|
|
|
|
LEADER |
00000nam a2200000 i 4500 |
001 |
b3136103 |
005 |
20240627104555.0 |
006 |
m o d |
007 |
cr ||||||||||| |
008 |
180224s2018 njuab ob 001 0 eng |
010 |
|
|
|a 2018009027
|
020 |
|
|
|a 9781119482116
|q (electronic book)
|
020 |
|
|
|a 1119482119
|q (electronic book)
|
020 |
|
|
|a 9781119482109
|q (electronic book)
|
020 |
|
|
|a 1119482100
|q (electronic book)
|
020 |
|
|
|z 9781119482086
|q (hardcover)
|
020 |
|
|
|z 1119482089
|q (hardcover)
|
035 |
|
|
|a (OCoLC)1021096780
|z (OCoLC)1020790036
|z (OCoLC)1021299458
|
035 |
|
|
|a (DLC)ebc5240570
|
040 |
|
|
|a DLC
|b eng
|e rda
|e pn
|c DLC
|d N$T
|d EBLCP
|d RECBK
|d YDX
|d OCLCO
|d YDX
|d OCLCF
|d OCLCO
|d OCLCQ
|d NhCcYME
|d UtOrBLW
|
042 |
|
|
|a pcc
|
050 |
|
4 |
|a HG104
|b .L67 2018
|
072 |
|
7 |
|a BUS
|x 027000
|2 bisacsh
|
082 |
0 |
0 |
|a 332.0285/631
|2 23
|
084 |
|
|
|a BUS036000
|2 bisacsh
|
100 |
1 |
|
|a López de Prado, Marcos Mailoc,
|e author.
|0 http://id.loc.gov/authorities/names/n2004142701
|
245 |
1 |
0 |
|a Advances in financial machine learning /
|c Marcos López de Prado.
|
264 |
|
1 |
|a Hoboken, New Jersey :
|b John Wiley & Sons, Inc.,
|c [2018]
|
300 |
|
|
|a 1 online resource (xxi, 366 pages)
|
336 |
|
|
|a text
|b txt
|2 rdacontent
|
337 |
|
|
|a computer
|b c
|2 rdamedia
|
338 |
|
|
|a online resource
|b cr
|2 rdacarrier
|
504 |
|
|
|a Includes bibliographical references and index.
|
505 |
0 |
0 |
|a Machine generated contents note:
|g 1.
|t Financial Machine Learning as a Distinct Subject --
|g 1.1.
|t Motivation --
|g 1.2.
|t Main Reason Financial Machine Learning Projects Usually Fail --
|g 1.2.1.
|t Sisyphus Paradigm --
|g 1.2.2.
|t Meta-Strategy Paradigm --
|g 1.3.
|t Book Structure --
|g 1.3.1.
|t Structure by Production Chain --
|g 1.3.2.
|t Structure by Strategy Component --
|g 1.3.3.
|t Structure by Common Pitfall --
|g 1.4.
|t Target Audience --
|g 1.5.
|t Requisites --
|g 1.6.
|t FAQs --
|g 1.7.
|t Acknowledgments --
|t Exercises --
|t References --
|t Bibliography --
|g pt. 1
|t DATA ANALYSIS --
|g 2.
|t Financial Data Structures --
|g 2.1.
|t Motivation --
|g 2.2.
|t Essential Types of Financial Data --
|g 2.2.1.
|t Fundamental Data --
|g 2.2.2.
|t Market Data --
|g 2.2.3.
|t Analytics --
|g 2.2.4.
|t Alternative Data --
|g 2.3.
|t Bars --
|g 2.3.1.
|t Standard Bars --
|g 2.3.2.
|t Information-Driven Bars --
|g 2.4.
|t Dealing with Multi-Product Series --
|g 2.4.1.
|t ETF Trick --
|g 2.4.2.
|t PCA Weights --
|g 2.4.3.
|t Single Future Roll --
|g 2.5.
|t Sampling Features --
|g 2.5.1.
|t Sampling for Reduction --
|g 2.5.2.
|t Event-Based Sampling --
|t Exercises --
|t References --
|g 3.
|t Labeling --
|g 3.1.
|t Motivation --
|g 3.2.
|t Fixed-Time Horizon Method --
|g 3.3.
|t Computing Dynamic Thresholds --
|g 3.4.
