arXiv subjects

Stefan Zohren

Publications and source records attributed to Stefan Zohren.

At least 37 records · Page 2Linked to original sources

arXiv2025

Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement

Time series data are foundational in finance, healthcare, and energy domains. However, most existing methods and datasets remain focused on a narrow spectrum of tasks, such as forecasting or anomaly detection. To bridge this gap, we introduce Time Series Multi-Task Question Answering (Time-MQA), a unified framework that enables natural language queries across multiple time series tasks - numerical analytical tasks and open-ended question answering with reasoning. Central to Time-MQA is the TSQA dataset, a large-scale dataset containing $\sim$200k question-answer pairs derived from diverse time series spanning environment, traffic, etc. This comprehensive resource covers various time series lengths and promotes robust model development. We further demonstrate how continually pre-training large language models (Mistral 7B, Llama-3 8B, and Qwen-2.5 7B) on the TSQA dataset enhanced time series reasoning capabilities, moving beyond mere numeric tasks and enabling more advanced and intuitive interactions with temporal data. The complete TSQA dataset, models, user study questionnaires for evaluation, and other related materials have been open-sourced.

cs.CL↗

arXiv2025

Trainability of Parametrised Linear Combinations of Unitaries

A principal concern in the optimisation of parametrised quantum circuits is the presence of barren plateaus, which present fundamental challenges to the scalability of applications, such as variational algorithms and quantum machine learning models. Recent proposals for these methods have increasingly used the linear combination of unitaries (LCU) procedure as a core component. In this work, we prove that an LCU of trainable parametrised circuits is still trainable. We do so by analytically deriving the expression for the variance of the expectation when applying the LCU to a set of parametrised circuits, taking into account the postselection probability. These results extend to incoherent superpositions. We support our conclusions with numerical results on linear combinations of fermionic Gaussian unitaries (matchgate circuits). Our work shows that sums of trainable parametrised circuits are still trainable, and thus provides a method to construct new families of more expressive trainable circuits. We argue that there is a scope for a quantum speed-up when evaluating these trainable circuits on a quantum device.

quant-ph↗

arXiv2025

LOB-Bench: Benchmarking Generative AI for Finance -- an Application to Limit Order Book Data

While financial data presents one of the most challenging and interesting sequence modelling tasks due to high noise, heavy tails, and strategic interactions, progress in this area has been hindered by the lack of consensus on quantitative evaluation paradigms. To address this, we present LOB-Bench, a benchmark, implemented in python, designed to evaluate the quality and realism of generative message-by-order data for limit order books (LOB) in the LOBSTER format. Our framework measures distributional differences in conditional and unconditional statistics between generated and real LOB data, supporting flexible multivariate statistical evaluation. The benchmark also includes features commonly used LOB statistics such as spread, order book volumes, order imbalance, and message inter-arrival times, along with scores from a trained discriminator network. Lastly, LOB-Bench contains "market impact metrics", i.e. the cross-correlations and price response functions for specific events in the data. We benchmark generative autoregressive state-space models, a (C)GAN, as well as a parametric LOB model and find that the autoregressive GenAI approach beats traditional model classes.

cs.LG↗

arXiv2025

ClusterLOB: Enhancing Trading Strategies by Clustering Orders in Limit Order Books

In the rapidly evolving world of financial markets, understanding the dynamics of limit order book (LOB) is crucial for unraveling market microstructure and participant behavior. We introduce ClusterLOB as a method to cluster individual market events in a stream of market-by-order (MBO) data into different groups. To do so, each market event is augmented with six time-dependent features. By applying the K-means++ clustering algorithm to the resulting order features, we are then able to assign each new order to one of three distinct clusters, which we identify as directional, opportunistic, and market-making participants, each capturing unique trading behaviors. Our experimental results are performed on one year of MBO data containing small-tick, medium-tick, and large-tick stocks from NASDAQ. To validate the usefulness of our clustering, we compute order flow imbalances across each cluster within 30-minute buckets during the trading day. We treat each cluster's imbalance as a signal that provides insights into trading strategies and participants' responses to varying market conditions. To assess the effectiveness of these signals, we identify the trading strategy with the highest Sharpe ratio in the training dataset, and demonstrate that its performance in the test dataset is superior to benchmark trading strategies that do not incorporate clustering. We also evaluate trading strategies based on order flow imbalance decompositions across different market event types, including add, cancel, and trade events, to assess their robustness in various market conditions. This work establishes a robust framework for clustering market participant behavior, which helps us to better understand market microstructure, and inform the development of more effective predictive trading signals with practical applications in algorithmic trading and quantitative finance.

