talk. (i) How did jumps in equity
returns change after the 2008-2009 financial crisis? (ii) Can the performance of
affine jump-diffusion models be improved if jump sizes are with tails heavier than
those of the normal distribution?
3 - Separating Skilled and Unskilled Fund Managers by
Contract Design
Sang Hu, Risk Management Institute, National University of
Singapore, 21 Heng Mui Keng Terrace, Icube Building #04-03,
Singapore, , Steven Kou, Xuedong He
Foster and Young (2010) shows that it is very difficult to design performance fee
contracts that reward skilled fund managers while screening out unskilled fund
managers. We show that (1) if there is a liquidation boundary, meaning that the
fund investors liquidate their stake as soon as the fund returns hit the boundary,
and (2) the fund manager has to use his/her own money to set up a deposit to
offset the potential losses from investors, then skilled and unskilled managers can
be separated.
4 - Optimal Exit Time from Casino Gambling: Why a Lucky Coin
and a Good Memory Matter
Xuedong He, Assistant Professor, Department of Industrial
Engineering and Operations Research, Columbia University,
Xunyu Zhou, Sang Hu, Jan Obloj
We consider a dynamic casino gambling model and study the optimal strategy of a
gambler with cumulative prospect theory (CPT) preferences. We develop a
systematic and analytical approach to finding the gambler’s optimal strategy,
illustrate how Markovian strategies can be strictly improved by reviewing the
betting history or by tossing an independent coin, and explain that the
improvement generated by using randomized strategies results from the lack of
quasi-convexity of CPT preferences.
SD07
07-Room 307, Marriott
Systemic Risk in Financial Networks
Cluster: Risk Management
Invited Session
Chair: Luitgard Veraart, Associate Professor, London School of
Economics and Political Science, Houghton Street, London,
WC2A 2AE, United Kingdom,
1 - Control of Interbank Contagion under Partial Information
Andreea Minca, Cornell University, Ithaca,
United States of America,
We consider a core-periphery financial network in which links lead to the
creation of projects in the outside economy but make banks prone to contagion
risk. The controller seeks to maximize the value of the financial system under
partial information. Our results show that the value of the system depends on the
connectivity in a non-monotonous way. It may be optimal to increase the rate of
intervention in the peripheral banks rather than in core banks.
2 - The Joint Impact of Bankruptcy Costs, Fire Sales and Cross-
holdings on Systemic Risk
Kerstin Awiszus, Leibniz Universität Hannover, Welfengarten 1,
Hannover, 30167, Germany,
Stefan Weber
The paper presents a comprehensive model of a banking system that integrates
network effects, bankruptcy costs, fire sales and cross-holdings. For the integrated
financial market we prove the existence of a price-payment equilibrium and
design an algorithm for the computation of the greatest and the least equilibrium.
The number of defaults corresponding to the greatest price-payment equilibrium
is analyzed in several comparative case studies.
3 - Systemic Risk Measures
Zachary Feinstein, Assistant Professor, Washington University in
St. Louis, 1 Brookings Drive, CB 1042, St. Louis, MO, 63130,
United States of America, Birgit Rudloff,
Stefan Weber
We propose a framework for measuring systemic risk in terms of capital
endowments of the financial firms. Their construction requires two ingredients: a
cash flow or value model that assigns to the capital allocations of the entities in
the system a relevant stochastic outcome, and an acceptability criterion, i.e. those
outcomes that are acceptable from the point of view of a regulatory authority.
Systemic risk is measured by the set of allocations of capital that lead to
acceptable outcomes.
4 - A Bayesian Methodology for Systemic Risk Assessment in
Financial Networks
Luitgard Veraart, Associate Professor, London School of
Economics and Political Science, Houghton Street, London,
WC2A 2AE, United Kingdom, Axel Gandy
We study the interbank market as a network in which the nodes represent banks
and the directed edges represent interbank liabilities. In practice, the network of
interbank liabilities is not fully observable. We present a Bayesian methodology to
deal with this lack of information when performing stress tests on such interbank
networks.
SD08
08-Room 308, Marriott
Surveillance
Sponsor: Telecommunications
Sponsored Session
Chair: Fabio D’Andreagiovanni, Senior Researcher, Konrad-Zuse-
Zentrum für Informationstechnik, Takustr. 7, Berlin, Germany,
1 - An Efficient Branch-column-cut Algorithm for Capacitated
Survivable Network Design
Richard Chen, Principal Member Of Technical Staff, Sandia
National Laboratories, 7011 East Ave, Livermore, CA, 94550,
United States of America, , Cynthia Phillips
We consider a capacitated survivable network design problem that requires a
feasible multicommodity flow to exist after any k edge failures. Existing
approaches generate violated inequalities based on static failure scenarios. We
present new valid inequalities that dynamically cover all failure scenarios
pertaining to a given vulnerability. We then present a branch-column-cut
algorithm and empirical studies on SNDlib and random instances to demonstrate
the effectiveness of our approach.
SD08