The Book of Alternative Data A Guide for Investors, Traders and Risk Managers

by Denev, Alexander; Amen, Saeed

• ISBN13: 9781119601791
• ISBN10: 1119601797
• Edition: 1st
• Format: Hardcover
• Copyright: 2020-07-21
• Publisher: Wiley

Summary

The first and only book to systematically address methodologies and processes of leveraging non-traditional information sources in the context of investing and risk management

Harnessing non-traditional data sources to generate alpha, analyze markets, and forecast risk is a subject of intense interest for financial professionals. A growing number of regularly-held conferences on alternative data are being established, complemented by an upsurge in new papers on the subject. Alternative data is starting to be steadily incorporated by conventional institutional investors and risk managers throughout the financial world. Methodologies to analyze and extract value from alternative data, guidance on how to source data and integrate data flows within existing systems is currently not treated in literature. Filling this significant gap in knowledge, The Book of Alternative Data is the first and only book to offer a coherent, systematic treatment of the subject.

This groundbreaking volume provides readers with a roadmap for navigating the complexities of an array of alternative data sources, and delivers the appropriate techniques to analyze them. The authors—leading experts in financial modeling, machine learning, and quantitative research and analytics—employ a step-by-step approach to guide readers through the dense jungle of generated data. A first-of-its kind treatment of alternative data types, sources, and methodologies, this innovative book:

• Provides an integrated modeling approach to extract value from multiple types of datasets
• Treats the processes needed to make alternative data signals operational
• Helps investors and risk managers rethink how they engage with alternative datasets
• Features practical use case studies in many different financial markets and real-world techniques
• Describes how to avoid potential pitfalls and missteps in starting the alternative data journey
• Explains how to integrate information from different datasets to maximize informational value

The Book of Alternative Data is an indispensable resource for anyone wishing to analyze or monetize different non-traditional datasets, including Chief Investment Officers, Chief Risk Officers, risk professionals, investment professionals, traders, economists, and machine learning developers and users.

Author Biography

ALEXANDER DENEV is Head of AI, Financial Services - Risk Advisory at Deloitte LLP. Prior to that he led Quantitative Research & Advanced Analytics at IHS Markit. Previously, he held roles at the Royal Bank of Scotland, Societe Generale, and European Investment Bank. Denev is a visiting lecturer at the University of Oxford where he graduated with a degree in Mathematical Finance. He is author of numerous papers and books on novel methods of financial modeling with applications ranging from stress testing to asset allocation.

SAEED AMEN is the founder of Cuemacro, where he consults on systematic trading. For 15 years, he has developed systematic trading strategies and quantitative indices including at major investment banks, Lehman Brothers and Nomura. He is also a visiting lecturer at Queen Mary University of London and a co-founder of the Thalesians, a quant think tank.

