DSMM: Data Science for Macro-Modeling with Financial and Economic Datasets

From datascience
(Redirected from Main Page)
Jump to: navigation, search

DSMM2016

Schedule

8:30 a.m. to 10 a.m. - WELCOME and FEIII Challenge Year One Report and Financial News 
Papers in 2016-Session1
 
10:30 a.m. to 12 noon - Networks, Agents and Ontologies
Papers in 2016-Session 2

12 noon to 1:30 p.m. - LUNCH  2016-list-of-posters
Enjoy lunch and the FEIII participant posters!

1:30 p.m. to 3 p.m. - SHORT papers and FEIII Participant Reports
Papers in 2016-Session 3
 
3:30 p.m. to 5 p.m. - FEIII Year Two Planning

Accepted DSMM Papers 2016-list-of-papers

Accepted FEIII Participant Reports 2016-list-of-posters

Overview

The DSMM 2016 workshop will explore the challenges of data science for macro-modeling with financial and/or economic datasets. The workshop will also showcase a planned multi-year Financial Entity Identification and Information Integration (FEIII) at Scale Challenge.

The promise of Big Data, linked data and social data is the availability of large scale yet granular datasets to support modeling of complex ecosystems reflecting cyber-human decision making. However, fully realizing this promise requires successful integration of heterogeneous data from a wide variety of data sources. While complex data-driven models have emerged for climate modeling or systems biology, there has been less activity in macro-modeling with multiple heterogeneous economic or financial datasets. Two trends are increasing opportunities for such macro-modeling of financial and economic ecosystems. First, public financial data is becoming increasingly available from a variety of sources, including WRDS’s CRSP, SEC EDGAR, and the Federal Reserve’s FRED. Second, Big Data infrastructures and analytical tools to support the required integration across these data sources are becoming increasingly available. Thus, an exploration of the data science challenges involved in such macro-modeling with financial and economic data is timely. Economists have had a successful history of using longitudinal datasets (US Census Bureau, Department of Labor, World Bank, etc.) to drive econometric and statistical research in finance and economics. However, such analyses fail to completely address the compelling need to analyze complex ecosystems and supply chains in their entirety. Such analytics requires dealing with multiple heterogeneous streams of data, each of which can be high in volume and variety and reflect varying degrees of veracity. Clearly, we have a classic big data challenge.

Although integrating datasets may pose technical and policy/privacy challenges, the potential benefits are immense. For example, social media data often contains features that could enhance macroeconomic statistics derived from traditional survey-driven datasets. The resulting enriched datasets could explore hypotheses with a different focus or level of granularity. The financial world is a closely interlinked Web of financial entities and networks, supply chains and financial ecosystems. Financial analysts, regulators and academic researchers recognize they must address the unprecedented and unfamiliar challenges of monitoring, integrating, and analyzing such networks and ecosystems at scale. A researcher would have to process multiple heterogeneous data streams, extract relevant information, clean it, integrate information from distinct streams, perform entity resolution, and aggregate data before they can even begin their analysis. Doing all of this creates a high barrier for financial and economic data science at scale. The benefits of addressing these challenges are immense and may result in improved tools for regulators to monitor financial systems or to set economic or fiscal policy. Additional benefits may include fundamentally new designs of market mechanisms, new ways to reach consumers, and new ways to exploit the wisdom of the crowds.

Targeted Audience: We expect attendees with an interest in information integration, data mining, knowledge representation, network and visual analytics, stream data processing, etc. The DSMM 2014 workshop, in conjunction with SIGMOD 2014, attracted a diverse group of researchers from databases, data modeling, finance, math/stat and economics. Proceedings of ACM DSMM 2014 are available here: http://dl.acm.org/citation.cfm?id=2630729

Important Dates ***** EXTENDED SUBMISSION DEADLINE *****

Submission deadline: Friday April 1, 2016
Notification to authors: Sunday May 1, 2016
Camera-ready: Friday May 13, 2016
Registration deadline: Sunday May 15, 2016
Workshop: Friday July 1, 2016

Submission

Authors are invited to submit original, unpublished research papers that are not being considered for publication in any other forum. We will accept the following types of papers:

* Regular papers that are a maximum of 6 pages will have a presentation slot.
* Extended abstracts of up to 2 pages will have a poster presentation and a short presentation slot.

