Librería Portfolio

Upgrade your programming language to more effectively handle high-frequency data

Machine Learning and Big Data with KDB+/Q offers quants, programmers and algorithmic traders a practical entry into the powerful but non-intuitive kdb+ database and q programming language. Ideally designed to handle the speed and volume of high-frequency financial data at sell- and buy-side institutions, these tools have become the de facto standard; this book provides the foundational knowledge practitioners need to work effectively with this rapidly-evolving approach to analytical trading.

The discussion follows the natural progression of working strategy development to allow hands-on learning in a familiar sphere, illustrating the contrast of efficiency and capability between the q language and other programming approaches. Rather than an all-encompassing "bibleö-type reference, this book is designed with a focus on real-world practicality ­to help you quickly get up to speed and become productive with the language.

Understand why kdb+/q is the ideal solution for high-frequency data
Delve into "meatö of q programming to solve practical economic problems
Perform everyday operations including basic regressions, cointegration, volatility estimation, modelling and more
Learn advanced techniques from market impact and microstructure analyses to machine learning techniques including neural networks
The kdb+ database and its underlying programming language q offer unprecedented speed and capability. As trading algorithms and financial models grow ever more complex against the markets they seek to predict, they encompass an ever-larger swath of data ­- more variables, more metrics, more responsiveness and altogether more "moving parts.ö

Traditional programming languages are increasingly failing to accommodate the growing speed and volume of data, and lack the necessary flexibility that cutting-edge financial modelling demands. Machine Learning and Big Data with KDB+/Q opens up the technology and flattens the learning curve to help you quickly adopt a more effective set of tools.



