High-Frequency Trading

Informer in Algorithmic Investment Strategies on High Frequency Bitcoin Data ArXiv ID: 2503.18096 “View on arXiv” Authors: Unknown Abstract The article investigates the usage of Informer architecture for building automated trading strategies for high frequency Bitcoin data. Three strategies using Informer model with different loss functions: Root Mean Squared Error (RMSE), Generalized Mean Absolute Directional Loss (GMADL) and Quantile loss, are proposed and evaluated against the Buy and Hold benchmark and two benchmark strategies based on technical indicators. The evaluation is conducted using data of various frequencies: 5 minute, 15 minute, and 30 minute intervals, over the 6 different periods. Although the Informer-based model with Quantile loss did not outperform the benchmark, two other models achieved better results. The performance of the model using RMSE loss worsens when used with higher frequency data while the model that uses novel GMADL loss function is benefiting from higher frequency data and when trained on 5 minute interval it beat all the other strategies on most of the testing periods. The primary contribution of this study is the application and assessment of the RMSE, GMADL, and Quantile loss functions with the Informer model to forecast future returns, subsequently using these forecasts to develop automated trading strategies. The research provides evidence that employing an Informer model trained with the GMADL loss function can result in superior trading outcomes compared to the buy-and-hold approach. ...

Label Unbalance in High-frequency Trading ArXiv ID: 2503.09988 “View on arXiv” Authors: Unknown Abstract In financial trading, return prediction is one of the foundation for a successful trading system. By the fast development of the deep learning in various areas such as graphical processing, natural language, it has also demonstrate significant edge in handling with financial data. While the success of the deep learning relies on huge amount of labeled sample, labeling each time/event as profitable or unprofitable, under the transaction cost, especially in the high-frequency trading world, suffers from serious label imbalance issue.In this paper, we adopts rigurious end-to-end deep learning framework with comprehensive label imbalance adjustment methods and succeed in predicting in high-frequency return in the Chinese future market. The code for our method is publicly available at https://github.com/RS2002/Label-Unbalance-in-High-Frequency-Trading . ...

A New Traders’ Game? – Empirical Analysis of Response Functions in a Historical Perspective ArXiv ID: 2503.01629 “View on arXiv” Authors: Unknown Abstract Traders on financial markets generate non-Markovian effects in various ways, particularly through their competition with one another which can be interpreted as a game between different (types of) traders. To quantify the market mechanisms, we empirically analyze self-response functions for pairs of different stocks and the corresponding trade sign correlators. While the non-Markovian dynamics in the self-responses is liquidity-driven, it is expectation-driven in the cross-responses which is related to the emergence of correlations. We empirically study the non-stationarity of these responses over time. In our previous data analysis, we only investigated the crisis year 2008. We now considerably extend this by also analyzing the years 2007, 2014 and 2021. To improve statistics, we also work out averaged response functions for the different years. We find significant variations over time revealing changes in the traders’ game. ...

The Market Maker’s Dilemma: Navigating the Fill Probability vs. Post-Fill Returns Trade-Off ArXiv ID: 2502.18625 “View on arXiv” Authors: Unknown Abstract Using data from a live trading experiment on the Binance Bitcoin perpetual, we examine the effects of (i) basic order book mechanics and (ii) the persistence of price changes from immediate to short timescales, revealing the interplay between returns, queue sizes, and orders’ queue positions. We document a fundamental trade-off: a negative correlation between maker fill likelihood and post-fill returns. This dictates that viable maker strategies often require a contrarian approach, counter-trading the prevailing order book imbalance. These dynamics render commonly-cited strategies highly unprofitable, leading us to model `Reversals’: situations where a contrarian maker strategy at the touch proves effective. ...

The “double” square-root law: Evidence for the mechanical origin of market impact using Tokyo Stock Exchange data ArXiv ID: 2502.16246 “View on arXiv” Authors: Unknown Abstract Understanding the impact of trades on prices is a crucial question for both academic research and industry practice. It is well established that impact follows a square-root impact as a function of traded volume. However, the microscopic origin of such a law remains elusive: empirical studies are particularly challenging due to the anonymity of orders in public data. Indeed, there is ongoing debate about whether price impact has a mechanical origin or whether it is primarily driven by information, as suggested by many economic theories. In this paper, we revisit this question using a very detailed dataset provided by the Japanese stock exchange, containing the trader IDs for all orders sent to the exchange between 2012 and 2018. Our central result is that such a law has in fact microscopic roots and applies already at the level of single child orders, provided one waits long enough for the market to “digest” them. The mesoscopic impact of metaorders arises from a “double” square-root effect: square-root in volume of individual impact, followed by an inverse square-root decay as a function of time. Since market orders are anonymous, we expect and indeed find that these results apply to any market orders, and the impact of synthetic metaorders, reconstructed by scrambling the identity of the issuers, is described by the very same square-root impact law. We conclude that price impact is essentially mechanical, at odds with theories that emphasize the information content of such trades to explain the square-root impact law. ...