q-fin.TR↗

arXiv2025

Unlocking the Power of LSTM for Long Term Time Series Forecasting

Traditional recurrent neural network architectures, such as long short-term memory neural networks (LSTM), have historically held a prominent role in time series forecasting (TSF) tasks. While the recently introduced sLSTM for Natural Language Processing (NLP) introduces exponential gating and memory mixing that are beneficial for long term sequential learning, its potential short memory issue is a barrier to applying sLSTM directly in TSF. To address this, we propose a simple yet efficient algorithm named P-sLSTM, which is built upon sLSTM by incorporating patching and channel independence. These modifications substantially enhance sLSTM's performance in TSF, achieving state-of-the-art results. Furthermore, we provide theoretical justifications for our design, and conduct extensive comparative and analytical experiments to fully validate the efficiency and superior performance of our model.

cs.LG↗

arXiv2025

Stories that (are) Move(d by) Markets: A Causal Exploration of Market Shocks and Semantic Shifts across Different Partisan Groups

Macroeconomic fluctuations and the narratives that shape them form a mutually reinforcing cycle: public discourse can spur behavioural changes leading to economic shifts, which then result in changes in the stories that propagate. We show that shifts in semantic embedding space can be causally linked to financial market shocks -- deviations from the expected market behaviour. Furthermore, we show how partisanship can influence the predictive power of text for market fluctuations and shape reactions to those same shocks. We also provide some evidence that text-based signals are particularly salient during unexpected events such as COVID-19, highlighting the value of language data as an exogenous variable in economic forecasting. Our findings underscore the bidirectional relationship between news outlets and market shocks, offering a novel empirical approach to studying their effect on each other.

cs.CL↗

arXiv2025

When Dimensionality Hurts: The Role of LLM Embedding Compression for Noisy Regression Tasks

Large language models (LLMs) have shown remarkable success in language modelling due to scaling laws found in model size and the hidden dimension of the model's text representation. Yet, we demonstrate that compressed representations of text can yield better performance in LLM-based regression tasks. In this paper, we compare the relative performance of embedding compression in three different signal-to-noise contexts: financial return prediction, writing quality assessment and review scoring. Our results show that compressing embeddings, in a minimally supervised manner using an autoencoder's hidden representation, can mitigate overfitting and improve performance on noisy tasks, such as financial return prediction; but that compression reduces performance on tasks that have high causal dependencies between the input and target data. Our results suggest that the success of interpretable compressed representations such as sentiment may be due to a regularising effect.

cs.CL↗

arXiv2025

Decision-informed Neural Networks with Large Language Model Integration for Portfolio Optimization

This paper addresses the critical disconnect between prediction and decision quality in portfolio optimization by integrating Large Language Models (LLMs) with decision-focused learning. We demonstrate both theoretically and empirically that minimizing the prediction error alone leads to suboptimal portfolio decisions. We aim to exploit the representational power of LLMs for investment decisions. An attention mechanism processes asset relationships, temporal dependencies, and macro variables, which are then directly integrated into a portfolio optimization layer. This enables the model to capture complex market dynamics and align predictions with the decision objectives. Extensive experiments on S\&P100 and DOW30 datasets show that our model consistently outperforms state-of-the-art deep learning models. In addition, gradient-based analyses show that our model prioritizes the assets most crucial to decision making, thus mitigating the effects of prediction errors on portfolio performance. These findings underscore the value of integrating decision objectives into predictions for more robust and context-aware portfolio management.

q-fin.PM↗

arXiv2025

Forecasting Credit Ratings: A Case Study where Traditional Methods Outperform Generative LLMs

Large Language Models (LLMs) have been shown to perform well for many downstream tasks. Transfer learning can enable LLMs to acquire skills that were not targeted during pre-training. In financial contexts, LLMs can sometimes beat well-established benchmarks. This paper investigates how well LLMs perform in the task of forecasting corporate credit ratings. We show that while LLMs are very good at encoding textual information, traditional methods are still very competitive when it comes to encoding numeric and multimodal data. For our task, current LLMs perform worse than a more traditional XGBoost architecture that combines fundamental and macroeconomic data with high-density text-based embedding features.

