Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

A Machine Learning Approach to the Optimal Execution Problem

Donahoe, Quinn (2019) A Machine Learning Approach to the Optimal Execution Problem. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

This is the latest version of this item.

[img] PDF
Restricted to University of Pittsburgh users only until 30 January 2024.

Download (961kB) | Request a Copy

Abstract

The Optimal Execution Problem has, for over a decade been of interest in financial mathematics. Solving the problem has, from the mathematics perspective involved using the dynamic programming principle in order to obtain a Hamilton-Jacobi-Bellman PDE to solve for the ideal trading curve. Taking the extended framework of Almgren's 2012 paper on the optimal execution problem with stochastic volatility and liquidity, we begin a statistical learning approach realizing parameters via real market data. From this point, learning algorithms are applied to find optimal trading curves in both limit order and market order strategic environments. We compare these trading curves with trading curves obtained from the classical approach.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Donahoe, Quinnqad1@pitt.edu
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairYao, Songsongyao@pitt.edu
Committee MemberChadam, Johnchadam@pitt.edu
Committee MemberNeilan, Michaelneilan@pitt.edu
Committee MemberZutter, Chadczutter@pitt.edu
Date: 30 January 2019
Date Type: Publication
Defense Date: 5 September 2018
Approval Date: 30 January 2019
Submission Date: 21 October 2018
Access Restriction: 5 year -- Restrict access to University of Pittsburgh for a period of 5 years.
Number of Pages: 114
Institution: University of Pittsburgh
Schools and Programs: Dietrich School of Arts and Sciences > Mathematics
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: none
Date Deposited: 30 Jan 2019 22:11
Last Modified: 30 Jan 2019 22:11
URI: http://d-scholarship.pitt.edu/id/eprint/35748

Available Versions of this Item

  • A Machine Learning Approach to the Optimal Execution Problem. (deposited 30 Jan 2019 22:11) [Currently Displayed]

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item