Statistical Arbitrage Ying Chen, Leonardo Bachega Yandong Guo, Xing Liu February, 2010.

Slides:



Advertisements
Similar presentations
PCA Data. PCA Data minus mean Eigenvectors Compressed Data.
Advertisements

Scientific Computing QR Factorization Part 2 – Algorithm to Find Eigenvalues.
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
Tensors and Component Analysis Musawir Ali. Tensor: Generalization of an n-dimensional array Vector: order-1 tensor Matrix: order-2 tensor Order-3 tensor.
Factor Analysis Continued
Statistical Arbitrage Team Leo, Ying, Yandong, Xing.
Chapter 21 Value at Risk Options, Futures, and Other Derivatives, 8th Edition, Copyright © John C. Hull 2012.
Chapter 21 Value at Risk Options, Futures, and Other Derivatives, 8th Edition, Copyright © John C. Hull 2012.
“Real-time” Transient Detection Algorithms Dr. Kang Hyeun Ji, Thomas Herring MIT.
Principal component analysis (PCA)
Financial Networks with Static and dynamic thresholds Tian Qiu Nanchang Hangkong University.
Principal Component Analysis (PCA) Principal component analysis (PCA) creates new variables (components) that consist of uncorrelated, linear combinations.
Improved estimation of covariance matrix for portfolio optimization - Priyanka Agarwal - Rez Chowdhury - Dzung Du - Nathan Mullen - Ka Ki Ng.
Rajesh Shekhar Data Mining Prof. Chris Volinsky. ◦ Use Data Mining techniques to build a portfolio with superior return/risk characteristics using technical.
PREDICTABILITY OF NON- LINEAR TRADING RULES IN THE US STOCK MARKET CHONG & LAM 2010.
Risk Management Stochastic Finance 2004 Autumn School João Duque September 2004.
Dimension Reduction and Feature Selection Craig A. Struble, Ph.D. Department of Mathematics, Statistics, and Computer Science Marquette University.
Clustering In Large Graphs And Matrices Petros Drineas, Alan Frieze, Ravi Kannan, Santosh Vempala, V. Vinay Presented by Eric Anderson.
MARKET SCAN TRADER A basic tool to reduce the markets complexity and make a short list of assets to invest. USERS designed for: Private Investors Professional.
Statistical Arbitrage in the U.S. Equities Market.
Ordinary least squares regression (OLS)
PCA Channel Student: Fangming JI u Supervisor: Professor Tom Geoden.
© 2014 CY Lin, Columbia University E6893 Big Data Analytics – Lecture 4: Big Data Analytics Algorithms 1 E6893 Big Data Analytics: Financial Market Volatility.
Duan Wang Center for Polymer Studies, Boston University Advisor: H. Eugene Stanley.
Digital Image Processing Final Project Compression Using DFT, DCT, Hadamard and SVD Transforms Zvi Devir and Assaf Eden.
Principal Component Analysis Principles and Application.
Statistical Physics Approaches to Financial Fluctuations Fengzhong Wang Advisor: H. Eugene Stanley Dec 13, 2007 Collaborators: Philipp Weber, Woo-Sung.
GROUP 5. Outline  Weekly Group Update  Update on Table 6 (2007 paper)  Update on Table 2 (2007 paper)  Plans for the 2008 paper.
Options, Futures, and Other Derivatives 6 th Edition, Copyright © John C. Hull Chapter 18 Value at Risk.
Statistical Arbitrage Ying Chen, Leonardo Bachega Yandong Guo, Xing Liu March, 2010.
Presented By Wanchen Lu 2/25/2013
PCA Example Air pollution in 41 cities in the USA.
PROFESSIONAL ASSET MANAGEMENT 1. Basic Categories Private Management: Clients each have a separate account {popular with institutions} Investor 1 Investor.
PROFESSIONAL ASSET MANAGEMENT 1. Basic Categories Private Management: Clients each have a separate account {popular with institutions} Investor 1 Investor.
PROFESSIONAL ASSET MANAGEMENT 1. Basic Categories Private Management: Clients each have a separate account {popular with institutions} Investor 1 Investor.
GROUP 5. Outline  Weekly Group Update  Information gathered this week  Current road blocks  Goals for next week.
Tutorial th Nov. Outline Hints for assignment 3 Score of assignment 2 (distributed in class)
Principal Component Analysis: Preliminary Studies Émille E. O. Ishida IF - UFRJ First Rio-Saclay Meeting: Physics Beyond the Standard Model Rio de Janeiro.
Finance 663 – International Finance Passive / Active Strategy on the Euro Stoxx 50 Index.
Statistical Arbitrage Team Xing Liu, Leo, Ying, Yandong.
Technical Report of Web Mining Group Presented by: Mohsen Kamyar Ferdowsi University of Mashhad, WTLab.
Symmetry Definition: Measures of Symmetry
Chapter 8 Stock Valuation (Homework: 4, 13, 21 & 23)
Reduces time complexity: Less computation Reduces space complexity: Less parameters Simpler models are more robust on small datasets More interpretable;
Value at Risk Chapter 20 Options, Futures, and Other Derivatives, 7th International Edition, Copyright © John C. Hull 2008.
Initial Stock Analysis Andrew Bentley February 8, 2012.
METHOD OF STEEPEST DESCENT ELE Adaptive Signal Processing1 Week 5.
Math 285 Project Diffusion Maps Xiaoyan Chong Department of Mathematics and Statistics San Jose State University.
Principal Component Analysis Zelin Jia Shengbin Lin 10/20/2015.
Principal Component Analysis (PCA).
Market analysis for the S&P500 Giulio Genovese Tuesday, December
Covariance Estimation For Markowitz Portfolio Optimization Ka Ki Ng Nathan Mullen Priyanka Agarwal Dzung Du Rezwanuzzaman Chowdhury 3/10/20101.
Lecture Note 1 – Linear Algebra Shuaiqiang Wang Department of CS & IS University of Jyväskylä
Correlation and Market Returns Mingwei Lei.  It is often said that correlations between stocks increases when the market is tanking  My goal is to empirically.
Chapter 15: Classification of Time- Embedded EEG Using Short-Time Principal Component Analysis by Nguyen Duc Thang 5/2009.
ONETICK ® Accelerating Quant Research and Trading Principal Component Analysis & Multi-Factor Modeling Tests with OneTick & R Historical & Real-Time 7.
The Capacity of Trading Strategies Landier (TSE), Simon (CFM), Thesmar (HEC) AFA 2016, San Francisco.
Data Science Dimensionality Reduction WFH: Section 7.3 Rodney Nielsen Many of these slides were adapted from: I. H. Witten, E. Frank and M. A. Hall.
Momentum and Reversal.
Developing Infant Suck Detection Interface
Momentum Effect (JT 1993).
Review Fundamental analysis is about determining the value of an asset. The value of an asset is a function of its future dividends or cash flows. Dividends,
II.V Volume weighted average purchase price
Singular Value Decomposition
CH14 Operating-Income-Based Valuation
Parallelization of Sparse Coding & Dictionary Learning
SVD, PCA, AND THE NFL By: Andrew Zachary.
Outline Singular Value Decomposition Example of PCA: Eigenfaces.
The Timevarying Ionosphere. measured by GPS
CSIC 5011 Project 1: Finance Data PCA, Parallel Analysis
Presentation transcript:

Statistical Arbitrage Ying Chen, Leonardo Bachega Yandong Guo, Xing Liu February, 2010

Outline Overview of the project Improvements in the last week Speedup the data access Improve the PCA algorithm Use adjusted price in PNL calculation Taking trading volume into account Future work

Framework Raw Historical Data From WRDS PCA Eigenportfolios PCA Eigenportfolios Residuals as increments of AR process Compute S-scores ETFs for industry sectors ETFs for industry sectors Signal trade orders Market model 60-day returns Residual process model Current stock prices Market model 252-day returns Adjusted Stock price Series + indices Data pre-processing (python scripts) Back-testing simulations (matlab scripts)

Code Speedup Data access Tradeoff Always read from disk: very slow Everything in memory: not robust, can be slow Cache parts of dataset in memory Fast code Same Total Speedup > 16 times BeforeAfter

PCA amelioration (1/4) Suppose X is a nxp matrix including n samples and p features; Original algorithm: Calculate the Eigen-decomposition of the correlation matrix: The matrix Q consists of the Eigen-vectors of the correlation matrix

PCA amelioration (2/4) Suppose X is a nxp matrix including n samples and p features; Substituted algorithm: We use singular value decomposition (SVD) to get the eigenvectors. Then V consists of Eigen-vectors of the correlation matrix. This will reduce the computational complexity by around 80%

PCA amelioration (3/4) Proof: Since U and V are orthogonal, V consists of the eigen-vectors of the correlation matrix And equals to diagonal matrix D

PCA amelioration (4/4) Notice: if p is one eigenvector of X, then –p is also its eigenvector Since if Then The effect of “negative” can be removed by the estimation.

Experiment result (Fig. 1) Top 50 eigenvalues of the correlation matrix of market returns computed on May estimated using a 1-year window and a universe of 1590 stocks

Experiment result 2 Value of the first eigenvector

Experiment result 2 Value of the second eigenvector

Experiment result 2 Value of the third eigenvector

Preliminary PNL Experiment Dec Feb

After correction

Taking trading volume into account Problem mean-reversion strategies are sensitive to trading volume immediately before the signal was triggered. Modified returns is the average daily trading volume over a given trading window. Experiments PCA/ETF actual price vs. using trading volume

Top 50 eigenvalues of the correlation matrix—trading time Top 50 eigenvalues of the correlation matrix of market returns computed on May estimated using a 1-year window and a universe of 1590 stocks

Top 50 eigenvalues of the correlation matrix——calendar time Top 50 eigenvalues of the correlation matrix of market returns computed on May estimated using a 1-year window and a universe of 1590 stocks

Value of the first eigenvector

Future work Experiment on ETF Associate each stock with one ETF Compare ETF with PCA Take into account Transaction fee, interest, dividend Calculate PCA using trading-time modified return

THANK YOU