Manuscripts should be submitted electronically as PDF files and be formatted using the SIGMOD camera-ready templates templates. Authors are allowed to include extra material beyond the six pages as a clearly marked appendix, which reviewers are not obliged to read.

Submission Site

https://cmt3.research.microsoft.com/DSMM2016/

Organization

Program Chairs

Doug Burdick IBM Research drburdic@us.ibm.com
Rajasekar Krishnamurthy IBM Research rajase@us.ibm.com
Louiqa Raschid University of Maryland louiqa@umiacs.umd.edu

Steering Committee

Laura Haas IBM Research lmhaas@us.ibm.com
H.V. Jagadish University of Michigan jag@umich.edu
Shiv Vaithyanathan IBM Research vaithyan@us.ibm.com

Program Committee

Sanjiv Das Santa Clara University srdas@scu.edu
Amol Deshpande University of Maryland amol@cs.umd.edu
Mark Flood Office of Financial Research mark.flood@ofr.treasury.gov
Gerard Hoberg USC hoberg@marshall.usc.edu
Vasant Honavar Pennsylvania State University vhonavar@ist.psu.edu
Panos Ipeirotis New York University panos@stern.nyu.edu
Joe Langsam University of Maryland jlangsam@rhsmith.umd.edu
Shawn Mankad University of Maryland smankad@rhsmith.umd.edu
Felix Naumann University of Potsdam felix.naumann@hpi.uni-potsdam.de
Frank Olken National Science Foundation folken@nsf.gov
Kevin Sheppard Office of Financial Research kevin.sheppard@ofr.treasury.gov
Ian Soboroff NIST ian.soboroff@nist.gov
Roger Stein CSRA and MIT steinr@mit.edu
Kunpeng Zhang University of Maryland kzhang@rhsmith.umd.edu

Financial Entity Identification and Information Integration (FEII) Challenges

The Financial Entity Identification and Information Integration (FEIII) Challenges are 
open data challenges that focus on the financial domain. Sign up to participate, 
download the data, follow the rules, submit your solution, and come talk about your 
work and future challenges at a workshop.  Our first challenge is aligning identifiers 
across databases. 

 Visit us at the NIST FEIII Challenges home page [1]

DSMM 2014

Schedule

8:30 a.m. to 10 a.m. - WELCOME and KEYNOTE and Opening Session on Financial Analytics 
Papers in Session1
 
10:30 a.m. to 12 noon - Financial Data Integration Tools and Methods and POSTER SLAM
Papers in Session 2

12 noon to 1:30 p.m. - LUNCH in the Summit Room list-of-posters
Enjoy the view and the posters!

1:30 p.m. to 3 p.m. - Financial Networks and Games and Regulatory Data
Papers in Session 3
 
3:30 p.m. to 5 p.m. - DSfin Financial Entity Resolution At Scale CHALLENGE and WRAP-UP
Session 4

Accepted Papers list-of-papers

Accepted Posters list-of-posters

Overview

Focus of the Workshop The increasing availability of Open Data from a variety of sources including the Web, social media and the government, in conjunction with the growth of Big Data infrastructures and analytics tools, provides the ability to model complex ecosystems enabling cyber-human decision making. While data-driven models have emerged for a range of challenges from climate modeling to systems biology to personalized medicine, there has been relatively, little activity in macro-modeling using multiple heterogeneous financial and economic datasets.

The real promise of Open Data and Big Data lies in the dramatically increased value gained from integrating data from multiple sources, as illustrated by the following example: The systemic risks associated with the subprime lending market and the crash of the housing market in 2007 could have been modeled through a comprehensive integration and analysis of available public datasets. For example, the datasets relevant to the home mortgage supply chain include the following: (a) regulatory documents made available by MBS issuers, publicly traded financial institutions and mutual funds; (b) subscription-based third party datasets on underlying mortgages; (c) individual home transaction data such as sales, foreclosure and tax records; (d) local economic data such as employment and income-levels; (e) financial news articles. Integrating these datasets may have provided financial analysts, regulators and academic researchers, with comprehensive models to enable risk assessment.

