Seminar by Łukasz Adamski, a PhD student at the Faculty of Economic Sciences
We invite you to the 70th seminar organised jointly by the QFRG and DSLab research centres. During the meeting, Łukasz Adamski (Department of Quantitative Finance and Machine Learning) will discuss the results of the study entitled “Reading Between the Rates: How Options Price Fed Uncertainty”. The study was co-authored by dr hab. Robert Ślepaczuk, prof. ucz. (Department of Quantitative Finance and Machine Learning).
We invite you to the meeting on May 25 at 4.45 pm. It will take place in room B002 (Faculty of Economic Sciences, University of Warsaw, Długa 44/50), and remotely via Zoom – to receive the link for the online meeting, please send an email to zqR.C@eY!+c-K4x6BuhI8j]#[kdBv/zP7@~RmT*pC~Z^R&W.
The lecture will last approximately 45 minutes, followed, as usual, by a discussion.
We ask everyone interested in attending the lecture to arrive, if possible, 5 minutes before it begins.
We invite you to read the abstract, available below.
----
Abstract
Our primary goal is to forecast and empirically examine the evolution of the implied volatility (IV) surface, with particular focus on the dates of scheduled meetings of the Federal Open Market Committee (FOMC). Firstly, we check for a monotonic increase of IV before the announcement, which is hypothesised to be stronger for short-dated, out-the-money (OTM) options in high volatility regimes. In the second part, the hypotheses turn the focus to verifying if the ML framework can beat the benchmark random walk in forecasting this effect. A feature related to dates of scheduled FOMC meetings augments the model, which allows us to discover if it can learn the effect of elevated pre-announcement uncertainty. Our contribution relies mainly on the quantitative prediction of the pre-announcement effect and the inclusion of exogenous information inside the ML framework used for the IV surface forecasting. It is also a first attempt to apply ML models directly on the IV surface without relying on dimensionality reduction. To achieve this, we employ a convolutional two-dimensional LSTM model, which is capable of learning spatio-temporal signals in the surface. Our analysis reveals that the edge of the ML framework can be limited due to the noisy characteristics of the IV surface. Nevertheless, our study reinforces the perspective that ML models can effectively forecast the IV surface also during abnormal days.
Keywords: Implied Volatility Surface, Convolutional 2D LSTM, FOMC Announcements, Pre-announcement Uncertainty