Table of Contents

Preface

Part I  -  Introduction And Theory

Chapter 1. Alternative data – the lay of the land

1.1. Introduction

1.2. What is “Alternative Data”?

1.3. Segmentation of alternative data

1.4. The Many Vs of Big Data

1.5. Why alternative data?

1.6. Who is using alternative data?

1.7. Capacity of a strategy and alternative data

1.8. Alternative data dimensions

1.9. Who are the alternative data vendors?

1.10. Usage of alternative datasets on the buy side

1.11. Conclusion

Chapter 2. The value of alternative data

2.1. Introduction

2.2. The Decay of Investment Value

2.3. Data markets

2.4. The Monetary Value of Data (Part I)

2.5. Evaluating (alternative) data strategies with and without backtesting

2.5.1. Systematic investors

2.5.2. Discretionary Investors

2.5.3. Risk Managers

2.6. The Monetary Value of Data (Part II)

2.6.1. The buyer’s perspective

2.6.2. The seller’s perspective

2.7. The advantages of maturing alternative datasets

2.8. Summary

Chapter 3. Alternative data risks and challenges

3.1. Legal Aspects of Data

3.2. Risks of using alternative data

3.3. Challenges of using alternative data

3.3.1. Entity Matching

3.3.2. Missing Data

3.3.3. Structuring the data

3.3.4. Treatment of outliers

3.4. Aggregating the data

3.5. Summary

Chapter 4. Machine learning techniques

4.1. Introduction

4.2. Machine Learning – definitions and techniques

4.2.1. Bias, Variance and Noise

4.2.2. Cross-Validation

4.2.3. Introducing machine learning

4.2.4. Popular supervised machine learning techniques

4.2.5. Clustering based unsupervised machine learning techniques

4.2.6. Other unsupervised machine learning techniques

4.2.7. Machine learning libraries

4.2.8. Neutral networks and deep learning

4.2.9. Gaussian Processes

4.3. Which technique to choose?

4.4. Assumptions and Limitations of the Machine Learning Techniques

4.5. Structuring images

4.6. Natural Language Processing (NLP)

4.7. Summary

Chapter 5. The Processes behind the Use of Alternative Data

5.1. Introduction

5.2. Steps in the alternative data journey

5.2.1. Step 1 – Set up a vision and strategy

5.2.2. Step 2 – Identify the Appropriate Datasets

5.2.3. Step 3 – Perform due diligence on vendors

5.2.4. Step 4 – Pre-assess risks

5.2.5. Step 5 – Pre-assess the existence of signals

5.2.6. Step 6 - Data on-boarding

5.2.7. Step 7 – Data pre-processing

5.2.8. Step 8 – Signal extraction

5.2.9. Step 9 – Implementation (or deployment in production)

5.2.10. Maintenance process

5.3. Structuring teams to use alternative data

5.4. Data Vendors

5.5. Summary

Chapter 6. Factor Investing

6.1. Introduction

6.2. The CAPM

6.3. Factor Models

6.3.1. The Arbitrage Pricing Theory

6.3.2. The Fama-French 3-Factor Model

6.3.3. The Carhart Model

6.3.4. Other Approaches (Data Mining)

6.4. The difference between cross sectional and time series trading approaches

6.5. Why factor investing?

6.6. Smart beta indices using alternative data inputs

6.7. ESG factors

6.8. Direct and Indirect Prediction

6.9. Summary

Part II  -  Practical Applications

Chapter 7. Missing Data  - Background

7.1. Introduction

7.2. Missing Data Classification

7.2.1. Missing Data Treatments

7.2.1.1. Deletion

7.2.1.2. Replacement

7.2.1.3. Predictive Imputation

7.3. Literature overview of missing data treatments

7.3.1. Luengo et al. (2012)

7.3.2. Garcia-Laencina et al. (2010)

7.3.3. Grzymala-Busse et al. (2000)

7.3.4. Zou et al (2005)

7.3.5. Jerez et al (2010)

7.3.6. Farhangfar et al. (2008)

7.3.7. Kang et al (2013)

7.3.8. Summary

Chapter 8. Missing Data – Case Studies

8.1. Introduction

8.2. Case Study – Imputing missing values in multivariate Credit Default Swap time series

8.2.1. Missing data classification

8.2.2. Imputation Metrics

8.2.3. CDS data and test data generation

8.2.4. Multiple imputation methods

8.2.4.1. The MVN Case

8.2.4.2. Expectation maximisation (EM) procedure

8.2.5. Deterministic and EOF based techniques

8.2.5.1. Brief recap of Singular Value Decomposition (SVD)

8.2.5.2. Data interpolation with empirical orthogonal functions (DINEOF)

8.2.5.3. Multiple singular spectral analysis (MSSA)

8.2.6. Results

8.3. Case Study – Satellite Images

8.4. Summary

8.5. Appendix: General description of the MICE procedure

8.6. Appendix: Software libraries used in this chapter

8.6.1.1. MICE

8.6.1.2. Amelia II

8.6.1.3. MissForest: Random Forest imputation

8.6.1.4. DINEOF

8.6.1.5. MSSA

Chapter 9. Outliers (Anomalies)

