- ホーム
- > 洋書
- > 英文書
- > Business / Economics
Full Description
A big picture analysis of quantitative factor investing combined with practical tools and strategies, including the latest machine learning techniques
In The Quantamental Revolution: Factor Investing in the Age of Machine Learning, veteran quantitative investor and strategist, Milind Sharma, delivers a comprehensive discussion of factor investing, risk premia, smart betas, multi-factor models and the deployment of ML ensembles towards monetizing alpha in the hedge fund world. Sharma draws on 30 years of industry and academic experience to bring us up to date on the cutting edge of quantitative factor investing.
You'll learn about the basics of Fama-French and obtain a practical blueprint for taming the factor zoo. This book provides a comprehensive factor investing framework designed to improve your investment process informed by an insightful industry perspective and backed up by 1st hand eye witness stories as narrated by the author.
The Quantamental Revolution also includes:
A mature and sweeping perspective, simultaneously incorporating industry (insider) insights and academic rigor, not provided by any other reference
Novel research backed by live performance leveraging a huge factor library
A practical reinvention of buy-side equities using a spanning set of factors and ML enhanced smart betas
Perfect for early-career quantitative investors and analysts, traders, and market data professionals, The Quantamental Revolution is also an essential read for portfolio managers interested in improving their investment processes. The engaging anecdotal vignettes coupled with academic rigor provide the reader with an authentic front row seat to the evolution of Quantamental investing on Wall Street over the past three decades.
Contents
Acknowledgments xiii
Chapter 1 A Quantamental Walk Down Wall Street 1
1.1 A Random Walk Down Wall Street 1
1.2 On the Way to $13 Trillion 4
1.3 Quantamental Versus Temperamental 9
1.4 The "Greed Is Good" Generation 11
1.5 From Quarks to Quasars 13
1.6 The Sky Is Not the Limit - Data, Compute, and Energy Are 15
1.7 The Thundering Herd 16
1.8 Hyperlinking to the Future 19
1.9 The Pioneering Quant Finance Program 21
1.10 Bankers Trust and the End of Exotics 24
1.11 It Ain't Rocket Surgery 26
1.12 The Volcker Rule 27
1.13 Ugly Americans 29
1.14 Quant Quakes 30
1.15 Sharpening the Sharpe Ratio 34
1.16 Manias, Panics, and Crashes 35
1.17 Floreat Aula 37
1.18 From Logicism to LLMs - The AI Revolution 38
1.19 Man Versus Machine 41
1.20 Singularity and the Age of Agentic AI 43
1.21 Quaffing a Few - Revenge of the Nerds 47
Chapter 2 Introduction to Factors and Smart Betas 57
2.1 A Survey of the Factor Zoo 57
2.2 The Fama- French Critique 64
2.3 Critique of UMD: Earnings Momentum Versus Price Momentum 66
2.4 Debunking the Size Factor 67
2.5 The Expanding Factor Zoo 68
2.6 Low- Risk Anomalies: IVOL, BAB, MAX, and Co- Skew 71
2.7 What Is Multifactor Investing? 73
2.8 Taming the Factor Zoo 75
2.9 What Are Smart Betas? 78
2.10 Why Combine Factors Within the Same Cohort? 78
2.11 Factor Cyclicality 86
Chapter 3 QMIT's Enhanced Smart Betas 89
3.1 QMIT's ESB Ranking Process 94
3.2 Data Pre- Processing 94
3.3 Factor Ranking 96
3.4 ESB Ranking: Mixing Versus Integrating 96
3.5 Moving from Constituent Factor Ranks to ESB Ranks 97
