arXiv subjects

Steve Yang

Publications and source records attributed to Steve Yang.

6 recordsLinked to original sources

arXiv2025

FlowHFT: Imitation Learning via Flow Matching Policy for Optimal High-Frequency Trading under Diverse Market Conditions

High-frequency trading (HFT) is an investing strategy that continuously monitors market states and places bid and ask orders at millisecond speeds. Traditional HFT approaches fit models with historical data and assume that future market states follow similar patterns. This limits the effectiveness of any single model to the specific conditions it was trained for. Additionally, these models achieve optimal solutions only under specific market conditions, such as assumptions about stock price's stochastic process, stable order flow, and the absence of sudden volatility. Real-world markets, however, are dynamic, diverse, and frequently volatile. To address these challenges, we propose the FlowHFT, a novel imitation learning framework based on flow matching policy. FlowHFT simultaneously learns strategies from numerous expert models, each proficient in particular market scenarios. As a result, our framework can adaptively adjust investment decisions according to the prevailing market state. Furthermore, FlowHFT incorporates a grid-search fine-tuning mechanism. This allows it to refine strategies and achieve superior performance even in complex or extreme market scenarios where expert strategies may be suboptimal. We test FlowHFT in multiple market environments. We first show that flow matching policy is applicable in stochastic market environments, thus enabling FlowHFT to learn trading strategies under different market conditions. Notably, our single framework consistently achieves performance superior to the best expert for each market condition.

q-fin.TR↗

arXiv2025

Unified GARCH-Recurrent Neural Network in Financial Volatility Forecasting

In this study, we develop a unified volatility modeling framework that embeds GARCH dynamics directly within recurrent neural networks. We propose two interpretable hybrid architectures, GARCH-GRU and GARCH-LSTM, that integrate the GARCH(1,1) volatility update into the multiplicative gating structure of GRU and LSTM cells. This unified design preserves economically meaningful GARCH parameters while enabling the networks to learn nonlinear temporal dependencies in financial time series. Comprehensive out-of-sample evaluations across major U.S. equity indices show that both models consistently outperform classical GARCH specifications, pipeline-style hybrids, and neural baselines such as the Transformer across multiple metrics (MSE, MAE, SMAPE, and out-of-sample R\textsuperscript{2}). Within this family, the GARCH-GRU achieves the strongest accuracy-efficiency tradeoff, training nearly three times faster than GARCH-LSTM while maintaining comparable or superior forecasting accuracy under normal market conditions and delivering stable and economically plausible parameter estimates. The advantages persist during extreme market turbulence. In the COVID-19 stress period, both architectures retain superior forecasting accuracy and deliver well-calibrated 99 percent Value-at-Risk forecasts, achieving lower violation ratios and competitive Pinball losses relative to all benchmarks. Overall, the findings underscore the effectiveness of embedding GARCH dynamics within recurrent neural architectures, yielding models that are accurate, efficient, interpretable, and robust for real-world risk-aware volatility forecasting.

q-fin.ST↗

arXiv2024

FinLoRA: Finetuning Quantized Financial Large Language Models Using Low-Rank Adaptation

Finetuned large language models (LLMs) have shown remarkable performance in financial tasks, such as sentiment analysis and information retrieval. Due to privacy concerns, finetuning and deploying Financial LLMs (FinLLMs) locally are crucial for institutions. However, finetuning FinLLMs poses challenges including GPU memory constraints and long input sequences. In this paper, we employ quantized low-rank adaptation (QLoRA) to finetune FinLLMs, which leverage low-rank matrix decomposition and quantization techniques to significantly reduce computational requirements while maintaining high model performance. We also employ data and pipeline parallelism to enable local finetuning using cost-effective, widely accessible GPUs. Experiments on financial datasets demonstrate that our method achieves substantial improvements in accuracy, GPU memory usage, and time efficiency, underscoring the potential of lowrank methods for scalable and resource-efficient LLM finetuning.

cs.LG↗

arXiv2024

A Report on Financial Regulations Challenge at COLING 2025

Financial large language models (FinLLMs) have been applied to various tasks in business, finance, accounting, and auditing. Complex financial regulations and standards are critical to financial services, which LLMs must comply with. However, FinLLMs' performance in understanding and interpreting financial regulations has rarely been studied. Therefore, we organize the Regulations Challenge, a shared task at COLING 2025. It encourages the academic community to explore the strengths and limitations of popular LLMs. We create 9 novel tasks and corresponding question sets. In this paper, we provide an overview of these tasks and summarize participants' approaches and results. We aim to raise awareness of FinLLMs' professional capability in financial regulations.

cs.CE↗

arXiv2020

Orbit: Probabilistic Forecast with Exponential Smoothing

Time series forecasting is an active research topic in academia as well as industry. Although we see an increasing amount of adoptions of machine learning methods in solving some of those forecasting challenges, statistical methods remain powerful while dealing with low granularity data. This paper introduces a refined Bayesian exponential smoothing model with the help of probabilistic programming languages including Stan. Our model refinements include additional global trend, transformation for multiplicative form, noise distribution and choice of priors. A benchmark study is conducted on a rich set of time-series data sets for our models along with other well-known time series models.

stat.CO↗

arXiv2018

Financial Aspect-Based Sentiment Analysis using Deep Representations

The topic of aspect-based sentiment analysis (ABSA) has been explored for a variety of industries, but it still remains much unexplored in finance. The recent release of data for an open challenge (FiQA) from the companion proceedings of WWW '18 has provided valuable finance-specific annotations. FiQA contains high quality labels, but it still lacks data quantity to apply traditional ABSA deep learning architecture. In this paper, we employ high-level semantic representations and methods of inductive transfer learning for NLP. We experiment with extensions of recently developed domain adaptation methods and target task fine-tuning that significantly improve performance on a small dataset. Our results show an 8.7% improvement in the F1 score for classification and an 11% improvement over the MSE for regression on current state-of-the-art results.

cs.CL↗