{"product_id":"generative-ai-for-trading-and-asset-management-isbn-9781394266975","title":"Generative AI for Trading and Asset Management","description":"\u003cp\u003e\u003cb\u003eExpert guide on using AI to supercharge traders' productivity, optimize portfolios, and suggest new trading strategies\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003e\u003ci\u003eGenerative AI for Trading and Asset Management\u003c\/i\u003e is an essential guide to understand how generative AI has emerged as a transformative force in the realm of asset management, particularly in the context of trading, due to its ability to analyze vast datasets, identify intricate patterns, and suggest complex trading strategies. Practically, this book explains how to utilize various types of AI: unsupervised learning, supervised learning, reinforcement learning, and large language models to suggest new trading strategies, manage risks, optimize trading strategies and portfolios, and generally improve the productivity of algorithmic and discretionary traders alike. These techniques converge into an algorithm to trade on the Federal Reserve chair's press conferences in real time. \u003c\/p\u003e\u003cp\u003eWritten by Hamlet Medina, chief data scientist Criteo, and Ernie Chan, founder of QTS Capital Management and Predictnow.ai, this book explores topics including: \u003c\/p\u003e\u003cul\u003e \u003cli\u003eHow large language models and other machine learning techniques can improve productivity of algorithmic and discretionary traders from ideation, signal generations, backtesting, risk management, to portfolio optimization\u003c\/li\u003e \u003cli\u003eThe pros and cons of tree-based models vs neural networks as they relate to financial applications. How regularization techniques can enhance out of sample performance\u003c\/li\u003e \u003cli\u003eComprehensive exploration of the main families of explicit and implicit generative models for modeling high-dimensional data, including their advantages and limitations in model representation and training, sampling quality and speed, and representation learning.\u003c\/li\u003e \u003cli\u003eTechniques for combining and utilizing generative models to address data scarcity and enhance data augmentation for training ML models in financial applications like market simulations, sentiment analysis, risk management, and more.\u003c\/li\u003e \u003cli\u003eApplication of generative AI models for processing fundamental data to develop trading signals.\u003c\/li\u003e \u003cli\u003eExploration of efficient methods for deploying large models into production, highlighting techniques and strategies to enhance inference efficiency, such as model pruning, quantization, and knowledge distillation.\u003c\/li\u003e \u003cli\u003eUsing existing LLMs to translate Federal Reserve Chair's speeches to text and generate trading signals.\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003e\u003ci\u003eGenerative AI for Trading and Asset Management\u003c\/i\u003e earns a well-deserved spot on the bookshelves of all asset managers seeking to harness the ever-changing landscape of  AI technologies to navigate  financial markets. \u003c\/p\u003e\u003cp\u003ePreface xv\u003c\/p\u003e \u003cp\u003eAcknowledgments xix\u003c\/p\u003e \u003cp\u003eAbout the Authors xxi\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePart I Generative AI for Trading and Asset Management: A No-code Introduction 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1 No-code Generative AI for Basic Quantitative Finance 3\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e1.1 Retrieving Historical Market Data 4\u003c\/p\u003e \u003cp\u003e1.2 Computing Sharpe Ratio 7\u003c\/p\u003e \u003cp\u003e1.3 Data Formatting and Analysis 8\u003c\/p\u003e \u003cp\u003e1.4 Translating Matlab Codes to Python Codes 11\u003c\/p\u003e \u003cp\u003e1.5 Conclusion 16\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 No-code Generative AI for Trading Strategies