TABLE OF CONTENTS
Preface xvii

About the Authors xxiii

Part One Language Fundamentals

Chapter 1 Fundamentals of the q Programming Language 3

1.1 The (Not So Very) First Steps in q 3

1.2 Atoms and Lists 5

1.2.1 Casting Types 11

1.3 Basic Language Constructs 14

1.3.1 Assigning, Equality and Matching 14

1.3.2 Arithmetic Operations and Right-to-Left Evaluation: Introduction to q Philosophy 17

1.4 Basic Operators 19

1.5 Difference between Strings and Symbols 31

1.5.1 Enumeration 31

1.6 Matrices and Basic Linear Algebra in q 33

1.7 Launching the Session: Additional Options 35

1.8 Summary and How-To's 38

Chapter 2 Dictionaries and Tables: The q Fundamentals 41

2.1 Dictionary 41

2.2 Table 44

2.3 The Truth about Tables 48

2.4 Keyed Tables are Dictionaries 50

2.5 From a Vector Language to an Algebraic Language 51

Chapter 3 Functions 57

3.1 Namespace 59

3.1.0.1 .quantQ. Namespace 60

3.2 The Six Adverbs 60

3.2.1 Each 60

3.2.1.1 Each 61

3.2.1.2 Each-left \: 61

3.2.1.3 Each-right /: 62

3.2.1.4 Cross Product /: \: 62

3.2.1.5 Each-both ´ 63

3.2.2 Each-prior ´: 66

3.2.3 Compose (') 67

3.2.4 Over and Fold / 67

3.2.5 Scan 68

3.2.5.1 EMA: The Exponential Moving Average 69

3.2.6 Converge 70

3.2.6.1 Converge-repeat 70

3.2.6.2 Converge-iterate 71

3.3 Apply 72

3.3.1 @ (apply) 72

3.3.2 . (apply) 73

3.4 Protected Evaluations 75

3.5 Vector Operations 76

3.5.1 Aggregators 76

3.5.1.1 Simple Aggregators 76

3.5.1.2 Weighted Aggregators 77

3.5.2 Uniform Functions 77

3.5.2.1 Running Functions 77

3.5.2.2 Window Functions 78

3.6 Convention for User-Defined Functions 79

Chapter 4 Editors and Other Tools 81

4.1 Console 81

4.2 Jupyter Notebook 82

4.3 GUIs 84

4.3.1 qStudio 85

4.3.2 Q Insight Pad 88

4.4 IDEs: IntelliJ IDEA 90

4.5 Conclusion 92

Chapter 5 Debugging q Code 93

5.1 Introduction to Making It Wrong: Errors 93

5.1.1 Syntax Errors 94

5.1.2 Runtime Errors 94

5.1.2.1 The Type Error 95

5.1.2.2 Other Errors 98

5.2 Debugging the Code 100

5.3 Debugging Server-Side 102

Part Two Data Operations

Chapter 6 Splayed and Partitioned Tables 107

6.1 Introduction 107

6.2 Saving a Table as a Single Binary File 108

6.3 Splayed Tables 110

6.4 Partitioned Tables 113

6.5 Conclusion 119

Chapter 7 Joins 121

7.1 Comma Operator 121

7.2 Join Functions 125

7.2.1 ij 125

7.2.2 ej 126

7.2.3 lj 126

7.2.4 pj 127

7.2.5 upsert 128

7.2.6 uj 129

7.2.7 aj 131

7.2.8 aj0 134

7.2.8.1 The Next Valid Join 135

7.2.9 asof 138

7.2.10 wj 140

7.3 Advanced Example: Running TWAP 144

Chapter 8 Parallelisation 151

8.1 Parallel Vector Operations 152

8.2 Parallelisation over Processes 155

8.3 Map-Reduce 155

8.4 Advanced Topic: Parallel File/Directory Access 158

Chapter 9 Data Cleaning and Filtering 161

9.1 Predicate Filtering 161

9.1.1 The Where Clause 161

9.1.2 Aggregation Filtering 163

9.2 Data Cleaning, Normalising and APIs 163

Chapter 10 Parse Trees 165

10.1 Definition 166

10.1.1 Evaluation 166

10.1.2 Parse Tree Creation 170

10.1.3 Read-Only Evaluation 170

10.2 Functional Queries 171

10.2.1 Functional Select 174

10.2.2 Functional Exec 178

10.2.3 Functional Update 179

10.2.4 Functional Delete 180

Chapter 11 A Few Use Cases 181

11.1 Rolling VWAP 181

11.1.1 N Tick VWAP 181

11.1.2 TimeWindow VWAP 182

11.2 Weighted Mid for N Levels of an Order Book 183

11.3 Consecutive Runs of a Rule 185

11.4 Real-Time Signals and Alerts 186

Part Three Data Science

Chapter 12 Basic Overview of Statistics 191

12.1 Histogram 191

12.2 First Moments 196

12.3 Hypothesis Testing 198

12.3.1 Normal p-values 198

12.3.2 Correlation 201

12.3.2.1 Implementation 202

12.3.3 t-test: One Sample 202

12.3.3.1 Implementation 204

12.3.4 t-test: Two Samples 204

12.3.4.1 Implementation 205

12.3.5 Sign Test 206

12.3.5.1 Implementation of the Test 208

12.3.5.2 Median Test 211

12.3.6 Wilcoxon Signed-Rank Test 212

12.3.7 Rank Correlation and Somers' D 214

12.3.7.1 Implementation 216

12.3.8 Multiple Hypothesis Testing 221

12.3.8.1 Bonferroni Correction 224

12.3.8.2 èidák's Correction 224

12.3.8.3 Holm's Method 225

12.3.8.4 Example 226

Chapter 13 Linear Regression 229

13.1 Linear Regression 230

13.2 Ordinary Least Squares 231

13.3 The Geometric Representation of Linear Regression 233

13.3.1 Moore-Penrose Pseudoinverse 235

13.3.2 Adding Intercept 237

13.4 Implementation of the OLS 240

13.5 Significance of Parameters 243

13.6 How Good is the Fit: R2 244

13.6.1 Adjusted R-squared 247

13.7 Relationship with Maximum Likelihood Estimation and AIC with Small Sample Correction 248

13.