|
on Market Microstructure |
| By: | Luca Lalor; Anatoliy Swishchuk |
| Abstract: | We develop a deep reinforcement learning (RL) framework for an optimal market-making (MM) trading problem, specifically focusing on price processes with semi-Markov and Hawkes Jump-Diffusion dynamics. We begin by discussing the basics of RL and the deep RL framework used, where we deployed the state-of-the-art Soft Actor-Critic (SAC) algorithm for the deep learning part. The SAC algorithm is an off-policy entropy maximization algorithm more suitable for tackling complex, high-dimensional problems with continuous state and action spaces like in optimal market-making (MM). We introduce the optimal MM problem considered, where we detail all the deterministic and stochastic processes that go into setting up an environment for simulating this strategy. Here we also give an in-depth overview of the jump-diffusion pricing dynamics used, our method for dealing with adverse selection within the limit order book, and we highlight the working parts of our optimization problem. Next, we discuss training and testing results, where we give visuals of how important deterministic and stochastic processes such as the bid/ask, trade executions, inventory, and the reward function evolved. We include a discussion on the limitations of these results, which are important points to note for most diffusion models in this setting. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.14504 |
| By: | Murat Tinic; Zeynep Ö. nder |
| Abstract: | This paper examines whether the bank-affiliated brokerage houses actively use the private information they possess about their affiliated publicly traded real estate investment trusts (REITs) around earnings announcements in Borsa Istanbul (BIST) between 2005 and 2015. The legal framework surrounding Turkish Real Estate Investment Trusts makes it particularly interesting to investigate the secondary market implications of the information asymmetry between majority and minority shareholders within BIST. We propose bank affiliation as a potential mechanism for disseminating private information about the official quarterly earnings announcements for the first time in the literature by assigning exogenous classifications across different investor types at high frequency. Our results indicate a substantial informed trading activity passing through bank-affiliated brokerage houses around earnings announcements, especially with the increase in earnings (when the announcement carries good news). Through intraday panel regressions, we also document that private information attributed to trades submitted through affiliated brokerage houses significantly enhances market quality by increasing future liquidity and reducing future volatility levels, whereas private information percolated through unaffiliated brokerage houses demand liquidity and increases volatility, reducing overall market quality. |
| Keywords: | emerging economies; Housing Supply; Price Elasticity; Undevelopable Land |
| JEL: | R3 |
| Date: | 2024–01–01 |
| URL: | https://d.repec.org/n?u=RePEc:arz:wpaper:eres2024-210 |
| By: | Carl von Havighorst; Vincil Bishop III |
| Abstract: | This research presents a novel approach to predicting option movements by analyzing residual transactions, which are trades that deviate from standard hedging activities. Unlike traditional methods that primarily focus on open interest and trading volume, this study argues that residuals can reveal nuanced insights into institutional sentiment and strategic positioning. By examining these deviations, the model identifies early indicators of market trends, providing a refined framework for forecasting option prices. The proposed model integrates classical machine learning and regression techniques to analyze patterns in high frequency trading data, capturing complex, non linear relationships. This predictive framework allows traders to anticipate shifts in option values, enhancing strategies for better market timing, risk management, and portfolio optimization. The model's adaptability, driven by real time data processing, makes it particularly effective in fast paced trading environments, where early detection of institutional behavior is crucial for gaining a competitive edge. Overall, this research contributes to the field of options trading by offering a strategic tool that detects early market signals, optimizing trading decisions based on predictive insights derived from residual trading patterns. This approach bridges the gap between conventional metrics and the subtle behaviors of institutional players, marking a significant advancement in options market analysis. |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2410.16563 |
| By: | Brokmann, Xavier; Itkin, David; Muhle-Karbe, Johannes; Schmidt, Peter |
| Abstract: | Empirical studies in various contexts find that the price impact of large trades approximately follows a power law with exponent between 0.4 and 0.7. Yet, tractable formulas for the portfolios that trade off predictive trading signals, risk, and trading costs in an optimal manner are only available for quadratic costs corresponding to linear price impact. In this paper, we show that the resulting linear strategies allow to achieve virtually optimal performance also for realistic nonlinear price impact, if the “effective” quadratic cost parameter is chosen appropriately. To wit, for a wide range of risk levels, this leads to performance losses below 2% compared to a numerical algorithm proposed by Kolm and Ritter, run at very high accuracy. The effective quadratic cost depends on the portfolio risk and concavity of the impact function, but can be computed without any sophisticated numerics by simply maximizing an explicit scalar function. |
| JEL: | F3 G3 |
| Date: | 2024–10–15 |
| URL: | https://d.repec.org/n?u=RePEc:ehl:lserod:125888 |