Development 17\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e2.1 Creating Codes from a Strategy Specification 19\u003c\/p\u003e \u003cp\u003e2.2 Summarizing a Trading Strategy Paper and Creating Backtest Codes from It 34\u003c\/p\u003e \u003cp\u003e2.3 Searching for a Portfolio Optimization Algorithm Based on Machine Learning 45\u003c\/p\u003e \u003cp\u003e2.4 Explore Options Term Structure Arbitrage Strategies 50\u003c\/p\u003e \u003cp\u003e2.5 Conclusion 64\u003c\/p\u003e \u003cp\u003e2.6 Exercises 66\u003c\/p\u003e \u003cp\u003e2A.1 Computing Next-day’s Return 67\u003c\/p\u003e \u003cp\u003e2A.2 Uploading the Fama-French Factors 68\u003c\/p\u003e \u003cp\u003e2A.3 Combining Fama-French Factors with Next-day’s Returns 68\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Whirlwind Tour of ML in Asset Management 71\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e3.1 Unsupervised Learning 72\u003c\/p\u003e \u003cp\u003e3.2 Supervised Learning 77\u003c\/p\u003e \u003cp\u003e3.3 Deep Reinforcement Learning 99\u003c\/p\u003e \u003cp\u003e3.4 Data Engineering 100\u003c\/p\u003e \u003cp\u003e3.5 Feature Engineering 102\u003c\/p\u003e \u003cp\u003e3.6 Conclusion 106\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePart II Deep Generative Models for Trading and Asset Management 107\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 Understanding Generative AI 109\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e4.1 Why Generative Models 110\u003c\/p\u003e \u003cp\u003e4.2 Difference with Discriminative Models 110\u003c\/p\u003e \u003cp\u003e4.3 How Can We Use Them? 111\u003c\/p\u003e \u003cp\u003e4.4 Illustrating Generative Models with ChatGPT 113\u003c\/p\u003e \u003cp\u003e4.5 Hybrid Modeling: Combining Generative and Discriminative Models 119\u003c\/p\u003e \u003cp\u003e4.6 Taxonomy of Generative Models 123\u003c\/p\u003e \u003cp\u003e4.7 Conclusion 124\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 Deep Autoregressive Models for Sequence Modeling 125\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e5.1 Representation Complexity 126\u003c\/p\u003e \u003cp\u003e5.2 Representation and Complexity Reduction 127\u003c\/p\u003e \u003cp\u003e5.3 A Short Tour of Key Model Families 128\u003c\/p\u003e \u003cp\u003e5.4 Model Fitting 155\u003c\/p\u003e \u003cp\u003e5.5 Conclusions 157\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Deep Latent Variable Models 159\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e6.1 Introduction 160\u003c\/p\u003e \u003cp\u003e6.2 Latent Variable Models 162\u003c\/p\u003e \u003cp\u003e6.3 Examples of Traditional Latent Variable Models 162\u003c\/p\u003e \u003cp\u003e6.4 Learning 171\u003c\/p\u003e \u003cp\u003e6.5 Variational Autoencoder (VAE) 176\u003c\/p\u003e \u003cp\u003e6.6 VAEs for Sequential Data and Time Series 177\u003c\/p\u003e \u003cp\u003e6.7 Conclusion 181\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 7 Flow Models 183\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e7.1 Introduction 183\u003c\/p\u003e \u003cp\u003e7.2 Model Training 185\u003c\/p\u003e \u003cp\u003e7.3 Linear Flows 185\u003c\/p\u003e \u003cp\u003e7.4 Designing Nonlinear Flows 187\u003c\/p\u003e \u003cp\u003e7.5 Coupling Flows 188\u003c\/p\u003e \u003cp\u003e7.6 Autoregressive Flows 195\u003c\/p\u003e \u003cp\u003e7.7 Continuous Normalizing Flows 195\u003c\/p\u003e \u003cp\u003e7.8 Modeling Financial Time Series with Flow Models 196\u003c\/p\u003e \u003cp\u003e7.9 Conclusion 199\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 8 Generative Adversarial Networks 201\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e8.1 Introduction 202\u003c\/p\u003e \u003cp\u003e8.2 Training 204\u003c\/p\u003e \u003cp\u003e8.3 Some Theoretical Insight in GANs 208\u003c\/p\u003e \u003cp\u003e8.4 Why Is GAN Training Hard? Improving GAN Training Techniques 209\u003c\/p\u003e \u003cp\u003e8.5 Wasserstein GAN (WGAN) 211\u003c\/p\u003e \u003cp\u003e8.6 Extending GANs