Ni, Hao (Lecturer in mathematics),
An introduction to machine learning in quantitative finance / by Hao Ni (University College London, UK), Xin Dong (Citadel Securities LLC, UK), Jinsong Zheng (Huatai Securities, China) and Guangxi Yu (SWS Research, China). - 1 online resource (xxiv, 238 pages). - Advanced textbooks in mathematics . - Advanced textbooks in mathematics. .
Includes bibliographical references and index.
Preface -- About the authors -- Acknowledgments -- Disclaimer -- Listings -- Overview of machine learning and financial applications -- Supervised learning -- Linear regression and regularization -- Tree-based models -- Neural networks -- Cluster analysis -- Principal component analysis -- Reinforcement learning -- Case study in finance : home credit default risk -- Bibliography -- Index.
"In today's world, we are increasingly exposed to the words "machine learning" (ML), a term which sounds like a panacea designed to cure all problems ranging from image recognition to machine language translation. Over the past few years, ML has gradually permeated the financial sector, reshaping the landscape of quantitative finance as we know it. An Introduction to Machine Learning in Quantitative Finance aims to demystify ML by uncovering its underlying mathematics and showing how to apply ML methods to real-world financial data. In this book the authors Provide a systematic and rigorous introduction to supervised, unsupervised and reinforcement learning by establishing essential definitions and theorems. Dive into various types of neural networks, including artificial nets, convolutional nets, recurrent nets and recurrent reinforcement learning. Summarize key contents of each section in the tables as a cheat sheet. Include ample examples of financial applications. Showcase how to tackle an exemplar ML project on financial data end-to-end. Supplement Python codes of all the methods/examples in a GitHub repository. Featured with the balance of mathematical theorems and practical code examples of ML, this book will help you acquire an in-depth understanding of ML algorithms as well as hands-on experience. After reading An Introduction to Machine Learning in Quantitative Finance, ML tools will not be a black box to you anymore, and you will feel confident in successfully applying what you have learnt to empirical financial data! The Python codes contained within An Introduction to Machine Learning in Quantitative Finance have been made publicly available on the author's GitHub: https://github.com/deepintomlf/mlfbook.git that contains supplementary Python codes of all methods/examples. Featured with the balance of mathematical theorems and practical code examples of ML, this book will help you acquire an in-depth understanding of ML algorithms as well as hands-on experience. After reading An Introduction to Machine Learning in Quantitative Finance, ML tools will not be a black box to you anymore, and you will feel confident in successfully applying what you have learnt to empirical financial data!"--Publisher's website.
Mode of access: World Wide Web.
System requirements: Adobe Acrobat Reader.
9781786349378
Finance--Mathematical models.
Machine learning.
Electronic books.
HG106 / .N52 2021
332.0285/631
An introduction to machine learning in quantitative finance / by Hao Ni (University College London, UK), Xin Dong (Citadel Securities LLC, UK), Jinsong Zheng (Huatai Securities, China) and Guangxi Yu (SWS Research, China). - 1 online resource (xxiv, 238 pages). - Advanced textbooks in mathematics . - Advanced textbooks in mathematics. .
Includes bibliographical references and index.
Preface -- About the authors -- Acknowledgments -- Disclaimer -- Listings -- Overview of machine learning and financial applications -- Supervised learning -- Linear regression and regularization -- Tree-based models -- Neural networks -- Cluster analysis -- Principal component analysis -- Reinforcement learning -- Case study in finance : home credit default risk -- Bibliography -- Index.
"In today's world, we are increasingly exposed to the words "machine learning" (ML), a term which sounds like a panacea designed to cure all problems ranging from image recognition to machine language translation. Over the past few years, ML has gradually permeated the financial sector, reshaping the landscape of quantitative finance as we know it. An Introduction to Machine Learning in Quantitative Finance aims to demystify ML by uncovering its underlying mathematics and showing how to apply ML methods to real-world financial data. In this book the authors Provide a systematic and rigorous introduction to supervised, unsupervised and reinforcement learning by establishing essential definitions and theorems. Dive into various types of neural networks, including artificial nets, convolutional nets, recurrent nets and recurrent reinforcement learning. Summarize key contents of each section in the tables as a cheat sheet. Include ample examples of financial applications. Showcase how to tackle an exemplar ML project on financial data end-to-end. Supplement Python codes of all the methods/examples in a GitHub repository. Featured with the balance of mathematical theorems and practical code examples of ML, this book will help you acquire an in-depth understanding of ML algorithms as well as hands-on experience. After reading An Introduction to Machine Learning in Quantitative Finance, ML tools will not be a black box to you anymore, and you will feel confident in successfully applying what you have learnt to empirical financial data! The Python codes contained within An Introduction to Machine Learning in Quantitative Finance have been made publicly available on the author's GitHub: https://github.com/deepintomlf/mlfbook.git that contains supplementary Python codes of all methods/examples. Featured with the balance of mathematical theorems and practical code examples of ML, this book will help you acquire an in-depth understanding of ML algorithms as well as hands-on experience. After reading An Introduction to Machine Learning in Quantitative Finance, ML tools will not be a black box to you anymore, and you will feel confident in successfully applying what you have learnt to empirical financial data!"--Publisher's website.
Mode of access: World Wide Web.
System requirements: Adobe Acrobat Reader.
9781786349378
Finance--Mathematical models.
Machine learning.
Electronic books.
HG106 / .N52 2021
332.0285/631