Andreas
S. Weigend, PhD
|
+1 (917) 697-3800
|
303 East Pike Street #401
Seattle, WA 98122, USA
|
aweigend@stanford.edu
www.stanford.edu/~aweigend
|
Amazon.com, Chief Scientist Seattle, WA
- Responsible for
research in machine learning and computational marketing
- In charge of development
and strategic application of analytic approaches throughout the firm
- Applications include real-time
predictions of customer intent and satisfaction, actionable models of
shopping behavior, personalization and long-term optimization of pricing
and promotions
- Point person for relations
with academic and other external researchers
Stanford University, Department of Statistics, Visiting Professor Stanford, CA
- Teaching “Data Mining and
E-Business” (Statistics252, 3 units)
Strategic
- Leverage information
technology and the internet to create value from data
- Transfer relevant
scientific research from academia to business
Scientific and Technical
- Machine learning, data
mining and knowledge discovery
- Time series analysis
and prediction
- Risk management,
quantitative and behavioral finance
- Information retrieval
and visualization
Experience and Environments
|
Academic
- Business School (New
York University, Associate Professor; 3 years full-time;
Executive MBA faculty at China Europe International Business School –
CEIBS; 1 year)
- Computer Science (University of Colorado, Assistant Professor;
4 years full-time)
Research
- Xerox PARC (Palo Alto Research Center, 2 years full-time)
- Published six books and
more than 100 scientific papers, some cited more than 300 times
Entrepreneurship
- Startups (Shockmarket,
Moodlogic; 2 years full-time)
- Consulting (data
mining, behavioral analytics, trading and risk models; 10 years part-time)
Stanford University
|
PhD Thesis on Neural Networks for Time Series Analysis
and Prediction
Advisors:
D. E.
Rumelhart, J. H.
Friedman,
W. B.
Arthur, B. A.
Huberman, W. A.
Little
|
Stanford, CA
(86-91)
PhD in Physics
MS in Physics
|
Bonn University
|
Masters
Thesis on Comparing Computer Simulations of Elementary Particle Physics with
Experimental Data at CERN
|
Bonn, Germany
(83-86) Diplom-Physiker
|
Trinity College,
Cambridge
|
Graduate
coursework in Physics and Philosophy
|
Cambridge, UK (82-83)
|
Karlsruhe University
|
Undergraduate
degrees in Electrical Engineering and Physics
|
Karlsruhe, Germany
(79-82) Vordiplom
|
Previous
Full-Time Positions
|
ShockMarket
Corporation (Chief Scientist)
|
Palo Alto, CA (00-01)
|
A financial information services startup providing information products
and market sentiment
Funded by Deutsche Bank, D. E. Shaw,
Odeon Capital and others, currently “mothballed”
Research and
Development
- Directed
interdisciplinary team to:
- Develop analytics
based on real-time transactions from online brokerages
- Design core products
based on quantitative data analysis and behavioral finance concepts
- Verify validity of
data collection and results using advanced statistical techniques
- Assembled and managed
board of scientific advisors (D. Kahneman, T. Odean, N. Schwarz,
R. H. Thaler)
Corporate
Activities
- Worked closely with CEO
to define strategy and vision
- Developed partnerships
with hedge funds, distribution channels, and financial institutions
- Presented to major
brokerages, financial and information services companies, and venture
firms
MoodLogic,
Inc. (Chief Scientist) (formerly Emotioneering,
Inc.)
|
San Francisco, CA (99-00)
|
A music technology startup providing software systems and data services
for audio consumer electronics, music desktop applications,
and music subscription services
Research and
Development
- Designed music
navigation system based on music perception and digital fingerprinting
- Led initial research
and developed successful prototype
Corporate
Activities
- Created long-term
vision for managing, programming, and discovering music
- Built interdisciplinary
team (hired first eight employees)
New York University, Stern School of Business
|
New York, NY (97-00)
|
Associate
Professor of Information Systems
(Sabbatical
at Stanford University, Department of Statistics,
99-01)
- Directed research group
on data mining and knowledge discovery
- Received New York University Teaching Award for course on Data
Mining in Finance
University of Colorado at Boulder
|
Boulder, CO (93-96)
|
Assistant
Professor of Computer Science and Cognitive Science
- Founded research group
on time series analysis and prediction
- Taught courses on
artificial intelligence, neural networks, and music cognition
Xerox Palo Alto Research Center (PARC)
|
Palo Alto, CA (91-93)
|
Member of
Research Staff, Machine Perception Group
- Invented architecture
for hierarchical classification of text documents
- Applied neural networks
to optical character recognition
Yodlee, Inc.
|
Redwood Shores, CA (02)
|
Led team to develop strategy for data and
information products based on account aggregation
Lava Trading,
Inc
|
New York, NY (02)
|
Presented value-added products and new order types based
on real-time analytics on direct trading data
Grantham, Mayo,
Van Otterloo & Co. LLC
|
Boston, MA (98-99)
|
Implemented and evaluated Hidden Markov Models for
trading strategies, now used in production
J.P. Morgan
|
New York, NY (95-97)
|
Developed and delivered model for volatility
prediction
Nikko Securities
|
Tokyo, Japan (96)
|
Built trading model for Nikkei 225 index
Prediction
Company
|
Santa Fe, NM (96)
|
Assessed novel machine learning technologies for
statistical arbitrage
Union Bank of Switzerland
|
Zurich, Switzerland (95-96)
|
Invented information radar to alert investors
of relevant trends and events
Morgan Stanley
|
New York, NY (95-96)
|
Developed neural network to optimize Sharpe ratio in
trading model
Goldman Sachs
|
New York, NY (93-95)
|
Evaluated use of neural networks for financial time
series prediction
Other engagements included the Swiss Stock Exchange (Zurich),
Shanghai Credit Information Systems, Stockstore (Breda,
Netherlands), Bank of
China (Beijing), and Bank of
Thailand (Bangkok).