9.1. Introduction

9.2. Outliers definition, classification, and approaches to detection

9.3. Temporal structure

9.4. Global vs local outliers, point anomalies and micro-clusters

9.5. Outlier detection problem setup

9.6. Comparative evaluation of outlier detection algorithms

9.7. Approaches to outlier explanation

9.7.1. Micenkova et al.

9.7.2. Duan et al.

9.7.3. Angiulli et al.

9.8. Case Study - outlier detection on Fed communications index

9.9. Summary

9.10. Appendix

9.10.1. Model-based techniques

9.10.2. Distance-based techniques

9.10.3. Density-based Techniques

9.10.4. Heuristics-based approaches

Chapter 10. Automotive Fundamental Data

10.1. Introduction

10.2. Data

10.3. Approach 1 – Indirect Approach

10.3.1. The Steps Followed

10.3.2. Stage 1

10.3.2.1. Process

10.3.2.2. Example

10.3.2.3. Clairvoyance

10.3.2.4. Ranking factors used

10.3.2.5. Supporting statistics

10.3.2.6. Other info

10.3.2.7. Results

10.4. Approach 2 – Direct Approach

10.4.1. The Data

10.4.2. Factor Generation

10.4.3. Factor performance

10.4.4. Detailed factor results

10.4.4.1. revenues_sales_prev_3m_sum_prev_1m_pct_change – monthly change in quarterly sales volume

10.4.4.2. ww_market_share_prev_1m_pct_change – monthly change in worldwide market share

10.4.4.3. usa_sales_volume_prev_12m_sum_prev_3m_pct_change – quarterly change in yearly US sales volume

10.4.4.4. Factor correlations

10.4.5. Notes

10.5. Gaussian Processes Example

10.6. Summary

10.7. Appendix

10.7.1. List of companies

10.7.2. Description of financial statement items

10.7.3. Ratios used

10.7.4. IHS Markit data features

10.7.5. Reporting delays by country

Chapter 11. Survey and crowdsourced data

11.1. Introduction

11.2. Survey Data as Alternative Data

11.3. About Grapedata

11.4. The Product

11.5. Case Studies

11.5.1. Case Study – Company Event Study (Pooled Survey)

11.5.2. Case Study – Oil & Gas Production (Q&A Survey)

11.6. Technical considerations

11.7. Alpha capture data

11.8. Crowdsourcing analyst estimates

11.9. Summary

11.10. Appendix

Chapter 12. Purchasing Managers’ Index

12.1. Introduction

12.2. PMI Performance

12.3. Nowcasting GDP Growth

12.4. Impacts on financial markets

12.5. Summary

Chapter 13. Satellite imagery and aerial photography

13.1. Introduction

13.2. Forecasting US export growth

13.3. Car counts and earnings per share for retailers

13.4. Measuring Chinese PMI manufacturing with satellite data

13.5. Summary

Chapter 14. Location data

14.1. Introduction

14.2. Shipping data to track crude oil supplies

14.3. Mobile phone location data to understand retail activity

14.3.1. Trading REIT ETF using mobile phone location data

14.3.2. Estimating earnings per share with mobile phone location data

14.4. Taxi ride data and New York Fed meetings

14.5. Corporate jet location data and M&A

14.6. Summary

Chapter 15. Text, web, social media and news

15.1. Introduction

15.2. Collecting web data

15.3. Social media

15.3.1. Hedonmeter Index

15.3.2. Using Twitter data to help forecast US change in nonfarm payrolls

15.3.3. Twitter data to forecast stock market reaction to FOMC

15.3.4. Liquidity and sentiment from social media

15.4. News

15.4.1. Machine readable news to trade FX and understand FX volatility

15.4.2. Federal Reserve communications and US Treasury yields

15.5. Other web sources

15.5.1. Measuring consumer price inflation

15.6. Summary

Chapter 16. Investor attention

16.1. Introduction

16.2. Readership of payrolls to measure investor attention

16.3. Google Trends data to measure market themes

16.4. Investopedia search data to measure investor anxiety

16.5. Using Wikipedia to understand price action in cryptocurrencies

16.6. Online attention for countries to inform EMFX trading

16.7. Summary

Chapter 17. Consumer transactions

17.1. Introduction

17.2. Credit and debit card transaction data

17.3. Consumer receipts

17.4. Summary

Chapter 18. Government, industrial and corporate data

18.1. Introduction

18.2. Using innovation measures to trade equities

18.3. Quantifying currency crisis risk

18.4. Modelling central bank invention in currency markets

18.5. Summary

Chapter 19. Market data

19.1. Introduction

19.2. Relationship between institutional FX flow data and FX spot

19.3. Understanding liquidity using high frequency FX data

19.4. Summary

Chapter 20. Alternative data in private markets

20.1. Introduction

20.2. Defining private equity and venture capital firms

20.3. Private equity datasets

20.4. Understanding the performance of private firms

20.5. Summary

Chapter 21. Conclusions

21.1. Some last words

Bibliography

About the Authors

Index