Artificial Intelligence in Finance - Yves Hilpisch Mysłowice

The widespread adoption of AI and machine learning is revolutionizing many industries today. Once these technologies are combined with the programmatic availability of historical and real-time financial data, the financial industry will also change fundamentally. With this practical book, you'll learn how to use AI and machine learning to discover statistical inefficiencies in financial markets and exploit them through algorithmic trading.Author Yves Hilpisch shows practitioners, students, and academics in both finance and data science practical ways to apply machine learning and deep learning algorithms to finance. Thanks to lots of self-contained Python examples, you'll be able to replicate all results and figures presented in the book.In five parts, this guide helps you:Learn central notions and algorithms from AI, including recent breakthroughs on the way to artificial general intelligence (AGI) and superintelligence (SI)Understand why data-driven finance, AI, and machine learning will have a lasting impact on financial theory and practiceApply neural networks and reinforcement learning to discover statistical inefficiencies in financial marketsIdentify and exploit economic inefficiencies through backtesting and algorithmic trading--the automated execution of trading strategiesUnderstand how AI will influence the competitive dynamics in the financial industry and what the potential emergence of a financial singularity might bring about Spis treści: Preface References Conventions Used in This Book Using Code Examples OReilly Online Learning How to Contact Us Acknowledgments I. Machine Intelligence 1. Artificial Intelligence Algorithms Types of Data Types of Learning Unsupervised Learning Reinforcement learning Types of Tasks Types of Approaches Neural Networks OLS Regression Estimation with Neural Networks Scikit-learn Keras Classification with Neural Networks Importance of Data Small Data Set Larger Data Set Big Data Conclusions References 2. Superintelligence Success Stories Atari The story An example Go Chess Importance of Hardware Forms of Intelligence Paths to Superintelligence Networks and Organizations Biological Enhancements Brain-Machine Hybrids Whole Brain Emulation Artificial Intelligence Intelligence Explosion Goals and Control Superintelligence and Goals Superintelligence and Control Potential Outcomes Conclusions References II. Finance and Machine Learning 3. Normative Finance Uncertainty and Risk Definitions Numerical Example Traded assets Arbitrage pricing Expected Utility Theory Assumptions and Results Axioms and normative theory Preferences of an agent Utility functions Expected utility functions Risk aversion Numerical Example Mean-Variance Portfolio Theory Assumptions and Results Portfolio statistics Sharpe ratio Numerical Example Portfolio statistics Investment opportunity set Minimum volatility and maximum Sharpe ratio Efficient frontier Capital Asset Pricing Model Assumptions and Results Numerical Example Capital market line Optimal portfolio Indifference curves Arbitrage Pricing Theory Assumptions and Results Numerical Example Conclusions References 4. Data-Driven Finance Scientific Method Financial Econometrics and Regression Data Availability Programmatic APIs Structured Historical Data Structured Streaming Data Unstructured Historical Data Unstructured Streaming Data Alternative Data Normative Theories Revisited Expected Utility and Reality Mean-Variance Portfolio Theory Capital Asset Pricing Model Arbitrage Pricing Theory Debunking Central Assumptions Normally Distributed Returns Sample data sets Real financial returns Linear Relationships Conclusions References Python Code 5. Machine Learning Learning Data Success Capacity Evaluation Bias and Variance Cross-Validation Conclusions References 6. AI-First Finance Efficient Markets Market Prediction Based on Returns Data Market Prediction with More Features Market Prediction Intraday Conclusions References III. Statistical Inefficiencies 7. Dense Neural Networks The Data Baseline Prediction Normalization Dropout Regularization Bagging Optimizers Conclusions References 8. Recurrent Neural Networks First Example Second Example Financial Price Series Financial Return Series Financial Features Estimation Classification Deep RNNs Conclusions References 9. Reinforcement Learning Fundamental Notions OpenAI Gym Monte Carlo Agent Neural Network Agent DQL Agent Simple Finance Gym Better Finance Gym FQL Agent Conclusions References IV. Algorithmic Trading 10. Vectorized Backtesting Backtesting an SMA-Based Strategy Backtesting a Daily DNN-Based Strategy Backtesting an Intraday DNN-Based Strategy Conclusions References 11. Risk Management Trading Bot Vectorized Backtesting Event-Based Backtesting Assessing Risk Backtesting Risk Measures Stop Loss Trailing Stop Loss Take Profit Conclusions References Python Code Finance Environment Trading Bot Backtesting Base Class Backtesting Class 12. Execution and Deployment Oanda Account Data Retrieval Order Execution Trading Bot Deployment Conclusions References Python Code Oanda Environment Vectorized Backtesting Oanda Trading Bot V. Outlook 13. AI-Based Competition AI and Finance Lack of Standardization Education and Training Fight for Resources Market Impact Competitive Scenarios Risks, Regulation, and Oversight Conclusions References 14. Financial Singularity Notions and Definitions What Is at Stake? Paths to Financial Singularity Orthogonal Skills and Resources Scenarios Before and After Star Trek or Star Wars Conclusions References VI. Appendixes A. Interactive Neural Networks Tensors and Tensor Operations Simple Neural Networks Estimation Classification Shallow Neural Networks Estimation Classification References B. Neural Network Classes Activation Functions Simple Neural Networks Estimation Classification Shallow Neural Networks Estimation Classification Predicting Market Direction C. Convolutional Neural Networks Features and Labels Data Training the Model Testing the Model Resources Index O autorze: Dr Yves Hilpisch - właściciel firm The Python Quants i The AI Machine specjalizujących się w projektowaniu i we wdrażaniu mechanizmów algorytmicznych, sztucznej inteligencji i uczenia maszynowego przy użyciu języka Python. Autor kilku książek analizujących zastosowanie tego języka w biznesie i profesor kontraktowy finansów obliczeniowych.