Economists have been the leaders in creating longitudinal panel datasets and have had a successful history of using national datasets from the Census Bureau, the Department of Labor, etc., and global datasets from the UN, World Bank, etc. Here, too, there has been much less activity in modeling that integrated multiple heterogeneous datasets. While integrating datasets may pose technical, policy and privacy challenges, the potential benefits are immense. For example, social media data often contains features that could enhance macroeconomic statistics derived from traditional survey-driven datasets. Enriching longitudinal panel datasets with social media could explore hypotheses with a different focus or level of granularity; for example, one could study the decision making of individuals whose social media profiles would reflect their beliefs, intent, interests, sentiments, opinions, and state of mind.

This workshop will explore the challenges of data science for macro-modeling with financial and/or economic datasets. Two workshops, in 2010 and 2012, brought together a diverse community of academic researchers, regulators and practitioners who articulated the range of multi-disciplinary research challenges for macro-prudential modeling of financial systemic risk. The National Bureau of Economic Research Summer Institute in 2012 offered a workshop on novel data-centric techniques that attracted both economists and computer scientists. The workshop will target attendees of these prior meetings and will build upon the solid foundation established at these prior events.

Targeted Audience: We expect a mix of paper submissions and attendees with an interest in information integration, data mining, knowledge representation, stream data processing, etc. A small number of domain specialists from finance and economics are also expected to attend.

Important Dates

Submission deadline:     EXTENDED!!! Monday March 31, 2014. EXTENDED!!!
Notification to authors: Friday May 2, 2014.
Camera-ready due:        Friday May 23, 2014.
Registration deadline: 
Workshop:                Friday June 27, 2014.

Submission Format Authors are invited to submit original, unpublished research papers that are not being considered for publication in any other forum. We will accept the following types of papers:

* Regular papers that are a maximum of 6 pages will have a presentation slot.
* Extended abstracts of up to 2 pages will have a poster presentation and a short presentation slot 
   if time permits.

Manuscripts should be submitted electronically as PDF files and be formatted using the SIGMOD camera-ready templates templates. Authors are allowed to include extra material beyond the six pages as a clearly marked appendix, which reviewers are not obliged to read.

Submission Site

https://cmt.research.microsoft.com/DSMM2014/

Organization

Program Chairs

Rajasekar Krishnamurthy IBM Research rajase@us.ibm.com
Louiqa Raschid University of Maryland louiqa@umiacs.umd.edu
Shiv Vaithyanathan IBM Research vaithyan@us.ibm.com

Steering Committee

Lise Getoor University of California Santa Cruz getoor@soe.ucsc.edu
Laura Haas IBM Research lmhaas@us.ibm.com
H.V. Jagadish University of Michigan jag@umich.edu

Program Committee

Richard Anderson Lindenwood University rganderson.stl@gmail.com
Michael Cafarella University of Michigan michjc@umich.edu
Sanjiv Das Santa Clara University srdas@scu.edu
Amol Deshpande University of Maryland amol@cs.umd.edu
Mark Flood Office of Financial Research mark.flood@treasury.gov
Juliana Freire New York University juliana.freire@nyu.edu
Gerard Hoberg University of Maryland ghoberg@rhsmith.umd.edu
Vasant Honavar Pennsylvania State University vhonavar@ist.psu.edu
Joe Langsam University of Maryland jlangsam@rhsmith.umd.edu
Shawn Mankad University of Maryland smankad@rhsmith.umd.edu
Frank Olken National Science Foundation folken@nsf.gov
Felix Naumann Hasso Plattner Institute, Germany felix.naumann@hpi.uni-potsdam.de
Christopher Ré Stanford University chrismre@cs.stanford.edu
Webmaster
Peratham Wiriyathammabhum University of Maryland peratham@cs.umd.edu

Getting started