Rajesh Shekhar Data Mining Prof. Chris Volinsky. ◦ Use Data Mining techniques to build a portfolio with superior return/risk characteristics using technical.

Slides:



Advertisements
Similar presentations
Quantitative Stock Selection Portable Alpha Gambo Audu Preston Brown Xiaoxi Li Vivek Sugavanam Wee Tang Yee.
Advertisements

Portfolio Management Grenoble Ecole de Management MSc Finance Fall 2009.
Quantsmile: Quantitative Portfolio Management Quantsmile: Quantitative Portfolio Management.
6 Efficient Diversification Bodie, Kane, and Marcus
 The McGraw-Hill Companies, Inc., 1999 INVESTMENTS Fourth Edition Bodie Kane Marcus Irwin/McGraw-Hill 24-1 Portfolio Performance Evaluation.
A SSET A LLOCATION Portfolio Management Ali Nejadmalayeri.
INVESTMENTS | BODIE, KANE, MARCUS ©2011 The McGraw-Hill Companies CHAPTER 7 Optimal Risky Portfolios 1.
Trading Interactive Simulator A basic Interactive tool for experimentation To experiment within minutes, with many weeks, months and years of investments,
Equity portfolio management strategies
Asset Management Lecture 22. Review class Asset management process Planning with the client Investor objectives, constraints and preferences Execution.
Optimal Risky Portfolios
McGraw-Hill/Irwin © 2008 The McGraw-Hill Companies, Inc., All Rights Reserved. Capital Asset Pricing and Arbitrage Pricing Theory CHAPTER 7.
Lecture Presentation Software to accompany Investment Analysis and Portfolio Management Seventh Edition by Frank K. Reilly & Keith C. Brown Chapter.
1 ASSET ALLOCATION. 2 With Riskless Asset 3 Mean Variance Relative to a Benchmark.
FIN352 Vicentiu Covrig 1 Common Stocks: Analysis and Strategy (chapter 11)
Vicentiu Covrig 1 Mutual funds Mutual funds. Vicentiu Covrig 2 Diversification Professional management Low capital requirement Reduced transaction costs.
GLOBAL ASSET ALLOCATION AND STOCK SELECTION ASSIGNMENT # 1 SMALL CAP LONG-SHORT STRATEGY FIRST-YEAR BRAVES Daniel Grundman, Kader Hidra, Damian Olesnycky,
Moden Portfolio Theory Dan Thaler. Definition Proposes how rational investors will use diversification to optimize their portfolios MPT models an asset’s.
Long/Short Trading Strategy Cam’s Crazies Global Asset Allocation February 2005.
Presentation by: Bryan Durand Josh Amoss Suri Thummala Steve Beuchaw Matthew Malouin Global Asset Allocation February 28, 2005.
McGraw-Hill/Irwin Copyright © 2005 by The McGraw-Hill Companies, Inc. All rights reserved. Chapter 24 Portfolio Performance Evaluation.
Long/Short Sector-based Trading Strategy Emergent Asset Management, LLC Konstantin Savov Scott Smith Pin-Yew Wong Vaswar Mitra Vinaya Jain February 27,
1Capital IQ, A Standard & Poor’s Business Variations on Minimum Variance March 2011 Ruben Falk, Capital IQ Quantitative Research.
Lecture Presentation Software to accompany Investment Analysis and Portfolio Management Eighth Edition by Frank K. Reilly & Keith C. Brown Chapter 16.
Lecture Presentation Software to accompany Investment Analysis and Portfolio Management Seventh Edition by Frank K. Reilly & Keith C. Brown Chapter 17.
Testing “market beating” schemes and strategies. Testing Market Efficiency Tests of market efficiency look at the whether specific investment strategies.
Optimal Risky Portfolios
Portfolio Management-Learning Objective
Lecture Presentation Software to accompany Investment Analysis and Portfolio Management Seventh Edition by Frank K. Reilly & Keith C. Brown Chapter 7.
Capital Asset Pricing Model CAPM Security Market Line CAPM and Market Efficiency Alpha (  ) vs. Beta (  )
E QUITY P ORTFOLIO M ANAGEMENT Portfolio Management Ali Nejadmalayeri.
PROFESSIONAL ASSET MANAGEMENT 1. Basic Categories Private Management: Clients each have a separate account {popular with institutions} Investor 1 Investor.
Portfolio Performance Evaluation
Value vs Growth & Active vs Passive. Growth Stocks Growth: High P/E Ratio (high MV/BV) Low or no dividend yield High ROA High Expected growth rate in.
Chapter 8 Portfolio Selection.
Modern Portfolio Theory. History of MPT ► 1952 Horowitz ► CAPM (Capital Asset Pricing Model) 1965 Sharpe, Lintner, Mossin ► APT (Arbitrage Pricing Theory)
1 BM410: Investments Portfolio Construction 2: Market Anomalies and Portfolio Tilts.
Active Portfolio Management Joel R. Barber Department of Finance, BA 205A Florida International University.
Empirical Issues Portfolio Performance Evaluation.
1 Portfolio Management- Asset Allocation 1. Objective 2. Know Your Limitations Risk Tolerance 3. Have an Investment Philosophy Some portfolio managers.
PROFESSIONAL ASSET MANAGEMENT. Basic Categories Private Management: Clients each have a separate account {popular with institutions} Investor 1 Investor.
INVESTMENTS | BODIE, KANE, MARCUS Copyright © 2011 by The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill/Irwin CHAPTER 8 Index Models.
Portfolio Management Unit – 1 Session No.3 Topic: Portfolio Management Process Unit – 1 Session No.3 Topic: Portfolio Management Process.
1 International Finance Chapter 6 (b) Balance of Payments I: The Gains from Financial Globalization.
 The McGraw-Hill Companies, Inc., 1999 INVESTMENTS Fourth Edition Bodie Kane Marcus Irwin/McGraw-Hill 24-1 Portfolio Performance Evaluation Chapter.
Travis Wainman partner1 partner2
Chapter 7 An Introduction to Portfolio Management.
1 CHAPTER THREE: Portfolio Theory, Fund Separation and CAPM.
1 Conditional Weighted Value + Growth Portfolio (a.k.a MCP) Midas Asset Management Under the instruction of Prof. Campbell Harvey Feb 2005 Assignment 1.
Lecture 16 Portfolio Weights. determine market capitalization value-weighting equal-weighting mean-variance optimization capital asset pricing model market.
INVESTMENTS | BODIE, KANE, MARCUS Copyright © 2014 McGraw-Hill Education. All rights reserved. No reproduction or distribution without the prior written.
Investments, 8 th edition Bodie, Kane and Marcus Slides by Susan Hine McGraw-Hill/Irwin Copyright © 2009 by The McGraw-Hill Companies, Inc. All rights.
EQUITY-PORTFOLIO MANAGEMENT
Lecture Presentation Software to accompany Investment Analysis and Portfolio Management Sixth Edition by Frank K. Reilly & Keith C. Brown Chapter 22.
Portfolio Performance Evaluation
Risk Budgeting.
Topic 4: Portfolio Concepts
Markowitz Risk - Return Optimization
FIGURE 12.1 Walgreens and Microsoft Stock Prices,
Portfolio Performance Evaluation
6 Efficient Diversification Bodie, Kane and Marcus
Portfolio Performance Evaluation
Portfolio Performance Evaluation
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,
…A Quantitative Approach
Overview Hypothesis: Develop a market-neutral long/short strategy
Chapter 16: Equity Portfolio Management Strategies
Figure 6.1 Risk as Function of Number of Stocks in Portfolio
FIN 422: Student Managed Investment Fund
Quadrus Canadian Low Volatility Equity (London Capital)
Presentation transcript:

Rajesh Shekhar Data Mining Prof. Chris Volinsky

◦ Use Data Mining techniques to build a portfolio with superior return/risk characteristics using technical indicators  Maximize return  Minimize risk ◦ Build different momentum based strategies

◦ Risk Diversification  Select stocks across sectors for a natural diversification.  Virtual sectors created using k-means cluster algorithm ◦ Return maximization  Use momentum based indicators to predict future returns  Try different trading algorithms

 Investment Universe: Large Market Cap Stocks (Top 100/300/500)  Data collected for everyday stock prices from WRDS (CRSP database) for the entire stock universe from  Custom benchmark of top 100/300/500 stocks was created as composition of S&P 500 was not known over the period

IssueApproach Large Dataset (Entire stock universe from 1999 to 2009; more than 5 GB) Use database (SQL Server) and query to get subset of the data and create proper indexes. Ticker name change.Use permno Dividends: The price change for stocks does not give the true return as it ignores the dividend paid. Use daily adjusted return which adjusts for the dividend. Missing ReturnsUse average to fill the returns Duplicates Use ‘select distinct’ SQL query to filter the data Null Values:Use average to fill the returns

 Used k-means cluster to create virtual clusters  11 clusters for 300/500 stock universe and 10 clusters for 100 stock universe  Input: β, Market Cap (Liquidity), P/E (Price/Earning)  β stock = cov(R stock, R market )/var(R marke )  β captures long term adjusted equilibrium rate of return

◦ Different models tried for capturing momentum indicators (linear models (based on APT)  Best model to capture model momentum was:  Based on time decay of historical returns  r = k j *r j where r = predicted stock return j = time period (j=0 for the current time) k = constant achieved after calibration  More weights on recent data ◦ Two years of moving window for prediction ◦ Portfolio analysis and rebalancing every two weeks