q-fin.RM↗

arXiv2025

On Sequential Bayesian Inference for Continual Learning

Sequential Bayesian inference can be used for continual learning to prevent catastrophic forgetting of past tasks and provide an informative prior when learning new tasks. We revisit sequential Bayesian inference and test whether having access to the true posterior is guaranteed to prevent catastrophic forgetting in Bayesian neural networks. To do this we perform sequential Bayesian inference using Hamiltonian Monte Carlo. We propagate the posterior as a prior for new tasks by fitting a density estimator on Hamiltonian Monte Carlo samples. We find that this approach fails to prevent catastrophic forgetting demonstrating the difficulty in performing sequential Bayesian inference in neural networks. From there we study simple analytical examples of sequential Bayesian inference and CL and highlight the issue of model misspecification which can lead to sub-optimal continual learning performance despite exact inference. Furthermore, we discuss how task data imbalances can cause forgetting. From these limitations, we argue that we need probabilistic models of the continual learning generative process rather than relying on sequential Bayesian inference over Bayesian neural network weights. In this vein, we also propose a simple baseline called Prototypical Bayesian Continual Learning, which is competitive with state-of-the-art Bayesian continual learning methods on class incremental continual learning vision benchmarks.

cs.LG↗

arXiv2024

Extracting Alpha from Financial Analyst Networks

We investigate the effectiveness of a momentum trading signal based on the coverage network of financial analysts. This signal builds on the key information-brokerage role financial sell-side analysts play in modern stock markets. The baskets of stocks covered by each analyst can be used to construct a network between firms whose edge weights represent the number of analysts jointly covering both firms. Although the link between financial analysts coverage and co-movement of firms' stock prices has been investigated in the literature, little effort has been made to systematically learn the most effective combination of signals from firms covered jointly by analysts in order to benefit from any spillover effect. To fill this gap, we build a trading strategy which leverages the analyst coverage network using a graph attention network. More specifically, our model learns to aggregate information from individual firm features and signals from neighbouring firms in a node-level forecasting task. We develop a portfolio based on those predictions which we demonstrate to exhibit an annualized returns of 29.44% and a Sharpe ratio of 4.06 substantially outperforming market baselines and existing graph machine learning based frameworks. We further investigate the performance and robustness of this strategy through extensive empirical analysis. Our paper represents one of the first attempts in using graph machine learning to extract actionable knowledge from the analyst coverage network for practical financial applications.

q-fin.CP↗

arXiv2024

DeepVol: Volatility Forecasting from High-Frequency Data with Dilated Causal Convolutions

Volatility forecasts play a central role among equity risk measures. Besides traditional statistical models, modern forecasting techniques based on machine learning can be employed when treating volatility as a univariate, daily time-series. Moreover, econometric studies have shown that increasing the number of daily observations with high-frequency intraday data helps to improve volatility predictions. In this work, we propose DeepVol, a model based on Dilated Causal Convolutions that uses high-frequency data to forecast day-ahead volatility. Our empirical findings demonstrate that dilated convolutional filters are highly effective at extracting relevant information from intraday financial time-series, proving that this architecture can effectively leverage predictive information present in high-frequency data that would otherwise be lost if realised measures were precomputed. Simultaneously, dilated convolutional filters trained with intraday high-frequency data help us avoid the limitations of models that use daily data, such as model misspecification or manually designed handcrafted features, whose devise involves optimising the trade-off between accuracy and computational efficiency and makes models prone to lack of adaptation into changing circumstances. In our analysis, we use two years of intraday data from NASDAQ-100 to evaluate the performance of DeepVol. Our empirical results suggest that the proposed deep learning-based approach effectively learns global features from high-frequency data, resulting in more accurate predictions compared to traditional methodologies and producing more accurate risk measures.

q-fin.RM↗

arXiv2024

Deep Learning for Options Trading: An End-To-End Approach

We introduce a novel approach to options trading strategies using a highly scalable and data-driven machine learning algorithm. In contrast to traditional approaches that often require specifications of underlying market dynamics or assumptions on an option pricing model, our models depart fundamentally from the need for these prerequisites, directly learning non-trivial mappings from market data to optimal trading signals. Backtesting on more than a decade of option contracts for equities listed on the S&P 100, we demonstrate that deep learning models trained according to our end-to-end approach exhibit significant improvements in risk-adjusted performance over existing rules-based trading strategies. We find that incorporating turnover regularization into the models leads to further performance enhancements at prohibitively high levels of transaction costs.

q-fin.PM↗

arXiv2024

Temporal Representation Learning for Stock Similarities and Its Applications in Investment Management

In the era of rapid globalization and digitalization, accurate identification of similar stocks has become increasingly challenging due to the non-stationary nature of financial markets and the ambiguity in conventional regional and sector classifications. To address these challenges, we examine SimStock, a novel temporal self-supervised learning framework that combines techniques from self-supervised learning (SSL) and temporal domain generalization to learn robust and informative representations of financial time series data. The primary focus of our study is to understand the similarities between stocks from a broader perspective, considering the complex dynamics of the global financial landscape. We conduct extensive experiments on four real-world datasets with thousands of stocks and demonstrate the effectiveness of SimStock in finding similar stocks, outperforming existing methods. The practical utility of SimStock is showcased through its application to various investment strategies, such as pairs trading, index tracking, and portfolio optimization, where it leads to superior performance compared to conventional methods. Our findings empirically examine the potential of data-driven approach to enhance investment decision-making and risk management practices by leveraging the power of temporal self-supervised learning in the face of the ever-changing global financial landscape.

