Hands-On Deep Learning for Finance: Implement deep learning techniques and algorithms to create powerful trading strategies
by: Luigi Troiano,Arjun Bhandari,et al.
Print Length 页数: 390 pages
Publisher finelybook 出版社: Packt Publishing – ebooks Account (March 10,2020)
Language 语言: English
ISBN-10: 1789613175
ISBN-13: 9781789613179
Book Description
Take your quantitative strategies to the next level by: exploring nine examples that make use of cutting-edge deep learning technologies,including CNNs,LSTM,GANs,reinforcement learning,and CapsNets
Quantitative methods are the vanguard of the investment management industry. With this book,you’ll learn how you can use deep learning models to capture insights from financial data and implement deep learning models using Python libraries such as TensorFlow and Keras.
Starting with an overview of deep learning in the finance domain,you’ll use neural network architectures such as CNNs,RNNs,and LSTM to develop,test,and validate trading-based models. You’ll enhance your understanding of financial models by: applying deep learning algorithms and exploit them systematically. With a practical approach,this book will cover different aspects of asset management and guide you in enhancing financial trading strategies. As you advance,you’ll perform index replication and forecasting using autoencoders and LSTM,respectively,and move on to using advanced NLP techniques and BLSTM to process newsfeed for specific stocks. This deep learning book will initially take you through using CNNs to develop a trading signal with simple technical indicators and then using CapsNets to improve their performance. Toward the end,you’ll even learn how to use generative adversarial networks (GANs) to perform risk management and implement deep reinforcement learning for automated trading.
What you will learn
Implement quantitative financial models using the various building blocks of a deep neural network
Build,train,and optimize deep networks from scratch
Use LSTM to process data sequences such as time series and news feeds
Implement convolutional neural networks (CNNs),CapsNets,and other models to create trading strategies
Adapt popular neural networks for pattern recognition in finance using transfer learning
Automate investment decisions by: using reinforcement learning
Discover how a risk model can be constructed using D-GAN
Contents
Preface
Section 1: Introduction
Chapter 1: Deep Learning for Finance 101
Chapter 2: Designing Neural Network Architectures
Chapter 3: Constructing,Testing,and Validating Models
Section 2: Foundational Architectures
Chapter 4: Index Replication by Autoencoders
Chapter 5: Volatility Forecasting by LSTM
Chapter 6: Trading Rule ldentification by CNN
Section 3: Hybrid Models
Chapter 7: Asset Allocation by LSTM over a CNN
Chapter 8: Digesting News Using NLP with BLSTM
Chapter 9: Risk Measurement Using GAN
Section 4: Advanced Techniques
Chapter 10: Chart Visual Analysis by Transfer Learning
Chapter 11: Better Chart Analysis Using CapsNets
Chapter 12: Training Trader Robots Using Deep Reinforcement Learning
Chapter 13: What Next?
Other Books You May Enjoy
Index