|t Triple-Barrier Method --
|g 3.5.
|t Learning Side and Size --
|g 3.6.
|t Meta-Labeling --
|g 3.7.
|t How to Use Meta-Labeling --
|g 3.8.
|t Quantamental Way --
|g 3.9.
|t Dropping Unnecessary Labels --
|t Exercises --
|t Bibliography --
|g 4.
|t Sample Weights --
|g 4.1.
|t Motivation --
|g 4.2.
|t Overlapping Outcomes --
|g 4.3.
|t Number of Concurrent Labels --
|g 4.4.
|t Average Uniqueness of a Label --
|g 4.5.
|t Bagging Classifiers and Uniqueness --
|g 4.5.1.
|t Sequential Bootstrap --
|g 4.5.2.
|t Implementation of Sequential Bootstrap --
|g 4.5.3.
|t Numerical Example --
|g 4.5.4.
|t Monte Carlo Experiments --
|g 4.6.
|t Return Attribution --
|g 4.7.
|t Time Decay --
|g 4.8.
|t Class Weights --
|t Exercises --
|t References --
|t Bibliography --
|g 5.
|t Fractionally Differentiated Features --
|g 5.1.
|t Motivation --
|g 5.2.
|t Stationarity vs. Memory Dilemma --
|g 5.3.
|t Literature Review --
|g 5.4.
|t Method --
|g 5.4.1.
|t Long Memory --
|g 5.4.2.
|t Iterative Estimation --
|g 5.4.3.
|t Convergence --
|g 5.5.
|t Implementation --
|g 5.5.1.
|t Expanding Window --
|g 5.5.2.
|t Fixed-Width Window Fracdiff --
|g 5.6.
|t Stationarity with Maximum Memory Preservation --
|g 5.7.
|t Conclusion --
|t Exercises --
|t References --
|t Bibliography --
|g pt. 2
|t MODELLING --
|g 6.
|t Ensemble Methods --
|g 6.1.
|t Motivation --
|g 6.2.
|t Three Sources of Errors --
|g 6.3.
|t Bootstrap Aggregation --
|g 6.3.1.
|t Variance Reduction --
|g 6.3.2.
|t Improved Accuracy --
|g 6.3.3.
|t Observation Redundancy --
|g 6.4.
|t Random Forest --
|g 6.5.
|t Boosting --
|g 6.6.
|t Bagging vs. Boosting in Finance --
|g 6.7.
|t Bagging for Scalability --
|t Exercises --
|t References --
|t Bibliography --
|g 7.
|t Cross-Validation in Finance --
|g 7.1.
|t Motivation --
|g 7.2.
|t Goal of Cross-Validation --
|g 7.3.
|t Why K-Fold CV Fails in Finance --
|g 7.4.
|t Solution: Purged K-Fold CV --
|g 7.4.1.
|t Purging the Training Set --
|g 7.4.2.
|t Embargo --
|g 7.4.3.
|t Purged K-Fold Class --
|g 7.5.
|t Bugs in Sklearn's Cross-Validation --
|t Exercises --
|t Bibliography --
|g 8.
|t Feature Importance --
|g 8.1.
|t Motivation --
|g 8.2.
|t Importance of Feature Importance --
|g 8.3.
|t Feature Importance with Substitution Effects --
|g 8.3.1.
|t Mean Decrease Impurity --
|g 8.3.2.
|t Mean Decrease Accuracy --
|g 8.4.
|t Feature Importance without Substitution Effects --
|g 8.4.1.
|t Single Feature Importance --
|g 8.4.2.
|t Orthogonal Features --
|g 8.5.
|t Parallelized vs. Stacked Feature Importance --
|g 8.6.
|t Experiments with Synthetic Data --
|t Exercises --
|t References --
|g 9.
|t Hyper-Parameter Tuning with Cross-Validation --
|g 9.1.
|t Motivation --
|g 9.2.
|t Grid Search Cross-Validation --
|g 9.3.
|t Randomized Search Cross-Validation --
|g 9.3.1.
|t Log-Uniform Distribution --
|g 9.4.
|t Scoring and Hyper-parameter Tuning --
|t Exercises --
|t References --
|t Bibliography --
|g pt. 3
|t BACKTESTING --
|g 10.
|t Bet Sizing --
|g 10.1.
