About
I'm Peter Pommergård Lind a Ph.D.-Fellow in Finance at Aalborg University. I research the exciting cross-section of machine learning and option theory.
Ph.D.-Fellow in Finance at Aalborg University.
Currently, I seek a Ph.D. in Finance specializing in machine learning and option theory. I have a Bachelor’s and a Master’s degree in Actuarial Mathematics from University of Copenhagen. Some of my work experience include 2 years at PFA as an Actuary and several years teaching at University of Copenhagen and Aalborg University.
- Birthday: 8 July 1995
- Papers: SSRN
- Phone: +45 51 15 78 81
- City: New York, USA and Aalborg, Denmark
- Age: 28
- Degree: Cand. act.
- Email: ppl@business.aau.dk
- Job: Ph.D.-Fellow in Finance
I love sports and play all kinds of sports such as table football, soccer, tennis, etc... Other interests include card games, computer science, mathematics, and trading.
Research
I research machine learning methods for Finance. More specifically, I develop fast and accurate methods for option valuation and calibration. In my research, I combine classical option theory methods with modern methods such as neural networks, tree regression, and differential machine learning to produce powerful tools for trading and risk management. I hope these tools can improve solutions to complex, real-world problems, changing the world.
Papers
Delta Least Squares Monte Carlo Pricing of American Options
We present a new simulation-based American option pricing method, Delta least squares Monte Carlo (Delta LSM).
Whereas the classical LSM method from Longstaff & Schwartz (2001) uses only the discounted payoff to learn the continuation value,
Delta LSM uses both the discounted payoff and its derivative (Delta) to estimate regression coefficients.
The Delta LSM is straightforward to implement and comes at a little extra numerical cost. It is quite literally an add-on to the LSM method.
Our numerical experiments show that irrespective of your speed/safety preference – and robustly across market scenarios – Delta LSM gives a marked improvement over classical LSM.
Preprint available online here.
NN de-Americanization: A Fast and Efficient Calibration Method for American-Style Options
Neural network (NN) de-Americanization produces fast and accurate pseudo-European option prices from American option market prices,
facilitating the calibration of derivative models. The industry approach binomial de-Americanization takes a flat volatility surface as input.
In contrast, the NN de-Americanization method takes the detailed shape of the volatility surface as an input;
this is critical for the accurate evaluation of the early exercise premium (EEP) when interest rates are not close to zero.
Preprint available online here.
Overcoming the Feature Selection Issue in the Pricing of American Options
The feedforward neural network Monte Carlo method (FNNMC) exhibits more robustness and
accuracy than the state-of-the-art least squares Monte Carlo method (LSM) in pricing several
American-style options. Specifically, the FNNMC price estimates are accurate for basket options,
where the FNNMC price errors are more than four times smaller than the LSM with the best
choice of basis functions. By training the neural network the FNNMC avoids the issue of choosing
a proper set of basis functions. Hence we circumvent manually engineering the features for each
type of option. Furthermore, we explore in-depth the hyperparameter selection for the FNNMC.
In the exploration, we use a novel approach called price grid search, where the search is done at
the price level instead of at the usual regression level.
Preprint available online here.
Outreach
Upcoming
- Jul 2024, NN de-Americanization, Bachelier World Congress 2024, Rio de Janeiro, Brazil
Past
- Mar 2024, NN de-Americanization, Stony Brook Quant Finance Webinar, New York, USA
- Jan 2024, NN de-Americanization, Vola Dynamics, New York, USA
- Jan 2024, NN de-Americanization, OptionMetrics, New York, USA
- Nov 2023, Danish Podcast on Option Theory, Rig på viden, Copenhagen, Denmark
- Nov 2023, NN de-Americanization, QuantMinds 2023, London, England
- Oct 2023, NN de-Americanization, Bloomberg Quant (BBQ) Seminar Series, New York, USA
- Mar 2022, Overcoming the Feature Selection Issue in the Pricing of American Options, AU Econometrics-Finance Lunch Seminar, Aarhus, Denmark
- Mar 2022, Overcoming the Feature Selection Issue in the Pricing of American Options, CBS Junior Economic Seminar, Copenhagen, Denmark
Resume
Summary
Peter Pommergård Lind
Ph.D. fellow in Finance (Quantitative Finance) at Aalborg University Business School. Studying option pricing and machine learning methods in Finance.
- Fibigerstræde 11, office 61
- +45 51 15 78 81
- ppl@business.aau.dk
Education
Ph.D. in Finance
Expected graduation date: 2024
Aalborg University, Business School, Aalborg
Keywords: Option Theory, Machine Learning, Numerical Method, Deep Learning, Optimal Stopping
M.S. in Actuarial Mathematics
Graduated 2020
University of Copenhagen, Department of Mathematics, Copenhagen
Thesis: Classical Option Pricing Theory and Extensions to Deep Learning
B.S. in Actuarial Mathematics
Graduated 2019
University of Copenhagen, Department of Mathematics, Copenhagen
Employment
Ph.D. Fellow in Finance
2021 - Present
Aalborg University, Aalborg, Denmark
- Researching in Machine Learning and Numerical Methods Option Theory
Internship: Front Office Research Analyst
Summer 2023
Norlys Energy Trading, Aalborg, Denmark
- Developed a valuation model for gas storage and optimal execution
Teaching Assistant
2019 - 2022
University of Copenhagen, Copenhagen, Denmark
Held exercise classes for both undergraduate and graduate students at Aalborg University and University of Copenhagen (see below in 'Teaching Portfolio' for more details).
Actuary
2019 - 2021
PFA Pension, Copenhagen, Denmark
Numerical software design and solutions to handle the biggest Danish pension fund internal policy system.
Internship: Front Office Student Assistant
Summer 2020
PFA Asset Management, Copenhagen, Denmark
Took the charge in implementing efficient routines for interest rate curve interpolation/extrapolation (Monotone Convex and Smith-Wilson) for the internal Quant library.
Teaching Portfolio
I consider myself privileged to teach an array of diverse courses to students who truly inspire me.
Year | Title | Study level | Responsibility |
---|---|---|---|
Spring 2023 | Master Theses in Economics | Master | Supervisor |
Spring 2023 | Financial Engineering Project | Master | Supervisor |
Spring 2022 | Financial Derivatives | Master | Teaching Assistant |
Spring 2022 | Bachelor Thesis in Economics | Bachelor | Supervisor |
Fall 2021 | Portfolio Theory | Master | Teaching Assistant |
Fall 2021 | International Finance | Master | Teaching Assistant |
Fall 2021 | Statistical Analyses of Econometric Time Series | Master | Teaching Assistant |
Spring 2021 | Mathematical Modelling | Bachelor | Teaching Assistant |
Fall 2020 | Continuous-Time Finance | Master | Teaching Assistant |
Fall 2020 | Basic Non-Life Insurance Mathematics | Bachelor | Teaching Assistant |
Spring 2020 | Topics in Non-Life Insurance | Master | Teaching Assistant |
Spring 2020 | Insurance and Law Topics | Bachelor | Teaching Assistant |
Fall 2019 | Introduction to Economics | Bachelor | Teaching Assistant |
Fall 2019 | Introduction to Numerical Analysis | Bachelor | Teaching Assistant |
Contact
Thank you for visiting my website. If you have any questions or would like to learn more about my research, please do not hesitate to send me an email at ppl@business.aau.dk.