Bayesian Machine Learning in Quantitative Finance
Description
This book offers a comprehensive discussion of the Bayesian inference framework and demonstrates why this probabilistic approach is ideal for tackling the various modelling problems within quantitative finance. It demonstrates how advanced Bayesian machine learning techniques can be applied within financial engineering, investment portfolio management, insurance, municipal finance management as well as banking.
The book covers a broad range of modelling approaches, including Bayesian neural networks, Gaussian processes and Markov Chain Monte Carlo methods. It also discusses the utility of Bayesian inference in quantitative finance and discusses future research goals in the applications of Bayesian machine learning in quantitative finance. Chapters are rooted in the theory of quantitative finance and machine learning while also outlining a range of practical considerations for implementing Bayesian techniques into real-world quantitative finance problems. This book is ideal for graduate researchers and practitioners at the intersection of machine learning and quantitative finance, as well as those working in computational statistics and computer science more broadly.
More details
Other editions
Additional editions
Persons
Wilson Tsakane Mongwe is a machine learning research fellow at the University of Johannesburg, South Africa, and an Associate Director and the Head Quantitative Analyst at a Big Four audit firm's Financial Services Advisory business unit. He was previously the Head of Market Risk and Capital Analytics at a tier 1 South African bank's Global Markets division. He holds a Masters in Mathematical Finance from the University of Cape Town and a PhD in Artificial Intelligence from the University of Johannesburg. He was awarded a Google PhD fellowship in machine learning in 2020, which supported his PhD research. He received the Mail and Guardian Top 200 Young South Africans award for 2020, and was recognized as one of 30 Young Mandela's in 2022 by News24. He is an author of the machine learning book entitled "Hamiltonian Monte Carlo Methods in Machine Learning".
Rendani Mbuvha is currently Associate Professor of Actuarial Science in the Department of Mathematics at the University of Manchester, UK. Previously, he served as a Google DeepMind Academic Fellow with Queen Mary University of London (QMUL) and as an Associate Professor at the University of Witwatersrand, South Africa. He is a fellow of the Institute and Faculty of Actuaries and Co-Founder of AfriClimate AI, a grassroots community focused on AI for Climate action research in the global south. He has published extensively in probabilistic inference in machine learning, renewable energy modeling, and computational finance.
Tshilidzi Marwala is United Nations Under-Secretary-General and Rector of the UN University and was formerly the Vice-Chancellor of the University of Johannesburg (UJ), South Africa. He was the trustee of the Nelson Mandela Foundation and is a member of the American Academy of Arts and Sciences, Chinese Academy of Sciences, The World Academy of Sciences and the African Academy of Sciences. He holds a Bachelor of Science in Mechanical Engineering from Case Western Reserve University and a PhD in Artificial Intelligence from the University of Cambridge. He has published 27 books in artificial intelligence and related areas.
Content
1 Introduction To Bayesian Machine Learning In Quantitative Finance.- 2 Background To Bayesian Machine Learning In Quantitative Finance.- 3 On the Stochastic Alpha Beta Rho Model and Hamiltonian Monte Carlo Techniques.- 4 Learning Equity Volatility Surfaces using Sparse Gaussian Processes.- 5 Analyzing South African Equity Option Prices Using Normalizing Flows.- 6 Sparse and Distributed Gaussian Processes For Modeling Corporate Credit Ratings.- 7 Bayesian Detection Of Recovery On Charged-Off Loan Accounts.- 8 Bayesian Audit Outcome Model Selection Using Normalising Flows.- 9 Bayesian Detection Of Unauthorized Expenditure Using Langevin and Hamiltonian Monte Carlo.- 10 Bayesian Neural Network Inference Of Motor Insurance Claims.- 11 Shadow and Adaptive Hamiltonian Monte Carlo Methods For Calibrating The Nelson and Siegel Model.- 12 Static and Dynamic Nested Sampling For Yield Curve Model Selection.- 13 A Bayesian Investment Analyst On The Johannesburg Stock Exchange.- 14 Conclusions to Bayesian Machine Learning In Quantitative Finance.