 Long Only  Short Only  Long-Short  Sector Rotation  Sector Portfolio Optimization

 Basic Idea: Long top “n” performing stocks in each sector based on market cap  Portfolio Weights: All selected stocks are equally weighted in portfolio Basic Idea: Short bottom “n” performing stocks in each sector based on market cap Portfolio Weights: All selected stocks are equally weighted in portfolio Short Only

 Basic Idea: Combination of Long and Short  Portfolio Weights: All selected stocks are equally weighted in portfolio Basic Idea: Long top performing sectors & short on bottom performing ones Portfolio Weights: Weight in each sector is proportional to return (More weight on the more outperforming sector; shorting allowed) Sector Rotation

 Basic Idea: Select stocks using long only strategy.  Portfolio Weights: Decided by Markowitz Portfolio optimization techniques ◦ Sector Constraints : (weights vary from 1.1 to 0.9 of the target sector weights) ◦ Asset Constraints (Shorting and leverage allowed): (weights vary from -0.1 to 1.1) ◦ Allocation on the efficient frontier

(SQL Server) Database Portfolio Engine (MATLAB Code) Portfolio Reports &Graphs Risk Analysis (MATLAB Code) Performance & Risk Report MATLAB (Object Oriented) SQL Server database (> 5 GB of raw data and with indexes 12GB)

 Vary Input parameters ◦ Stock universe (100/300/500) ◦ Stock selected (10/20/40) ◦ Running time window ( , ) ◦ Rebalancing period (15/21/30/45 days)

Results: 300 stocks universe

Performance Measurement : Risk Metrics (100 stocks) Long Only Short Only Long Short Sector Rotation Sector PortOpt Return (annual) 20.16%37.10%16.18%52.15%14.49% Sigma (annual) 32.93%55.44%36.73%47.04%30.01% Alpha (annual) 37.35%54.29%33.36%69.34%31.68% SharpeRatio (annual) InfoRatio (annual) Var (95% Daily) -2.91%-3.93%-3.28%-3.96%-2.81% CVAR (95% Daily) -3.72%-7.23%-5.56%-5.97%-3.69% MaxDD (Daily) 15.39%43.56%27.95%30.36%13.40% (100 stocks) Long Only Short Only Long Short Sector Rotation Sector PortOpt Return (annual) 25.55%0.53%6.00%22.43%33.30% Sigma (annual) 15.29%15.71%12.49%16.77%16.23% Alpha (annual) 15.43%-9.59%-4.12%12.30%23.18% SharpeRatio (annual) InfoRatio (annual) Var (95% Daily) -1.31%-1.51%-1.22%-1.52%-1.37% CVAR (95% Daily) -1.71%-2.15%-1.52%-1.91%-1.79% MaxDD (Daily) 8.64%8.04%5.90%8.59%7.78% (300 stocks) Long Only Short Only Long Short Sector Rotation Sector PortOpt Return (annual) 37.91%90.17%57.09%105.86%61.34% Sigma (annual) 42.74%66.97%48.95%54.23%42.79% Alpha (annual) 54.26%106.53%73.44%122.21%77.69% SharpeRatio (annual) InfoRatio (annual) Var (95% Daily) -3.58%-4.69%-4.40%-4.17%-3.52% CVAR (95% Daily) -4.53%-8.36%-6.78%-6.33%-4.48% MaxDD (Daily) 17.55%45.84%27.92%33.22%24.54% (300 stocks) Long Only Short Only Long Short Sector Rotation Sector Port Opt Return (annual) 70.02%25.05%45.07%51.91%69.17% Sigma (annual) 21.68%19.03%17.62%22.98%23.96% Alpha (annual) 58.18%13.22%33.24%40.08%57.33% Sharpe Ratio (annual) Info Ratio (annual) VaR (95% Daily) -1.44%-1.54%-1.29%-1.72%-1.61% CVAR (95% Daily) -1.89%-2.24%-1.83%-2.43%-2.34% Max DD (Daily) 10.99%10.09%8.27%13.61%15.98%

 Benchmark : Custom Benchmark  Value-added Return = Pure sector allocation + Allocation/Selection interaction + Within-sector selection R V = + + Rv = the value-added return w P,j = portfolio weight of sector j w B,j = benchmark weight of sector j R P,j = portfolio return of sector j R B,j = benchmark return of sector j R B = return in the portfolio’s benchmark S = number of sectors

 Transaction Costs: ◦ Slippage cost and explicit costs are taken into account ◦ Market impact and other implicit costs are ignored  Leverage costs are not taken into account  Portfolio Turnover not taken into account

 Virtual sectors works reasonably well.  Time decay returns is a decent predictor of future returns in stable market for short time periods.  Statistically relevant for large market caps.