|t Motivation --
|g 10.2.
|t Strategy-Independent Bet Sizing Approaches --
|g 10.3.
|t Bet Sizing from Predicted Probabilities --
|g 10.4.
|t Averaging Active Bets --
|g 10.5.
|t Size Discretization --
|g 10.6.
|t Dynamic Bet Sizes and Limit Prices --
|t Exercises --
|t References --
|t Bibliography --
|g 11.
|t Dangers of Backtesting --
|g 11.1.
|t Motivation --
|g 11.2.
|t Mission Impossible: The Flawless Backtest --
|g 11.3.
|t Even If Your Backtest Is Flawless, It Is Probably Wrong --
|g 11.4.
|t Backtesting Is Not a Research Tool --
|g 11.5.
|t Few General Recommendations --
|g 11.6.
|t Strategy Selection --
|t Exercises --
|t References --
|t Bibliography --
|g 12.
|t Backtesting through Cross-Validation --
|g 12.1.
|t Motivation --
|g 12.2.
|t Walk-Forward Method --
|g 12.2.1.
|t Pitfalls of the Walk-Forward Method --
|g 12.3.
|t Cross-Validation Method --
|g 12.4.
|t Combinatorial Purged Cross-Validation Method --
|g 12.4.1.
|t Combinatorial Splits --
|g 12.4.2.
|t Combinatorial Purged Cross-Validation Backtesting Algorithm --
|g 12.4.3.
|t Few Examples --
|g 12.5.
|t How Combinatorial Purged Cross-Validation Addresses Backtest Overfitting --
|t Exercises --
|t References --
|g 13.
|t Backtesting on Synthetic Data --
|g 13.1.
|t Motivation --
|g 13.2.
|t Trading Rules --
|g 13.3.
|t Problem --
|g 13.4.
|t Our Framework --
|g 13.5.
|t Numerical Determination of Optimal Trading Rules --
|g 13.5.1.
|t Algorithm --
|g 13.5.2.
|t Implementation --
|g 13.6.
|t Experimental Results --
|g 13.6.1.
|t Cases with Zero Long-Run Equilibrium --
|g 13.6.2.
|t Cases with Positive Long-Run Equilibrium --
|g 13.6.3.
|t Cases with Negative Long-Run Equilibrium --
|g 13.7.
|t Conclusion --
|t Exercises --
|t References --
|g 14.
|t Backtest Statistics --
|g 14.1.
|t Motivation --
|g 14.2.
|t Types of Backtest Statistics --
|g 14.3.
|t General Characteristics --
|g 14.4.
|t Performance --
|g 14.4.1.
|t Time-Weighted Rate of Return --
|g 14.5.
|t Runs --
|g 14.5.1.
|t Returns Concentration --
|g 14.5.2.
|t Drawdown and Time under Water --
|g 14.5.3.
|t Runs Statistics for Performance Evaluation --
|g 14.6.
|t Implementation Shortfall --
|g 14.7.
|t Efficiency --
|g 14.7.1.
|t Sharpe Ratio --
|g 14.7.2.
|t Probabilistic Sharpe Ratio --
|g 14.7.3.
|t Deflated Sharpe Ratio --
|g 14.7.4.
|t Efficiency Statistics --
|g 14.8.
|t Classification Scores --
|g 14.9.
|t Attribution --
|t Exercises --
|t References --
|t Bibliography --
|g 15.
|t Understanding Strategy Risk --
|g 15.1.
|t Motivation --
|g 15.2.
|t Symmetric Payouts --
|g 15.3.
|t Asymmetric Payouts --
|g 15.4.
|t Probability of Strategy Failure --
|g 15.4.1.
|t Algorithm --
|g 15.4.2.
|t Implementation --
|t Exercises --
|t References --
|g 16.
|t Machine Learning Asset Allocation --
|g 16.1.
|t Motivation --
|g 16.2.
|t Problem with Convex Portfolio Optimization --
|g 16.3.
|t Markowitz's Curse --
|g 16.4.
|t From Geometric to Hierarchical Relationships --
|g 16.4.1.
|t Tree Clustering --
|g 16.4.2.
|t Quasi-Diagonalization --
|g 16.4.3.
|t Recursive Bisection --
|g 16.5.
|t Numerical Example --
|g 16.6.
|t Out-of-Sample Monte Carlo Simulations --
|g 16.7.
