|
on Market Microstructure |
| By: | Luca Lalor; Anatoliy Swishchuk |
| Abstract: | Algorithmic and High-Frequency trading (HFT) has become one of the main ways to complete transactions in many of today's major financial markets, with these transactions taking place inside what is called the limit order book (LOB). Developing sophisticated trading algorithms that accurately mimic LOB data is therefore a major topic in this area. In recent times, it has been proven that LOB data often follows non-Markovian dynamics, thus, we believe these models more accurately describe how the LOB would evolve. In this paper, we consider acquisition and liquidation problems for semi-Markov and Hawkes jump-diffusion models. We begin by developing jump-diffusion models to capture these dynamics and then proceed to use diffusion approximations for the jump parts. The optimal solutions to these trading problems are formulated under the stochastic optimal control framework and via numerical methods. Strategy simulations for the acquisition and liquidation problems are considered as well, where we show sample price paths for our price processes, average traded prices, inventory and trading speed paths. This analysis gives a general picture of how one could analyse how these strategies could perform under our more general price processes. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.12776 |
| By: | Kyungsub Lee |
| Abstract: | This study explores the prediction of high-frequency price changes using deep learning models. Although state-of-the-art methods perform well, their complexity impedes the understanding of successful predictions. We found that an inadequately defined target price process may render predictions meaningless by incorporating past information. The commonly used three-class problem in asset price prediction can generally be divided into volatility and directional prediction. When relying solely on the price process, directional prediction performance is not substantial. However, volume imbalance improves directional prediction performance. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.14157 |
| By: | Luca Lalor; Anatoliy Swishchuk |
| Abstract: | In this paper, we study the effects of fill probabilities and adverse fills on the trading strategy simulation process. We specifically focus on a stochastic optimal control market-making problem and test the strategy on ES (E-mini S&P 500), NQ (E-mini Nasdaq 100), CL (Crude Oil) and ZN (10-Year Treasury Note), which are some of the most liquid futures contract listed on the CME (Chicago Mercantile Exchange). We provide empirical evidence which shows how fill probabilities and adverse fills can significantly effect performance, and propose a more prudent simulation framework for dealing with this. Many previous works aim to measure different types of adverse selection in the limit order book, however, they often simulate price processes and market orders independently. This has the ability to largely inflate the performance of a short-term style trading strategy. Our studies show that using more realistic fill probabilities, and tracking adverse fills, in the strategy simulation process, more accurately portrays how these types of trading strategies would perform in reality. |
| Date: | 2024–09 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2409.12721 |
| By: | Corgnet, Brice; DeSantis, Mark; Siemroth, Christoph |
| JEL: | C92 D61 G12 G14 G41 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:vfsc24:302411 |