Consulting: Non-Financial
|
Bertelsmann
Venture Capital
|
San Francisco, CA, and Hamburg, Germany (01-02)
|
Performed due diligence on technology start-ups
Opion,
Inc.
|
Herndon, VA (00-01)
|
Designed algorithms for identifying opinion leaders
and trends from message boards
Acxiom
Corp.
|
Little Rock, AR (00)
|
Developed strategy for direct marketing on the Web
enhancing demographics with online behavioral data
Interval
Research Corp.
|
Palo Alto, CA (00)
|
Wrote research proposal for targeted advertising on
cable television
TextWise LLC
|
Syracuse, NY (95)
|
Unified diverse sources of relevance assessment for
text mining
Siemens
Corporate Technology
|
Munich, Germany (91-98)
|
Innovated time series analysis software now used
in-house and in consulting
Other
engagements included BHP Research (Melbourne), Deutsche Bahn AG (German
Railway, Frankfurt), Electricité de France (Paris), Yahoo (Mountain View), Zone
Reactor (Los Angeles), and the CIA.
- Startups
- Hedge funds
- Stanford University’s Asia Technology
Initiative
Awards
and Publications (Selection)
|
- IBM Partnership Award for work on Discovering Trading Styles in
Financial Transactions
- National Science Foundation (NSF) and the Air Force Office of
Scientific Research (AFOSR)
awards and grants for work on Time Series Prediction
- German National Scholarship Foundation (Studienstiftung des
Deutschen Volkes), and German
Academic Exchange Service (Deutscher Akademischer Autauschdienst, DAAD)
scholarships for
entire undergraduate and graduate education
- Baden-Württemberg State Award for best undergraduate degree
- Computational Finance. (1999) Abu-Mostafa, Y. S., B. LeBaron, A. W. Lo, and A. S. Weigend (Eds.) Proceedings of the
Sixth International Conference on Computational Finance (CF99, New York,
January 1999). Cambridge, MA: MIT Press.
- Decision Technologies
for Financial Engineering. (1997) Weigend, A. S., Y. S. Abu-Mostafa, and A.-P. N. Refenes (Eds.) Proceedings of the
Fourth International Conference on Neural Networks in the Capital Markets
(NNCM'96, Pasadena, November 1996). Singapore: World Scientific.
- Time Series Prediction:
Forecasting the Future and Understanding the Past. (1994) Weigend, A. S., and N. A. Gershenfeld (Eds.) Santa Fe Institute
Studies in the Sciences of Complexity XV; Proceedings of the NATO Advanced
Research Workshop on Comparative Time Series Analysis (Santa Fe, May 1992). Reading, MA: Addison-Wesley.
- Predicting Daily Probability Distributions of S&P500 Returns
(2000) Weigend, A. S., and S. Shi. Journal of Forecasting 19, p. 375-392.
- Data Mining for Features Using Scale-Sensitive Gated Experts
(1999) Srivastava, A. N., R. Su, and A. S. Weigend. IEEE
Transactions on Pattern Analysis and Machine Intelligence 21, p. 1268-1279.
- Exploiting Hierarchy in Text Categorization (1999) Weigend, A. S., E. D. Wiener, and J. O. Pedersen. Information Retrieval 1, p. 193-216.
- A Bootstrap Evaluation of the Effect of Data Splitting on
Financial Time Series (1998) LeBaron, B., and A. S. Weigend. IEEE
Transactions on Neural Networks 9, p. 213-220.
- Exploiting Local Relations as Soft Constraints to Improve
Forecasting (1998) Weigend, A. S., and H. G. Zimmermann. Journal
of Computational Intelligence in Finance 6, p. 14-23.
- A First Application of Independent Component Analysis to
Extracting Structure from Stock Returns (1997) Back, A. D., and A. S. Weigend. International
Journal of Neural Systems 8, p. 473-484.
- Nonlinear Trading Models Through Sharpe Ratio Maximization (1997)
Choey, M., and A. S. Weigend. International
Journal of Neural Systems 8, p. 417-431.
- Modeling Volatility Using State Space Models (1997) Timmer, J., and A. S. Weigend. International
Journal of Neural Systems 8, p. 385-398.
- Time Series Analysis and Prediction using Gated Experts with
Application to Energy Demand Forecasts (1996) Weigend, A. S. Applied
Artificial Intelligence 10, p. 583-624.
- Predicting Conditional Probability Distributions: A Connectionist
Approach (1995) Weigend, A. S., and A. N. Srivastava. International
Journal of Neural Systems 6, p. 109-118.
- Paradigm Change in Prediction (1994) Weigend, A. S. Philosophical
Transactions of the Royal Society, Series A (Physical Sciences) 348, p. 405-420 (with
discussion).
- Bayesian Back-Propagation (1991) Buntine, W. L., and A. S. Weigend. Complex
Systems 5, p. 603-643.
- Predicting the Future: A Connectionist Approach (1990) Weigend, A. S., B. A. Huberman, and D. E. Rumelhart. International
Journal of Neural Systems 1, p. 193-209.
The
full list of publications is available at www.weigend.com/publications