An Introduction to Machine Learning in Quantitative Finance

Abstract: 

Over the past few years, machine learning (ML) has gradually permeated the financial sector, reshaping the landscape of quantitative finance as we know it. This tutorial aims to demystify ML by uncovering its underlying mathematics and showing how to apply ML methods to real-world financial data. I will start with a brief overview of machine learning in quantitative finance and then dive into supervised learning, in particular deep learning. I will showcase the prediction task of the high-frequency limit order book using deep learning end-to-end as an illustrative example. This tutorial will help you acquire an in-depth understanding of deep learning as well as practical financial applications.

Session Outline
Module 1: Overview of Machine learning in Quantitative finance
You will have a high-level picture of machine learning techniques in quantitative finance. Besides, this module will introduce the main categories of machine learning (i.e. supervised learning, unsupervised learning and reinforcement learning) with demonstrative financial applications.
Module 2: Introduction to supervised learning
You will learn a systematic framework of supervised learning, which will enable you to learn new supervised learning algorithms quickly. This module will cover linear regression, non-linear regression and some important aspects of supervised learning models, such as the tradeoff between the complexity of the model and limited data size.
Module 3: Introduction to neural networks and deep learning
You will familiarize yourself with different types of neural networks, including the full connected neural network (DNN) and the recurrent neural network (RNN). You will learn the mathematical formulation of neural network and parameter optimization used in deep learning.
Module 4: The application of deep learning in finance
This module will provide you with a concrete example of predicting the price movement of the limit-order book using the recurrent neural network step-by-step. Through this example, you will learn the pipeline of tackling an empirical financial data problem using machine learning end-to-end.

Background Knowledge
The participants are required to have basic knowledge of statistics and probability.

Bio: 

Dr. Hao Ni is an associate professor in financial mathematics at UCL and a Turing fellow at Alan Turing Institute since September 2016. Prior to this Dr. Hao Ni was a visiting postdoctoral researcher at ICERM and Department of Applied Mathematics at Brown University from 2012/09 to 2013/05 and continued her postdoctoral research at the Oxford-Man Institute of Quantitative Finance until 2016. Dr. Hao Ni finished her D.Phil. in mathematics in 2012 under the supervision of Professor Terry Lyons at University of Oxford.

Open Data Science

 

 

 

Open Data Science
One Broadway
Cambridge, MA 02142
info@odsc.com

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Youtube
Consent to display content from - Youtube
Vimeo
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google