EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
224. Merged LSTM-MLP for option pricing
Invited abstract in session TB-57: Risk management and valuation of financial contracts, stream Modern Decision Making in Finance and Insurance.
Tuesday, 10:30-12:00Room: S06 (building: 101)
Authors (first author is the speaker)
| 1. | Rita Pimentel
|
| Industrial Economics and Technology Management, NTNU | |
| 2. | Morten Risstad
|
| Industrial Economics and Technology Management, NTNU | |
| 3. | Erlend Stegavik Rygg
|
| 4. | Jacob Vinje
|
| 5. | Sjur Westgaard
|
| Department of Industrial Economics and Technology Management, Norwegian University of Science and Technology | |
| 6. | Cassandra Wu
|
| Industrial Economics and Technology Management, Norwegian University of Science and Technology |
Abstract
This paper proposes a new merged LSTM-MLP deep learning approach for option pricing. The model has the advantage of combining time series data with static data. On the one hand, it learns from historical asset returns, as well as considers the option characteristics at the pricing date. This configuration does not need an estimation for an explicit volatility measure, improving upon existing methods. We test it on S&P 500 European call options from 2015 to 2022. The model excels in accuracy and risk-adjusted returns, showcasing its usefulness in real-life applications.
Keywords
- Financial Modelling
- Artificial Intelligence
Status: accepted
Back to the list of papers