3.6 BFOM Investable Strategies 102
3.7 Correlations 103
3.8 Multicollinearity 106
Chapter 4 From Smart Betas to Smarter Alphas 111
4.1 Factor Heatmaps 113
4.2 Factor Timing Versus Tilting 118
4.3 Factor Timing and Meta- Factor Considerations 119
4.4 Trading Signals 120
4.5 Fama- French Alphas of Composite Signals 127
4.6 Model Turnover During Earnings Season 128
4.7 Factor Exposures 131
4.8 Platinum Hedge - Crash Baskets 133
Chapter 5 Sector Rotation 139
5.1 Executive Summary 139
5.2 Why Sector Rotation Strategies? 140
5.3 QMIT's Factor Library and Enhanced Smart Betas 141
5.4 QMIT's Sizzling Seven Composite Signal 141
5.5 Methodology 144
5.6 Phase 1: Strategy Based on Sector ETFs 145
5.7 Phase 2: Strategy Based on Single Stocks 148
5.8 Comparison of Phase 1 and Phase 2 150
5.9 Regressions 151
5.10 Top Sector Picks - Frequency 152
5.11 Conclusion 152
Chapter 6 Style Analysis 159
6.1 Fund: Style and Performance Measurement 159
6.2 Methodology 161
6.3 Results 167
6.4 Conclusion 182
6.5 Replicating and Beating the Gurus 184
Chapter 7 Regime Dependence 185
7.1 Composite MFMs - Regime Dependence 190
7.2 Regime- Aware Models 192
Chapter 8 Longing for Winners: Evidence of Persistence in QMIT ESBs 201
8.1 Introduction 201
8.2 Literature Review 202
8.3 Methodology 207
8.4 Correlation Analysis 211
8.5 Performance of TSMOM Strategies (January 2000- September 2024) 216
8.6 Live Corroboration (January 2019- September 2024) 228
8.7 Publication Decay 229
8.8 Conclusion 237
Chapter 9 HEDGE FUND IN A BOX (HFIB) as the Archetypal EMN Construct 239
9.1 HFIB EMN Peer Comparisons, Turnover, and Transaction Costs 245
9.2 Diversification Is the Only Free Lunch 251
9.3 TCA: Delusions of Grandeur 257
9.4 TCA: Taming the Beast 259
Chapter 10 QMIT's Leveraged Buyout (LBO) Model 283
10.1 Mergers and Acquisitions (M&A), Leveraged Buyouts (LBOs), and Risk Arbitrage 283
10.2 QMIT's LBO Top 100 Model 288
10.3 Optimal Hedge Ratios for QMIT's LBO Models 299
10.4 LBO Top 100 - Hedge Ratio Profiles over 24Y 307
Chapter 11 QMIT's LBO model with NLP Sentiment 311
11.1 History of Financial Sentiment Analysis 311
11.2 Harvesting NLP Sentiment 315
11.3 Combining Factor- Based MFMs (Multifactor Models) with Alternative Data Signals 320
11.4 Conclusion 340
Chapter 12 The Causal Critique 343
12.1 Introduction 343
12.2 Granger Versus Pearl's Causality 344
12.3 The Causal Critique 345
12.4 Causality with QMIT ESBs and Combo Signals 353
12.5 PC and LiNGAM Algorithms 355
12.6 Critique of the Critique 365
Chapter 13 Singularity and the Agentic Future 371
13.1 Agentic AI and the Age of Abundance 371
13.2 Systemic Disruption: From the Buy Side to the Sell Side 379
13.3 Systemic Disruption: From the Middle Office to the Back Office 380
13.4 The Macro Picture 381
13.5 Reinventing Capitalism 382
13.6 Road Map to a Fully Automated Agent- Driven Quanty Equity Hedge Fund 383
13.7 Agentic AI Meets Real- World Deployment 392
13.8 Agentic AI and NLP- Based Sentiment for Portfolio Monitoring 394
13.9 Agentic AI in Factor Investing 407
Appendices 411
Appendix A.1 Coverage Universe 411
Appendix A.2 Table of QMIT's Enhanced Smart Betas (ESBs) 412
Appendix A.3 Performance Measures 414
Appendix A.4 Chart Book 419
Appendix A.5 Factor Momentum Results 426
Disclaimers 453
Bibliography 457
About the Author 471
Index 473
