Big Data Science in Finance.

Cover -- Title Page -- Copyright -- Contents -- Preface -- 1 Why Big Data? -- Introduction -- Appendix 1.A Coding Big Data in Python -- Reference -- 2 Neural Networks in Finance -- Introduction -- Neural Network Construction Methodology -- The Architecture of Neural Networks -- Choosing the Activation Function -- Construction and Training of Neural Networks -- Model Selection via Dropout -- Overfitting -- Adding Complexity -- Big Data in Machine Learning -- Coding a Simple Neural Network for One Instrument from Daily Data -- Defining Target Outputs -- Testing Performance -- Adding Activation Levels -- Convergence -- Choosing Input Variables -- Conclusion -- Appendix 2.A Building a Neural Network in Python -- References -- 3 Supervised Learning -- Introduction -- Supervised Learning -- Conclusion -- Appendix 3.A Python for Supervised Models -- References -- 4 Modeling Human Behavior with Semi‐Supervised Learning -- Introduction -- Performance Evaluation via Cross‐Validation -- Generative Models -- Other SSL Models and Enhancements -- Conclusion -- Appendix 4.A Python for Semi‐Supervised Models -- References -- 5 Letting the Data Speak with Unsupervised Learning -- Introduction -- Dimensionality Reduction in Finance -- Conclusion -- Appendix 5.A PCA and SVD in Python -- References -- 6 Big Data Factor Models -- Why PCA and SVD Deliver Optimal Factorization -- Eigenportfolios -- Using Factors to Predict Returns -- Factor Discovery -- Instrumented PCA -- The Three‐Pass Model -- Risk‐Premium PCA -- Nonlinear Factorization -- Correlation‐Based Factors -- Hierarchical PCA (HPCA) -- Disadvantages of PCA and SVD -- Conclusion -- Appendix 6.A Python for Big Data Factor Models -- References -- 7 Data as a Signal versus Noise -- Introduction -- Random Data Shows in Eigenvalue Distribution -- Application: What's in the Data Bag? -- The Marcenko‐Pastur Theorem.

Spike Model: Which Value to Pick on the "Elbow"? -- Dealing with Highly Correlated Data -- Deconstructing the Mona Lisa -- What's in the Data Bag? -- Applications -- The Karhunen‐Loève Transform -- Data Imputation -- Missing Eigenvalues -- The Tracy‐Widom Distribution -- Identifying (and Replacing) Missing Values in Streaming Data (the Johnson‐Lindenstrauss Lemma) -- Conclusion -- Appendix 7 Finding the Optimal Number of Eigenvectors in Python -- References -- 8 Applications: Unsupervised Learning in Option Pricing and Stochastic Modeling -- Introduction -- Application 1: Unsupervised Learning in Options Pricing -- Application 2: Optimizing Markov Chains with the Perron‐Frobenius Theorem -- Conclusion -- Appendix 8.A Determining the Percentage of Variation Explained by the Top Principal Components in Python -- References -- 9 Data Clustering -- Introduction -- Clustering Methodology -- Clustering Financial Data -- Empirical Results -- Conclusion -- Appendix 9.A Clustering with Python -- References -- Conclusion -- Index -- EULA.

Description based on publisher supplied metadata and other sources.

Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2024. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.