Low-frequency Traders Research Articles

Research on high-frequency trading strategies optimization based on deep learning

High-frequency trading is derived from programmatic trading and market maker mechanisms, and unlike low-frequency trading, it uses ultra-high-speed computers to acquire and analyze high-frequency trading data in the market, so as to identify price change patterns and quickly execute trades to complete the change of hands. In this work, we focused on optimizing high-frequency trading strategies using deep reinforcement learning. Specifically, we employ a dual deep Q network model, which consists of two deep neural networks that are used to generate action value estimates and provide target action values, respectively. The advantage of this structure is that it reduces bias in the estimation process, thereby improving the stability and efficiency of learning. The input layer of the model receives multi-dimensional features of market data, such as price, volume, order depth, etc., which are normalized and then fed into the network. The hidden layer includes multiple layers of fully connected layers to enhance the nonlinear representation of the model and the ability to handle complex market dynamics. We have also introduced batch normalization and dropout layers in the network to prevent overfitting merges and improve the generalization ability of the model. Eventually, the output layer generates action values corresponding to each possible trading action, deciding to buy, sell, or hold a position. In the experimental analysis, this study verifies the superiority of the proposed model in processing high-frequency trading data and executing trading decisions by comparing it with traditional trading strategies and other machine learning methods.

EarnHFT: Efficient Hierarchical Reinforcement Learning for High Frequency Trading

High-frequency trading (HFT) is using computer algorithms to make trading decisions in short time scales (e.g., second-level), which is widely used in the Cryptocurrency (Crypto) market, (e.g., Bitcoin). Reinforcement learning (RL) in financial research has shown stellar performance on many quantitative trading tasks. However, most methods focus on low-frequency trading, e.g., day-level, which cannot be directly applied to HFT because of two challenges. First, RL for HFT involves dealing with extremely long trajectories (e.g., 2.4 million steps per month), which is hard to optimize and evaluate. Second, the dramatic price fluctuations and market trend changes of Crypto make existing algorithms fail to maintain satisfactory performances. To tackle these challenges, we propose an Efficient hieArchical Reinforcement learNing method for High Frequency Trading (EarnHFT), a novel three-stage hierarchical RL framework for HFT. In stage I, we compute a Q-teacher, i.e., the optimal action value based on dynamic programming, for enhancing the performance and training efficiency of second level RL agents. In stage II, we construct a pool of diverse RL agents for different market trends, distinguished by return rates, where hundreds of RL agents are trained with different preferences of return rates and only a tiny fraction of them will be selected into the pool based on their profitability. In stage III, we train a minute-level router which dynamically picks a second-level agent from the pool to achieve stable performance across different markets. Through extensive experiments in various market trends on Crypto markets in a high-fidelity simulation trading environment, we demonstrate that EarnHFT significantly outperforms 6 state-of-art baselines in 6 popular financial criteria, exceeding the runner-up by 30% in profitability.

Algorithm-Based Low-Frequency Trading Using a Stochastic Oscillator and William%R: A Case Study on the U.S. and Korean Indices

Using stochastics in stock market analysis is widely accepted for index estimation and ultra-high-frequency trading. However, previous studies linking index estimation to actual trading without applying low-frequency trading are limited. This study applied William%R to the existing research and used fixed parameters to remove noise from stochastics. We propose contributing to stock market stakeholders by finding an easy-to-apply algorithmic trading methodology for individual and pension fund investors. The algorithm constructed two oscillators with fixed parameters to identify when to enter and exit the index and achieved good results against the benchmark. We tested two ETFs, SPY (S&P 500) and EWY (MSCI Korea), from 2010 to 2022. Over the 12-year study period, our model showed it can outperform the benchmark index, having a high hit ratio of over 80%, a maximum drawdown in the low single digits, and a trading frequency of 1.5 trades per year. The results of our empirical research show that this methodology simplifies the process for investors to effectively implement market timing strategies in their investment decisions.

High frequency market making: The role of speed

We propose a model where a strategic high frequency market maker exploits his speed and informational advantages to place quotes that interact with the market orders of low frequency traders. We characterize the optimal market making policy and the equilibrium that results. The model has testable implications regarding the impact of speed on the provision of liquidity. We test these implications by taking advantage of a natural experiment on the NYSE American stock exchange, which implemented an intentional delay in 2017 then removed it in 2019. We find broad agreement between the empirical evidence and the implications of the model.