q-fin.CP↗

arXiv2024

A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges

Recent advances in large language models (LLMs) have unlocked novel opportunities for machine learning applications in the financial domain. These models have demonstrated remarkable capabilities in understanding context, processing vast amounts of data, and generating human-preferred contents. In this survey, we explore the application of LLMs on various financial tasks, focusing on their potential to transform traditional practices and drive innovation. We provide a discussion of the progress and advantages of LLMs in financial contexts, analyzing their advanced technologies as well as prospective capabilities in contextual understanding, transfer learning flexibility, complex emotion detection, etc. We then highlight this survey for categorizing the existing literature into key application areas, including linguistic tasks, sentiment analysis, financial time series, financial reasoning, agent-based modeling, and other applications. For each application area, we delve into specific methodologies, such as textual analysis, knowledge-based analysis, forecasting, data augmentation, planning, decision support, and simulations. Furthermore, a comprehensive collection of datasets, model assets, and useful codes associated with mainstream applications are presented as resources for the researchers and practitioners. Finally, we outline the challenges and opportunities for future research, particularly emphasizing a number of distinctive aspects in this field. We hope our work can help facilitate the adoption and further development of LLMs in the financial sector.

q-fin.GN↗

arXiv2024

Time Machine GPT

Large language models (LLMs) are often trained on extensive, temporally indiscriminate text corpora, reflecting the lack of datasets with temporal metadata. This approach is not aligned with the evolving nature of language. Conventional methods for creating temporally adapted language models often depend on further pre-training static models on time-specific data. This paper presents a new approach: a series of point-in-time LLMs called Time Machine GPT (TiMaGPT), specifically designed to be nonprognosticative. This ensures they remain uninformed about future factual information and linguistic changes. This strategy is beneficial for understanding language evolution and is of critical importance when applying models in dynamic contexts, such as time-series forecasting, where foresight of future information can prove problematic. We provide access to both the models and training datasets.

cs.CL↗

arXiv2024

Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies

Forecasting models for systematic trading strategies do not adapt quickly when financial market conditions rapidly change, as was seen in the advent of the COVID-19 pandemic in 2020, causing many forecasting models to take loss-making positions. To deal with such situations, we propose a novel time-series trend-following forecaster that can quickly adapt to new market conditions, referred to as regimes. We leverage recent developments from the deep learning community and use few-shot learning. We propose the Cross Attentive Time-Series Trend Network -- X-Trend -- which takes positions attending over a context set of financial time-series regimes. X-Trend transfers trends from similar patterns in the context set to make forecasts, then subsequently takes positions for a new distinct target regime. By quickly adapting to new financial regimes, X-Trend increases Sharpe ratio by 18.9% over a neural forecaster and 10-fold over a conventional Time-series Momentum strategy during the turbulent market period from 2018 to 2023. Our strategy recovers twice as quickly from the COVID-19 drawdown compared to the neural-forecaster. X-Trend can also take zero-shot positions on novel unseen financial assets obtaining a 5-fold Sharpe ratio increase versus a neural time-series trend forecaster over the same period. Furthermore, the cross-attention mechanism allows us to interpret the relationship between forecasts and patterns in the context set.

q-fin.TR↗

arXiv2023

Asynchronous Deep Double Duelling Q-Learning for Trading-Signal Execution in Limit Order Book Markets

We employ deep reinforcement learning (RL) to train an agent to successfully translate a high-frequency trading signal into a trading strategy that places individual limit orders. Based on the ABIDES limit order book simulator, we build a reinforcement learning OpenAI gym environment and utilise it to simulate a realistic trading environment for NASDAQ equities based on historic order book messages. To train a trading agent that learns to maximise its trading return in this environment, we use Deep Duelling Double Q-learning with the APEX (asynchronous prioritised experience replay) architecture. The agent observes the current limit order book state, its recent history, and a short-term directional forecast. To investigate the performance of RL for adaptive trading independently from a concrete forecasting algorithm, we study the performance of our approach utilising synthetic alpha signals obtained by perturbing forward-looking returns with varying levels of noise. Here, we find that the RL agent learns an effective trading strategy for inventory management and order placing that outperforms a heuristic benchmark trading strategy having access to the same signal.

q-fin.TR↗