CF99 Some information about NYU's Stern School of Business

• Derivatives: What's New?
• Market Risk: Advances and Challenges
• Data Mining in Finance

• Exploiting Nonlinearities in Financial Data: Methodologies and Applications

The rest of this page contains some information about computational finance and financial engineering at Stern:
 

The NYU Center for Information Intensive Organizations (CIIS)

The Knowledge Discovery, Modeling and Data Mining Group

The NYU Salomon Center for Research in Financial Institutions and Markets

The Center is a forum for the generation, dissemination and application of ideas and knowledge in academia and business. Combining world-class research with a thorough understanding of today's business needs, the center explores state-of-the-art applications in business and contributes to theoretical progress, demonstrated by the broad set of publications in the top journals. The center focuses on longer-term research that generates transferable theoretical and conceptual insights into issues of relevance for business and commerce in the widest sense.

The Center provides an interdisciplinary and entrepreneurial environment for faculty to obtain research funding and enhance their international reputation without having to bear the overhead of managing projects and coordinating events. The Affiliates program serves as a structure through which a number of U.S. and international firms support the activities. Each Affiliate commits a limited amount of funds which underwrites research and/or conferences conducted under the auspices of the Center. Participation as an Affiliate of the Center is by invitation.

Affiliates are viewed as partners who not only financially support research, but actively participate in defining the mission. This coupling between the Affiliates and the Center is facilitated by events ranging from informal luncheons where practices, ideas and visions are openly discussed, executive round tables on topics (e.g., Networked Knowledge Organizations), and symposia (e.g., Information Technology on the Financial Services Industries, joint with Operations Management, April 1998) . These events are good starting points for joint projects, facilitate interactions between Affiliates, faculty and students, and also provide a forum for informal exchanges for Affiliates with peers from other companies.

Other benefits for affiliates include:

1. Affiliates have access to Stern's faculty. CIIS is a school-wide center in which faculty members from every department at Stern participate. Stern is very open to new and interesting statistical approaches to artificial intelligence, modern modeling techniques, knowledge discovery and data mining. The Center naturally brings together information systems, finance, marketing, statistics and operations research. The size, talent and diversity of the faculty provides an incredible intellectual capital to outside organizations.

2. Affiliates have access to Stern's students. Affiliates are invited to participate in formal recruiting activities such as Careers Nights. In the area of computational finance, Stern offers a highly quantitative MBA Financial Engineering Track, a Masters of Science in Statistics with Specialization in Mathematical Finance, and of course PhD programs in all departments. Furthermore, NYU's Masters of Science in Information Systems, a joint program between the Computer Science Department at the Courant Institute and the Information Systems Department at the Stern School of Business uniquely combines technical skills and business knowledge and includes on-the-job experience through local consulting projects.

3. Affiliates are invited to the Center's conferences, symposia, workshops and seminars at reduced rates or without charge. Examples include:

• Learning from Data in Finance and Business, a one-day workshop (March 1997) that focused on the challenges facing data intensive organizations in the current transformation from passive collectors to active explorers and exploiters of data. Professors Dhar and Weigend presented a framework for how companies with increasing access to information can benefit from data mining methods by learning about their markets, customers, suppliers, internal business processes and operations. Well attended by academics, practitioners and decision makers, this workshop balanced research results with applications and products jointly developed with Affiliate firms;
• Computational Finance (CF99, January 1999), the sixth in a series of annual conferences previously called Neural Networks in the Capital Markets held at the London Business School and at the California Institute of Technology. The expanding set of methods has moved this meeting from its original emphasis on neural networks to a broader spectrum of computationally intensive approaches in finance with applications to risk management, asset allocation, dynamic trading and hedging strategies, forecasting, and option pricing. This fully refereed conference emphasizes in-depth analysis and comparative evaluation with established approaches.

• The MBA Refresher targets decision makers with broad functional responsibilities whose success depends on staying current. Emphasis is placed on gaining insight through conceptual, intellectually rich and visionary teaching. The first of two weeks (February 1999) is an integrated set of courses on the Information Economy. The second week (March 1999) consists of focused half-day sessions including Statistical Tools for Measuring Financial Performance (Prof. Tenenbein), Competitive Marketing Strategies (Prof. Czepiel), and Data Mining (Prof. Weigend);
• Exploiting Nonlinearities in Financial Data: Methodologies and Applications brings state-of-the-art academic knowledge to a technically sophisticated audience of strategists and quants. Taught by Professors Boudouk, Richardson, Weigend and Whitelaw, this intense two-day course (April 1999) is part of the Frontiers in Finance series.

• Seven Methods for Transforming Data into Business Intelligence. Dhar and Stein. Prentice-Hall;
• Data Mining in Finance (Special issue of the International Journal of Neural Systems 8). Srivastava and Weigend;
• Decision Technologies for Financial Engineering. Weigend, Abu-Mostafa and Refenes. World Scientific.