Utilization of Weekly Options for the Improvement of the Volatility Index

As the liquidity of KOSPI 200 index options is concentrated on the nearest expiration contract, the V-KOSPI 200 index, which is based on near- and next-term months options, fluctuates abnormally, and the designated market makers of V-KOSPI 200 futures suffer from hedging their inventory positions. This study suggests the volatility index, which includes KOSPI 200 weekly options instead of next-term monthly options. The index can mitigate rare spikes and the low volatility of the V-KOSPI 200 index, which mainly arise from stale market prices and low-frequency trading in the second and third contract months. The empirical results show that the monthly trading volume of weekly options more than triples compared to second- and third-contract month options, and the microstructure of both markets is roughly similar. The trading frequency of weekly options is six times higher than that of next-term monthly options. Therefore, V-KOSPI 200 futures market makers can use weekly options traded more actively instead of second-month options as components of hedging portfolios, while helping the new volatility index mitigate the abnormal fluctuation of the V-KOSPI 200 index.

Profit from Volatility Based on Investment Strategy Model

The investment market is rapidly changing and asset prices may vary greatly in a relatively short period of time due to their instability. We analyze the variation characteristics of gold and bitcoin prices. Obviously, the gold price movements are significantly more stable than bitcoin, so we consider using a long- term low-frequency trading strategy with wavelet transform for gold and a short-term high- frequency trading strategy for bitcoin. Based on these indicators, a multilayer perceptual (MLP) neural network was used to develop price prediction models for each of the two assets. These models achieve accurate forecasting of future prices based on historical data, and the models’ test error levels are both about 2%.

Liquidity of China’s agricultural futures market: measurement and cross-market dependence

PurposeThis paper aims to present the first empirical liquidity measurement of China’s agricultural futures markets and study time-varying liquidity dependence across markets.Design/methodology/approachBased on both high- and low-frequency trading data of soybean and corn, this paper evaluates short-term liquidity adjustment in Chinese agricultural futures market measured by liquidity benchmark and long-term liquidity development measured by liquidity proxies.FindingsBy constructing comparisons, the authors identify the seminal paper of Fong, Holden and Trzcinka (2017) as the best low-frequency liquidity proxy in China’s agricultural futures market and capture similar historical patterns of the liquidity in soybean and corn markets. The authors further employ Copula-generalized autoregressive conditional heteroskedasticity models to investigate liquidity dependence between soybean and corn futures markets. Results show that cross-market liquidity dependence tends to be dynamic and asymmetric (in upper versus lower tails). The liquidity dependence becomes stronger when these markets experience negative shocks than positive shocks, indicating a concern on the contagion effect of liquidity risk under negative financial situations.Originality/valueThe findings of this study provide useful information on the dynamic evolution of liquidity pattern and cross-market dependence of fastest-growing agricultural futures in the largest emerging economy.

Are high frequency traders responsible for extreme price movements?

This is the first paper to investigate the association between losses to liquidity providers and price jumps, separately for high frequency traders [HFT] and low frequency traders. Highly reliable data from Nasdaq identifies the trade direction of each trade and the trades that have HFT participation. To determine if trades executed by high or low frequency traders are more frequently associated with a price jump, we use the volume-synchronised probability of informed trading [VPIN] metric. We find that VPIN rapidly increases prior to a price jump but does not peak until after a price jump. HFT liquidity demand and supply prior to a price jump shows that HFT reduce their trading prior to price jumps. Low frequency traders hence remain as the main market participants during price jumps and are the information channel that leads to price jumps. Regulators and broker–dealers can implement strategies to protect investors against price jumps when VPIN rapidly increases and the proportion of HFT to other traders falls.

Drivers of Stock Prices in Ghana: An Empirical Mode Decomposition Approach

This study utilized the empirical mode decomposition (EMD) technique and examined which group of investors based on their trading frequencies influence stock prices in Ghana. We applied this technique to a dataset of daily closing prices of GSE Financial Stock Index for the period 04/01/2011 to 28/08/2015. The daily closing prices were decomposed into six intrinsic mode functions (IMFs) and a residue. We used the hierarchical clustering method to reconstruct the IMFs into high frequency, low frequency, and trend components. Using statistical measures such as Pearson product moment correlation coefficient and the Kendall rank correlation, we found that the low frequency and trend components of stock prices are the main drivers of the GSE stock index. These low-frequency traders are the institutional investors. Therefore, stock prices on the GSE are affected by real economic growth but not short-lived market fluctuations.