|t Further Research --
|g 16.8.
|t Conclusion --
|t Appendices --
|g 16.A.1.
|t Correlation-based Metric --
|g 16.A.2.
|t Inverse Variance Allocation --
|g 16.A.3.
|t Reproducing the Numerical Example --
|g 16.A.4.
|t Reproducing the Monte Carlo Experiment --
|t Exercises --
|t References --
|g pt. 4
|t USEFUL FINANCIAL FEATURES --
|g 17.
|t Structural Breaks --
|g 17.1.
|t Motivation --
|g 17.2.
|t Types of Structural Break Tests --
|g 17.3.
|t CUSUM Tests --
|g 17.3.1.
|t Brown-Durbin-Evans CUSUM Test on Recursive Residuals --
|g 17.3.2.
|t Chu-Stinchcombe-White CUSUM Test on Levels --
|g 17.4.
|t Explosiveness Tests --
|g 17.4.1.
|t Chow-Type Dickey-Fuller Test --
|g 17.4.2.
|t Supremum Augmented Dickey-Fuller --
|g 17.4.3.
|t Sub- and Super-Martingale Tests --
|t Exercises --
|t References --
|g 18.
|t Entropy Features --
|g 18.1.
|t Motivation --
|g 18.2.
|t Shannon's Entropy --
|g 18.3.
|t Plug-in (or Maximum Likelihood) Estimator --
|g 18.4.
|t Lempel-Ziv Estimators --
|g 18.5.
|t Encoding Schemes --
|g 18.5.1.
|t Binary Encoding --
|g 18.5.2.
|t Quantile Encoding --
|g 18.5.3.
|t Sigma Encoding --
|g 18.6.
|t Entropy of a Gaussian Process --
|g 18.7.
|t Entropy and the Generalized Mean --
|g 18.8.
|t Few Financial Applications of Entropy --
|g 18.8.1.
|t Market Efficiency --
|g 18.8.2.
|t Maximum Entropy Generation --
|g 18.8.3.
|t Portfolio Concentration --
|g 18.8.4.
|t Market Microstructure --
|t Exercises --
|t References --
|t Bibliography --
|g 19.
|t Microstructural Features --
|g 19.1.
|t Motivation --
|g 19.2.
|t Review of the Literature --
|g 19.3.
|t First Generation: Price Sequences --
|g 19.3.1.
|t Tick Rule --
|g 19.3.2.
|t Roll Model --
|g 19.3.3.
|t High-Low Volatility Estimator --
|g 19.3.4.
|t Corwin and Schultz --
|g 19.4.
|t Second Generation: Strategic Trade Models --
|g 19.4.1.
|t Kyle's Lambda --
|g 19.4.2.
|t Amihud's Lambda --
|g 19.4.3.
|t Hasbrouck's Lambda --
|g 19.5.
|t Third Generation: Sequential Trade Models --
|g 19.5.1.
|t Probability of Information-based Trading --
|g 19.5.2.
|t Volume-Synchronized Probability of Informed Trading --
|g 19.6.
|t Additional Features from Microstructural Datasets --
|g 19.6.1.
|t Distibution of Order Sizes --
|g 19.6.2.
|t Cancellation Rates, Limit Orders, Market Orders --
|g 19.6.3.
|t Time-Weighted Average Price Execution Algorithms --
|g 19.6.4.
|t Options Markets --
|g 19.6.5.
|t Serial Correlation of Signed Order Flow --
|g 19.7.
|t What Is Microstructural Information? --
|t Exercises --
|t References --
|g pt. 5
|t HIGH-PERFORMANCE COMPUTING RECIPES --
|g 20.
|t Multiprocessing and Vectorization --
|g 20.1.
|t Motivation --
|g 20.2.
|t Vectorization Example --
|g 20.3.
|t Single-Thread vs. Multithreading vs. Multiprocessing --
|g 20.4.
|t Atoms and Molecules --
|g 20.4.1.
|t Linear Partitions --
|g 20.4.2.
|t Two-Nested Loops Partitions --
|g 20.5.
|t Multiprocessing Engines --
|g 20.5.1.
|t Preparing the Jobs --
|g 20.5.2.
|t Asynchronous Calls --
|g 20.5.3.
|t Unwrapping the Callback --
|g 20.5.4.
