《Haskell Financial Data Modeling and Predictive Analytics》

【实例截图】

【核心代码】

Table of Contents
Preface 1
Chapter 1: Getting Started with the Haskell Platform 5
The Haskell platform 6
Quick tour of Haskell 10
Laziness 10
Functions as first-class citizens 11
Datatypes 12
Type classes 13
Pattern matching 14
Monads 15
The IO monad 16
Summary 17
Chapter 2: Getting Your Hands Dirty 19
The domain model 19
The Attoparsec library 20
Parsing plain text files 21
Parsing files in applicative style 22
Outlier detection 23
Essential mathematical packages 23
Grubb's test for outliers 25
Template Haskell, quasiquotes, type families, and GADTs 26
Persistent ORM framework 27
Declaring entities 28
Inserting and updating data 28
Fetching data 30
Summary 30
Table of Contents
[ ii ]
Chapter 3: Measuring Tick Intervals 31
Point process 31
Counting process 31
Durations 32
Experimental durations 32
Maximum likelihood estimation 34
Generic MLE implementation 35
Poisson process calibration 35
MLE estimation 36
Akaike information criterion 37
Haskell implementation 38
Renewal process calibration 38
MLE estimation 38
Cox process calibration 39
MLE estimation 41
Model selection 41
The secant root-finding algorithm 42
The QuickCheck test framework 43
QuickCheck test data modifiers 45
Summary 47
Chapter 4: Going Autoregressive 49
The ARMA model definition 49
The Kalman filter 50
Matrix manipulation libraries in Haskell 52
HMatrix basics 52
The Kalman filter in Haskell 54
The state-space model for ARMA 55
ARMA in Haskell 55
ACD model extension 56
Experimental conditional durations 57
The Autocorrelation function 58
Stream fusion 59
The Autocorrelation plot 61
QML estimation 61
State-space model for ACD 63
Summary 63
Chapter 5: Volatility 65
Historic volatility estimators 65
Volatility estimator framework 66
Table of Contents
[ iii ]
Alternative volatility estimators 67
The Parkinson's number 68
The Garman-Klass estimator 69
The Rogers-Satchel estimator 69
The Yang-Zhang estimator 69
Choosing a volatility estimator 70
The variation ratio method 70
Forecasting volatility 71
The GARCH (1,1) model 72
Maximum likelihood estimation of parameters 73
Implementation details 74
Parallel computations 75
Code benchmarking 75
Haskell Run-Time System 77
The divide-and-conquer approach 78
GARCH code in parallel 81
Evaluation strategy 81
Summary 83
Chapter 6: Advanced Cabal 85
Common usage 86
Packaging with Cabal 86
Cabal in sandbox 87
Summary 89
Appendix: References 91
Index 93