Does High-Frequency Trading Impede Order Execution in the Stock Market?

The controversy about the high-frequency trading (HFT) behavior and its impact on the other trader parties has been a long-term question. This study examines how the HFT behavior affects the execution of orders traded by non-HFT traders. Using a NASDAQ order book data, we categorize orders as either high or low-frequency trading (LFT), and examine several measures. We find evidence that more HFT behavior will increase the number of executed LFT orders, as well as volumes and attained revenue for each LFT orders, and reduce the waiting time for execution. Our results apply to both LFT limit orders and market orders.

Does the investment horizon of institutional investors matter for stock liquidity?

This paper examines the role of the investment horizon of institutional investors on stock liquidity of firms. We show that an increase in long-term institutional ownership is negatively associated with firm liquidity, while an increase in short-term ownership is positively related to a firm's stock liquidity. We identify the ownership-liquidity relationship by examining two major channels: the trading activity channel and the informational friction channel. Long-term investors reduce stock liquidity through low frequency trading and access to value-enhancing and private information, which induces adverse selection bias. In contrast, short-term investors improve liquidity through trading activity and competition with other investors, which lowers transaction costs. Our findings further suggest that the effects of an increase in long-term (short-term) institutional investors on liquidity weaken (strengthen) when a firm has more publicly available information. Finally, we show that the positive impact of an increase in long-term ownership on valuation is more pronounced for firms with higher liquidity and the valuation effect is persistent.

Offline Algorithms in Low-Frequency Trading

Expectations run high for software that makes real-world decisions, particularly when money hangs in the balance. This third episode of the Drill Bits column shows how well-designed software can effectively create wealth by optimizing gains from trade in combinatorial auctions. We'll unveil a deep connection between auctions and a classic textbook problem, we'll see that clearing an auction resembles a high-stakes mutant Tetris, we'll learn to stop worrying and love an NP-hard problem that's far from intractable in practice, and we'll contrast the deliberative business of combinatorial auctions with the near-real-time hustle of high-frequency trading. The example software that accompanies this installment of Drill Bits implements two algorithms that clear combinatorial auctions.

The optimal bid-ask price strategies of high-frequency trading and the effect on market liquidity

We propose a model for determining the optimal bid-ask spread strategy by a high-frequency trader (HFT) who has an informational advantage and receives information about the true value of a security. We employ an information cost function that includes volatility and the volume of the asset. Subsequently, we characterize the optimal bid-ask price strategies and obtain a stable bid-ask spread. We assume that orders submitted by low-frequency traders (LFTs) and news events arrive at the market with Poisson processes. Additionally, our model supports the trading of the two-sided quote in one period. We find that more LFTs and a higher exchange latency both hurt market liquidity. The HFT prefers to choose a two-sided quote to gain more profits while cautiously chooses a one-sided quote during times of high volatility. The model generates some testable implications with supporting empirical evidence from the NASDAQ-OMX Nordic Market.

Assessment of Asymmetric Information Cost in Indian Stock Market: A Sectoral Approach

Bid-ask spread, along with profit, also encompass the impact of asymmetric information cost and order processing cost. Asymmetric information influences stock prices with varying degree of investors’ perception. Estimation of asymmetric information cost and its determinants have been explored significantly under low-frequency trading. The literature hardly attempts to study asymmetric information cost under high-frequency trading (HFT). Asymmetric information cost significantly influences bid-ask spread, and hence the nature of its impact under different market conditions needs to be analyzed under HFT. The study attempts to estimate asymmetric information cost in HFT and analyze its determinants under different industry sectors and market conditions. The study followed Affleck-Graves et al. (1994 , The Journal of Finance, 49(4), 1471–1488) model to estimate the asymmetric information cost using 5 minutes interval data for a period of 82 trading days. Information gets reflected in equity through the movement in price, variation in trading volume, and return volatility. The study has found share price, traded volume, return volatility and trading frequency as the major determinants of asymmetric information cost in different market conditions. The findings of the study have significant implications for market microstructure for trading, lowering information asymmetry in market and enhancing market quality.

