|
|
Data Mining in Finance
is a new course that
develops links between Information Systems, Statistics and Finance. It covers
fundamentals of modern modeling, knowledge discovery, and data mining techniques.
Among the topics surveyed are neural networks, hidden Markov models, and clustering
techniques. This course highlights the assumptions of different model
classes, stresses the critical evaluation and comparison with established
methods, and offers techniques for interpreting the results. These methods
are useful for current problems in finance including measuring and understanding
risk, and building and evaluating trading models. Seven hands-on assignments,
based on MATLAB, help develop intuitions and serve as starting points to
solve real problems. Possibilities of in-depth group projects in conjunction
with major financial firms exist. Towards the end of the semester, several
Wall Street practitioners present their perspectives on data mining in
finance.
Prerequisites: One of the following two courses is required:
- Statistical Inference and Regression Analysis
(B90.3302)
- Regression
and Multivariate Data Analysis (B90.2301 = B90.3311)
Furthermore, some programming
experience (in any language) is helpful.
Information
about related courses at Stern.
|
|
|
The logistics
page contains the general information about the instructor and teaching
assistant, readings, software, and the grading for this course.
If you are looking for specific files, the following links will take you
directly to the directories:
|
|
|
|
#
|
Date
|
Day
|
Topic
|
Readings
|
|
1
|
1/20/99
|
Wed
|
Introduction: Data Mining and Data Snooping
|
|
|
2
|
1/25/99
|
Mon
|
Learning
from Data; Seven Steps of Modeling
|
|
|
3
|
1/27/99
|
Wed
|
Bootstrapping
|
|
|
4
|
2/1/99
|
Mon
|
Evaluation,
Model Risk
|
|
|
5
|
2/3/99
|
Wed
|
Data
and Representation, Linear Models
|
|
|
6
|
2/8/99
|
Mon
|
Nonlinear
Models (see also the Information
Theory notes)
|
|
|
7
|
2/10/99
|
Wed
|
Neural Network Introduction: Yield
Curve Demo
|
|
|
PD
|
2/15/99
|
Mon
|
(no class)
|
|
|
8
|
2/17/99
|
Wed
|
Neural
Network Learning: Error Backpropagation, Overfitting Problem
|
|
|
9
|
2/22/99
|
Mon
|
Neural
Network Theory: Maximum
Likelihood Framework
|
|
|
10
|
2/24/99
|
Wed
|
Predicting
Conditional Normal Distributions (Local Error Bars)
|
|
|
11
|
3/1/99
|
Mon
|
Predicting
Conditional Non-normal Distributions (Gated Experts)
|
Mangeas
|
|
12
|
3/3/99
|
Wed
|
Predicting
Quantiles, Tails of Distributions, and Rare Events
|
Chang
|
|
13
|
3/8/99
|
Mon
|
Extracting
Risk-Neutral Densities from Options Prices (Mixture Binomial Trees)
|
Pirkner
|
|
14
|
3/10/99
|
Wed
|
Summary of Approaches to Nonlinear Prediction and Risk
Management
|
|
|
SB
|
3/15/99
|
Mon
|
(no class)
|
|
|
SB
|
3/17/99
|
Wed
|
(no class)
|
|
|
15
|
3/22/99
|
Mon
|
Reducing
the Dimensionality of the Data (Principal Component Analysis)
|
B310-317,454-456
C182-186,431-436
|
|
16
|
3/24/99
|
Wed
|
Discovering
Statistically Independent Sources (Independent Component Analysis)
|
Back
|
|
17
|
3/29/99
|
Mon
|
Doug Martin, MathSoft, Trellis Graphics and Robust
Approaches for Financial Modeling
|
|
|
18
|
3/31/99
|
Wed
|
Fidelio Tata, Vice President, CSFB, Mining
for Short-Term Micro-Arbitrage
|
|
|
19
|
4/5/99
|
Mon
|
Discovering Hidden States in the Market (Hidden Markov
Experts)
|
|
|
20
|
4/7/99
|
Wed
|
Vasant Dhar, How Decisions Makers View Data
Mining in Finance
|
|
|
WS
|
4/10/99
|
Sat
|
Georg Zimmermann, Building
Trading Models: Tricks of the Trade [9am-5pm]
|
|
|
21
|
4/12/99
|
Mon
|
Classification
|
|
|
22
|
4/14/99
|
Wed
|
Credit Risk and Bankruptcy Prediction
|
|
|
23
|
4/19/99
|
Mon
|
David Modest, Principal, Long Term Capital Management, The Crisis at Long Term Capital Management: An Insider's View
|
|
|
24
|
4/21/99
|
Wed
|
Style Analysis: Traders (Clustering)
|
|
|
25
|
4/26/99
|
Mon
|
Style Analysis: Funds
|
|
|
26
|
4/28/99
|
Wed
|
Allan Grody, Implementing Enterprise-Wide Risk Management Systems
|
|
|
27
|
5/3/99
|
Mon
|
Review
|
|
|
F
|
5/10/99
|
Mon
|
Final
|
|
|