for Time Series 214\u003c\/p\u003e \u003cp\u003e8.7 Conclusion 215\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 9 Leveraging LLMs for Sentiment Analysis in Trading 217\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e9.1 Sentiment Analysis in Fed Press Conference Speeches Using Large Language Models 217\u003c\/p\u003e \u003cp\u003e9.2 Data: Video + Market Prices 221\u003c\/p\u003e \u003cp\u003e9.3 Speech-to-text Conversion 221\u003c\/p\u003e \u003cp\u003e9.4 Sentiment Analysis 225\u003c\/p\u003e \u003cp\u003e9.5 Experiment Results 232\u003c\/p\u003e \u003cp\u003e9.6 Conclusion 234\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 10 Efficient Inference 235\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e10.1 Introduction 235\u003c\/p\u003e \u003cp\u003e10.2 Scaling Large Language Models: High Performance, High Computational Cost, and Emergent Abilities 236\u003c\/p\u003e \u003cp\u003e10.3 Making FinBERT Faster 240\u003c\/p\u003e \u003cp\u003e10.4 Model Quantization 247\u003c\/p\u003e \u003cp\u003e10.5 Customizing Your LLM: Adapting Models to Your Needs 252\u003c\/p\u003e \u003cp\u003e10.6 Conclusions 256\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 11 Afterword 257\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e11.1 Diffusion Models 260\u003c\/p\u003e \u003cp\u003e11.2 Combining Generative Model Variants 260\u003c\/p\u003e \u003cp\u003e11.3 LLMs as Financial Advisors 261\u003c\/p\u003e \u003cp\u003eReferences 263\u003c\/p\u003e \u003cp\u003eAppendix 271\u003c\/p\u003e \u003cp\u003eA.1 Retrieving Adjusted Closing Prices and Computing Daily Returns 271\u003c\/p\u003e \u003cp\u003eA.2 Installing Python 273\u003c\/p\u003e \u003cp\u003eA.2.1 Step 1: Download Python 273\u003c\/p\u003e \u003cp\u003eA.2.2 Step 2: Install Python 274\u003c\/p\u003e \u003cp\u003eA.2.3 Step 3: Set Up a Virtual Environment (Optional but Recommended) 274\u003c\/p\u003e \u003cp\u003eA.2.4 Step 4: Install Packages with pip 274\u003c\/p\u003e \u003cp\u003eA.2.5 Step 5: Consider an Integrated Development Environment (IDE) 274\u003c\/p\u003e \u003cp\u003eA.2.6 Additional Tips 275\u003c\/p\u003e \u003cp\u003eA.3 Plotting the Risk-free-rate over the Years 276\u003c\/p\u003e \u003cp\u003eA.4 Computing the Sharpe Ratio of SPY 278\u003c\/p\u003e \u003cp\u003eA.5 Matlab Code for Computing Efficient Frontier and Finding the Tangency Portfolio 280\u003c\/p\u003e \u003cp\u003eIndex 283\u003c\/p\u003e  \u003cp\u003e\u003cb\u003eHAMLET JESSE MEDINA RUIZ\u003c\/b\u003e holds the position of Chief Data Scientist at Criteo. He specializes in time series forecasting, machine learning, deep learning, and Generative AI. He actively explores the potential of cutting-edge AI technologies, such as Generative AI across diverse applications. He holds an electronic engineering degree from Universidad Rafael Belloso Chacin in Venezuela, as well as two master’s degrees with honors in mathematics and machine learning from the Institut Polytechnique de Paris and Université Paris-Saclay. Additionally, he earned a PhD in physics from Université Paris-Saclay. Hamlet has consistently achieved first place and top ten rankings in global machine learning contests, earning the titles of Kaggle Expert and Numerai Expert for these challenges. Recently, he also earned a MicroMaster’s in finance from MIT’s Sloan School of Management. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eERNEST CHAN (ERNIE)\u003c\/b\u003e is the Founder and Chief Scientific Officer of PredictNow.ai (www.predictnow.ai), which offers AI-driven adaptive optimization solutions to the finance industry and beyond. He is also the Founder and Non-executive Chairperson of QTS Capital Management (www.qtscm.com), a quantitative CTA\/CPO since 2011. He started his career as a machine learning researcher at IBM’s T.J. Watson Research Center’s language modeling group, which produced some of the best-known quant fund managers. Ernie is the acclaimed author of three previous books, \u003ci\u003eQuantitative Trading\u003c\/i\u003e (\u003ci\u003e2nd Edition\u003c\/i\u003e), \u003ci\u003eAlgorithmic Trading\u003c\/i\u003e, and \u003ci\u003eMachine Trading\u003c\/i\u003e, all published by Wiley. More about these books and Ernie’s workshops on topics in quantitative investing and machine learning can be found at www.epchan.com. He obtained his PhD in physics from Cornell University and his BS in physics from the University of Toronto.   \u003c\/p\u003e\u003cp\u003eIn \u003ci\u003eGenerative AI for Trading and Asset Management\u003c\/i\u003e, a team of veteran finance and technology experts delivers a transformative new guide to using contemporary forms of AI technology—including unsupervised learning, supervised learning, reinforcement learning, and large language models—to improve the productivity of algorithmic and discretionary traders. \u003c\/p\u003e\u003cp\u003eThe book explains how large language models and other machine learning techniques can contribute to trader efficiency and effectiveness, from ideation to signal generation, backtesting, risk management, and portfolio optimization. It demonstrates the pros and cons of tree-based models and neural networks as they relate to financial applications and how regularization techniques can enhance out-of-sample performance. \u003c\/p\u003e\u003cp\u003e\u003ci\u003eGenerative AI for Trading and Asset Management\u003c\/i\u003e offers comprehensive explorations of the most common families of explicit and implicit generative modeling of high-dimensional data and covers their advantages and limitations in model representation and training, sampling quality and speed, and representation learning. \u003c\/p\u003e\u003cp\u003eYou’ll learn how to develop new trading strategies, manage risks, optimize your own trading behavior, and improve your portfolios. The authors explain how to train your AI models to learn and evolve in real-time positions, helping readers capitalize on market opportunities to swiftly mitigate risk. \u003c\/p\u003e\u003cp\u003eThe book also discusses how to deploy many of its insightful methods at scale, showing you effective techniques for pushing large models into production and demonstrating strategies to enhance inference efficiency, like model pruning, quantization, and knowledge distillation. \u003c\/p\u003e\u003cp\u003ePerfect for asset managers everywhere, \u003ci\u003eGenerative AI for Trading and Asset Management \u003c\/i\u003eis an invaluable resource for anyone seeking to harness the ever-changing landscape of AI tech to navigate financial markets.   \u003c\/p\u003e\u003cp\u003e\u003cb\u003ePraise for GENERATIVE AI FOR TRADING AND ASSET MANAGEMENT\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003e“Kudos to Medina Ruiz and Chan for sharing their hard-earned knowledge and creating a practitioner resource that is timely, relevant, and ‘roll up your sleeves’ practical. They have the distinction of bringing to life a text that is both information-dense and comprehensive yet highly engaging and readable—a rare combination! Whether you plan to engage with Generative AI as your co-pilot or go deep into coding custom solutions, this book will serve as both a trusted guide and as a foundational reference. The addition of accompanying code repositories and notebooks will allow organizations to hit the ground running with Generative AI. I anticipate that I’ll have a well-thumbed copy near my computer monitor in the very near future!”\u003cbr\u003e \u003cb\u003e—JAY VYAS, \u003c\/b\u003eChief Strategy Officer, Firinne Capital; former Head of Research and Innovation, Canada Pension Plan Investment Board  \u003c\/p\u003e\u003cp\u003e“The book by Medina Ruiz and Chan has appeared when people are still wondering what ChatGPT in particular and LLMs in general are all about. Those who will read and implement it first will have an undisputed advantage: they have learned the industry-defining subject from experts who are known for their knack for making the complex easily accessible. The book is not just about LLMs. It is about Generative AI and its intelligent use in trading and, more generally, finance. Highly recommended for practitioners and academics alike.”