High frequency traders and the price process

Using a dataset that uniquely identifies counterparties to each S&P500 eMini transaction, we classify each market participant as high or low frequency, and each transaction, by the speed of the traders involved. We investigate empirically the comparative influence of high and low frequency traders on the price process, and conversely the influence of the price process on the trading of high and low frequency traders. We find that high frequency traders have a particularly high success rate on each transaction, measured by the likelihood that the following price change will go in their direction as well as by the amount of time they have to wait to realize their gain, when trading against low frequency traders. Contrary to common wisdom, we find that high frequency traders’ activity does not induce volatility or jumps. In fact, it is their absence that is problematic: volatility and jumps are more prevalent in periods when they trade less intensely. Conversely, we find that spikes in volatility and jumps cause high frequency traders to trade less intensely, decreasing their provision of liquidity. Finally, looking at the market microstructure noise component to the price model, we find that higher level of noise generates trading opportunities for high frequency traders and lead them to increase their trading activity.

The self-financing equation in limit order book markets

The goal of this paper is to present a mathematical framework for trading on a limit order book, including its associated transaction costs, and to propose continuous-time equations which generalise the self-financing relationships of frictionless markets. These equations naturally differentiate between trading via limit and via market orders, as they include a price impact or adverse selection constraint. We briefly mention several possible applications, including hedging European options with limit orders, to illustrate their impact and how they can be used to the benefit of low-frequency traders. Two appendices include empirical evidence for facts which are not universally recognised in the current literature on the subject.

Ecology of trading strategies in a forex market for limit and market orders.

There is a growing interest to understand financial markets as ecological systems, where the variety of trading strategies correspond to that of biological species. For this purpose, transaction data for individual traders are studied recently as empirical analyses. However, there are few empirical studies addressing how traders submit limit and market order at the level of individual traders. Since limit and market orders are key ingredients finally leading to transactions, it would be necessary to understand what kind of strategies are actually employed among traders before making transactions. Here we demonstrate the variety of limit-order and market-order strategies and show their roles in the financial markets from an ecological perspective. We find these trading strategies can be well-characterized by their response pattern to historical price changes. By applying a clustering analysis, we provide an overall picture of trading strategies as an ecological matrix, illustrating that liquidity consumers are likely to exhibit high trading performances compared with liquidity providers. Furthermore, we reveal both high-frequency traders (HFTs) and low-frequency traders (LFTs) exhibit high trading performance, despite the difference in their trading styles; HFTs attempt to maximize their trading efficiency by reducing risk, whereas LFTs make their profit by taking risk.

Phantom Liquidity and High-Frequency Quoting

This article examines every NASDAQ ITCH feed message for S&P 500 Index stocks for 2012 and identifies clusters of extremely high and extremely low limit-order cancellation activity. The authors find results consistent with the idea that cancel clusters are the result of high-frequency traders jockeying for queue position and reacting to information to establish a new price level. Furthermore, few trades seem to be executed during cancel clusters or even immediately after them. Low cancellation activity seems to be markedly different, with many level changes all caused by executions. The results are consistent with high-frequency trading firms behaving as agents who bring efficiency to the market without the need to have executions at intermediate prices. The authors also discuss the misconception that investors and low-frequency traders are synonymous and its implications for policy given these results.

How Does High-Frequency Trading Affect Low-Frequency Trading?

ABSTRACTHigh-frequency trading dominates trading in financial markets. How it affects the low-frequency trading, however, is still unclear. Using NASDAQ order book data, the authors investigate this question by categorizing orders as either high or low frequency, and examining several measures. They find that high-frequency trading enhances liquidity by increasing the trade frequency and quantity of low-frequency orders. High-frequency trading also reduces the waiting time of low-frequency limit orders and improves their likelihood of execution. The results indicate that high-frequency trading has a liquidity provision effect and improves the execution quality of low-frequency orders.

Front-Running and Market Quality: An Evolutionary Perspective on High Frequency Trading

We study front-running by high frequency traders (HFTs) in a limit order model with continuous trading. The model describes an evolutionary equilibrium of low frequency traders (LFTs) who compete in portfolio management services by offering investment styles. The introduction of front-runners inflicts heavy losses on speculators, while leaving passive investors relatively unscathed. This encourages investment in the market portfolio and markedly reduces overall turnover. Speculative trading persists despite its lower profitability. By most measures, market quality is not affected to any significant extent by front-running HFTs.