High-Frequency Market Manipulation Detection with a Markov-modulated Hawkes process ArXiv ID: 2502.04027 “View on arXiv” Authors: Unknown Abstract This work focuses on a self-exciting point process defined by a Hawkes-like intensity and a switching mechanism based on a hidden Markov chain. Previous works in such a setting assume constant intensities between consecutive events. We extend the model to general Hawkes excitation kernels that are piecewise constant between events. We develop an expectation-maximization algorithm for the statistical inference of the Hawkes intensities parameters as well as the state transition probabilities. The numerical convergence of the estimators is extensively tested on simulated data. Using high-frequency cryptocurrency data on a top centralized exchange, we apply the model to the detection of anomalous bursts of trades. We benchmark the goodness-of-fit of the model with the Markov-modulated Poisson process and demonstrate the relevance of the model in detecting suspicious activities. ...

High-frequency lead-lag relationships in the Chinese stock index futures market: tick-by-tick dynamics of calendar spreads ArXiv ID: 2501.03171 “View on arXiv” Authors: Unknown Abstract Lead-lag relationships, integral to market dynamics, offer valuable insights into the trading behavior of high-frequency traders (HFTs) and the flow of information at a granular level. This paper investigates the lead-lag relationships between stock index futures contracts of different maturities in the Chinese financial futures market (CFFEX). Using high-frequency (tick-by-tick) data, we analyze how price movements in near-month futures contracts influence those in longer-dated contracts, such as next-month, quarterly, and semi-annual contracts. Our findings reveal a consistent pattern of price discovery, with the near-month contract leading the others by one tick, driven primarily by liquidity. Additionally, we identify a negative feedback effect of the “lead-lag spread” on the leading asset, which can predict returns of leading asset. Backtesting results demonstrate the profitability of trading based on the lead-lag spread signal, even after accounting for transaction costs. Altogether, our analysis offers valuable insights to understand and capitalize on the evolving dynamics of futures markets. ...

Minimal Batch Adaptive Learning Policy Engine for Real-Time Mid-Price Forecasting in High-Frequency Trading ArXiv ID: 2412.19372 “View on arXiv” Authors: Unknown Abstract High-frequency trading (HFT) has transformed modern financial markets, making reliable short-term price forecasting models essential. In this study, we present a novel approach to mid-price forecasting using Level 1 limit order book (LOB) data from NASDAQ, focusing on 100 U.S. stocks from the S&P 500 index during the period from September to November 2022. Expanding on our previous work with Radial Basis Function Neural Networks (RBFNN), which leveraged automated feature importance techniques based on mean decrease impurity (MDI) and gradient descent (GD), we introduce the Adaptive Learning Policy Engine (ALPE) - a reinforcement learning (RL)-based agent designed for batch-free, immediate mid-price forecasting. ALPE incorporates adaptive epsilon decay to dynamically balance exploration and exploitation, outperforming a diverse range of highly effective machine learning (ML) and deep learning (DL) models in forecasting performance. ...

Limit Order Book Event Stream Prediction with Diffusion Model ArXiv ID: 2412.09631 “View on arXiv” Authors: Unknown Abstract Limit order book (LOB) is a dynamic, event-driven system that records real-time market demand and supply for a financial asset in a stream flow. Event stream prediction in LOB refers to forecasting both the timing and the type of events. The challenge lies in modeling the time-event distribution to capture the interdependence between time and event type, which has traditionally relied on stochastic point processes. However, modeling complex market dynamics using stochastic processes, e.g., Hawke stochastic process, can be simplistic and struggle to capture the evolution of market dynamics. In this study, we present LOBDIF (LOB event stream prediction with diffusion model), which offers a new paradigm for event stream prediction within the LOB system. LOBDIF learns the complex time-event distribution by leveraging a diffusion model, which decomposes the time-event distribution into sequential steps, with each step represented by a Gaussian distribution. Additionally, we propose a denoising network and a skip-step sampling strategy. The former facilitates effective learning of time-event interdependence, while the latter accelerates the sampling process during inference. By introducing a diffusion model, our approach breaks away from traditional modeling paradigms, offering novel insights and providing an effective and efficient solution for learning the time-event distribution in order streams within the LOB system. Extensive experiments using real-world data from the limit order books of three widely traded assets confirm that LOBDIF significantly outperforms current state-of-the-art methods. ...

Online High-Frequency Trading Stock Forecasting with Automated Feature Clustering and Radial Basis Function Neural Networks ArXiv ID: 2412.16160 “View on arXiv” Authors: Unknown Abstract This study presents an autonomous experimental machine learning protocol for high-frequency trading (HFT) stock price forecasting that involves a dual competitive feature importance mechanism and clustering via shallow neural network topology for fast training. By incorporating the k-means algorithm into the radial basis function neural network (RBFNN), the proposed method addresses the challenges of manual clustering and the reliance on potentially uninformative features. More specifically, our approach involves a dual competitive mechanism for feature importance, combining the mean-decrease impurity (MDI) method and a gradient descent (GD) based feature importance mechanism. This approach, tested on HFT Level 1 order book data for 20 S&P 500 stocks, enhances the forecasting ability of the RBFNN regressor. Our findings suggest that an autonomous approach to feature selection and clustering is crucial, as each stock requires a different input feature space. Overall, by automating the feature selection and clustering processes, we remove the need for manual topological grid search and provide a more efficient way to predict LOB’s mid-price. ...