\u003cbr\u003e \u003cb\u003e—PAUL ALEXANDER BILOKON, \u003c\/b\u003eCEO, Thalesians Ltd; Visiting Professor, Imperial College London  \u003c\/p\u003e\u003cp\u003e“\u003ci\u003eGenerative AI for Trading and Asset Management\u003c\/i\u003e by renowned quant Hamlet Medina Ruiz and Ernest Chan is the definitive guide to harnessing Generative AI in financial markets. From no-code AI for finance beginners to the fine-tuning of deep, multi-layered models, this book unpacks cutting-edge techniques with clarity and precision. Dive into deep autoregressive models, latent variable architectures, flow-based models, sentiment analysis, GANs, and LLMs—all tailored for quantitative trading and asset management. Whether you’re an aspiring quant, a hedge fund strategist, or a Goldman Sachs MD, this book is your blueprint for staying ahead in the AI-driven evolution of finance.”\u003cbr\u003e \u003cb\u003e—ALEXANDER FLEISS, \u003c\/b\u003eCEO of Rebellion Research, AI Asset Manager \u0026amp; Research Think Tank, Advisory Board Member of both Cornell Financial Engineering \u0026amp; Fordham Gabelli Quantitative Finance, Editor of \u003ci\u003eThe\u003c\/i\u003e \u003ci\u003eJournal of Financial Data Science\u003c\/i\u003e  \u003c\/p\u003e\u003cp\u003e“It is no exaggeration to view the last few years as the beginning of a new epoch in technology, much of which is propelled by the enormous advances in deep learning and generative AI. Hamlet and Ernie have done the investment community a great service by providing the foundation of a very difficult but exciting subject from the practitioners’ perspective. It is not only accessible to readers with rudimentary backgrounds in AI, but also informative and inspiring for even experienced machine learning experts.”\u003c\/p\u003e \u003cp\u003eWill Cong, The Rudd Family Professor of Management \u0026amp; Professor of Finance, Cornell University SC Johnson College of Business\u003c\/p\u003e \u003cp\u003e \u003c\/p\u003e \u003cp\u003e“As a researcher in signal and image processing, I have witnessed firsthand how deep learning and generative AI have revolutionized fields like computer vision and natural language processing. This book demonstrates how these powerful tools can bring similar transformations to finance. With a clear and concise approach, it serves as a guide for a broad audience ––– whether you come from an engineering background or the financial sector ––– seeking to understand and apply generative AI in tackling financial challenges. By seamlessly translating core concepts from statistical signal processing and machine learning into finance, the authors provide intuitive explanations, solid mathematical foundations, and practical coding examples.\u003c\/p\u003e \u003cp\u003eThe result is a resource that not only bridges disciplines but also equips readers with the knowledge and tools to address real-world financial problems. Whether you are an engineer venturing into finance or a finance professional embracing AI, this book distills insights typically spread across hundreds of pages into a single, accessible volume ––– a must read for anyone looking to stay ahead in this rapidly evolving field.”\u003c\/p\u003e \u003cp\u003eDr. Giuseppe Valenzise, CNRS (French National Centre for Scientific Research) researcher, Université Paris-Saclay, Editor-in-Chief of EURASIP Journal on Image and Video Processing\u003c\/p\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47989277589733,"sku":"NP9781394266975","price":55.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781394266975.jpg?v=1761783487","url":"https:\/\/k12savings.com\/es\/products\/generative-ai-for-trading-and-asset-management-isbn-9781394266975","provider":"K12savings","version":"1.0","type":"link"}