For further information about the Center for Information Intensive Organizations and its Affiliates program, please contact
Prof. Edward A. Stohr. E-mail: estohr@stern.nyu.edu; Phone: +1 (212) 998-0836.
Administration: Mary Anne Seaton. E-mail: mseaton@stern.nyu.edu; Phone: +1 (212) 998-0848. Fax +1 (212) 995-4228.
Web: http://eldorado.stern.nyu.edu/~center

We live in a world where data is constantly collected about us and our behavior: the places we visit, the phone calls we make, the goods we buy, the financial transactions we perform. In response to this explosion of data, a new field called knowledge discovery and data mining has emerged. It focuses on the process of discovering previously unknown, valid and comprehensible knowledge from large data sets. The goal is to apply this knowledge to decision making. Data mining integrates concepts from fields such as artificial intelligence, statistics, database and decision theory, and provides powerful tools that can reveal complex and hidden relationships in large amounts of data.

Data mining has a long tradition at Stern, beginning with the early work of several members of the IS department in database management and artificial intelligence. Professors Dhar and Tuzhilin started a data mining initiative in 1990 with a large market research company that was in the business of creating "market intelligence" primarily for consumer product companies. This early effort brought in an NSF grant to Professors Clifford, Dhar and Tuzhilin.

Subsequently, the data mining effort in the department has proceeded along a number of directions. Professor Dhar founded the data mining group at Morgan Stanley, led ensuing projects in trading and risk management, as well as in customer and salesforce profiling. After two years on Wall Street he is back at Stern. He currently investigates how various sources of equity information related to "expectations" and "value" are gradually assimilated by the market.

Professor Tuzhilin's research focuses on one-to-one and web-based marketing. The e-Butler project develops a personal shopping assistant system that analyzes customers' purchasing histories and provides them with purchasing recommendations based on this analysis as well as on information from various manufacturers and retailers. He contributed significantly to the theoretical progress on issues such as what makes patterns "interesting".

Professor Weigend joined the department in 1997, bringing with him a history of research on model building and evaluation. He currently focuses on financial time series analysis. He co-directs with Prof. Figlewski an extensive research program on US Treasury bond futures that mines three years of data of transactions of that market.

In the last years, the group developed:

• A recommendation system called e-Butler that provides its customers with purchasing recommendations in a truly one-to-one manner
• Models that continuously monitor market or customer data and act when the information is sufficient;
• Systems that discover unexpected and actionable patterns in data and enhance the knowledge of decision makers;
• Predictive models for analyzing how information is absorbed by the market;
• New methods for discovering unexpected temporal patterns and applying them to detect computer system intruders;
• An advanced framework for risk evaluation with applications to tactical asset allocation and risk management;
• Systems that blend supervised learning (prediction) and unsupervised learning (segmentation) with applications to finance (stock picking), accounting (earnings announcements) and marketing.

• Knowledge Systems in Organizations, taught by Prof. Dhar, is a case-oriented introduction to fundamental artificial intelligence techniques showing how they are being applied in business. The course covers all major techniques such as tree induction, neural networks and genetic algorithms, and demonstrates with software how different problems can be formulated and solved using such methods;
• Data Mining in Finance, taught by Prof. Weigend, is a cutting-edge course that covers the foundations of knowledge discovery, and nonlinear modeling as well as specific methods including neural networks, graphical models, evolutionary programming and clustering techniques. The course focuses on current problems in finance such as building and evaluating trading models and managing risk. Assignments use industrial state-of-the art data mining tools on various platforms. The course was awarded a 1998 NYU Curricular Development Challenge Grant.

The purpose of the NYU Salomon Center is to focus high quality research attention on the global financial services industry and its principal institutions. The Center underwrites applied academic research, conducts conferences for scholars and practitioners, engages in specialized executive education, and undertakes a variety of publications intended to contribute to understanding this critical sector of the domestic and international economy. In all of its work, the Center draws upon and supports the faculty of New York University and the Stern School of Business. The Center is intended to serve as an important link between scholars, practitioners and regulators concerned with financial institutions.

The Center distributes faculty working papers which the authors think will benefit from a broader audience of practitioners and public policymakers.

For further information about the NYU Salomon Center, please contact Prof. Ingo Walter.
E-mail: iwalter@stern.nyu.edu; Phone: +1 (212) 998-0707.
Administration: Mary Jaffier. E-mail: mjaffier@stern.nyu.edu; Phone: +1 212 998-0700; Fax: +1 212 995-4220.
Web: http://www.stern.nyu.edu/salomon
Of particular interest might be the newly founded Derivatives Research Project, part of the NYU Salomon Center..

For further information about the Derivatives Research Project, please contact Prof. Stephen Figlewski.
E-mail: sfiglews@stern.nyu.edu; Phone: +1 (212) 998-0712; Fax: +1 (212) 995-4220.

Responsible for this page: Andreas Weigend. Any feedback is welcome.
URL: http://www-psych.stanford.edu/~andreas/CF99