|t Pickle/Unpickle Objects --
|g 20.5.5.
|t Output Reduction --
|g 20.6.
|t Multiprocessing Example --
|t Exercises --
|t Reference --
|t Bibliography --
|g 21.
|t Brute Force and Quantum Computers --
|g 21.1.
|t Motivation --
|
505 |
0 |
0 |
|a Contents note continued:
|g 21.2.
|t Combinatorial Optimization --
|g 21.3.
|t Objective Function --
|g 21.4.
|t Problem --
|g 21.5.
|t Integer Optimization Approach --
|g 21.5.1.
|t Pigeonhole Partitions --
|g 21.5.2.
|t Feasible Static Solutions --
|g 21.5.3.
|t Evaluating Trajectories --
|g 21.6.
|t Numerical Example --
|g 21.6.1.
|t Random Matrices --
|g 21.6.2.
|t Static Solution --
|g 21.6.3.
|t Dynamic Solution --
|t Exercises --
|t References --
|g 22.
|t High-Performance Computational Intelligence and Forecasting Technologies /
|r Horst D. Simon --
|g 22.1.
|t Motivation --
|g 22.2.
|t Regulatory Response to the Flash Crash of 2010 --
|g 22.3.
|t Background --
|g 22.4.
|t HPC Hardware --
|g 22.5.
|t HPC Software --
|g 22.5.1.
|t Message Passing Interface --
|g 22.5.2.
|t Hierarchical Data Format 5 --
|g 22.5.3.
|t In Situ Processing --
|g 22.5.4.
|t Convergence --
|g 22.6.
|t Use Cases --
|g 22.6.1.
|t Supernova Hunting --
|g 22.6.2.
|t Blobs in Fusion Plasma --
|g 22.6.3.
|t Intraday Peak Electricity Usage --
|g 22.6.4.
|t Flash Crash of 2010 --
|g 22.6.5.
|t Volume-synchronized Probability of Informed Trading Calibration --
|g 22.6.6.
|t Revealing High Frequency Events with Non-uniform Fast Fourier Transform --
|g 22.7.
|t Summary and Call for Participation --
|g 22.8.
|t Acknowledgments --
|t References.
|
533 |
|
|
|a Electronic reproduction.
|b Ann Arbor, MI
|n Available via World Wide Web.
|
588 |
0 |
|
|a Online resource; title from digital title page (viewed on March 02, 2018).
|
650 |
|
0 |
|a Finance
|x Data processing.
|0 http://id.loc.gov/authorities/subjects/sh2020000036
|
650 |
|
0 |
|a Finance
|x Mathematical models.
|0 http://id.loc.gov/authorities/subjects/sh85048260
|
650 |
|
0 |
|a Machine learning.
|0 http://id.loc.gov/authorities/subjects/sh85079324
|
650 |
|
7 |
|a Finance
|x Data processing.
|2 fast
|0 (OCoLC)fst00924370
|
650 |
|
7 |
|a Finance.
|2 fast
|0 (OCoLC)fst00924349
|
650 |
|
7 |
|a Finance
|x Mathematical models.
|2 fast
|0 (OCoLC)fst00924398
|
650 |
|
7 |
|a Machine learning.
|2 fast
|0 (OCoLC)fst01004795
|
776 |
0 |
8 |
|i Print version:
|a López de Prado, Marcos Mailoc.
|t Advances in financial machine learning.
|d New Jersey : Wiley, [2018]
|z 9781119482086
|w (DLC) 2017049249
|
856 |
4 |
0 |
|u https://ebookcentral.proquest.com/lib/santaclara/detail.action?docID=5240570
|z Connect to this title online (unlimited simultaneous users allowed; 325 uses per year)
|t 0
|
907 |
|
|
|a .b31361031
|b 240906
|c 180305
|
916 |
|
|
|a YBP DDA purchased
|
918 |
|
|
|a .bckstg
|b 2016-12-01
|
919 |
|
|
|a .pcat
|b 2016-12-01
|
998 |
|
|
|a uww
|b 180409
|c m
|d z
|e l
|f eng
|g nju
|h 0
|
999 |
f |
f |
|i 0b0eaa32-f3c8-53e9-982e-3b59bf4cf27f
|s 706d6193-37a9-52d5-bbe7-8506c6f99981
|t 0
|