Searcharxiv⌕ Search

arXiv subjects

Stefan Zohren

Publications and source records attributed to Stefan Zohren.

At least 55 records · Page 3Linked to original sources
arXiv2023

Robust Detection of Lead-Lag Relationships in Lagged Multi-Factor Models

In multivariate time series systems, key insights can be obtained by discovering lead-lag relationships inherent in the data, which refer to the dependence between two time series shifted in time relative to one another, and which can be leveraged for the purposes of control, forecasting or clustering. We develop a clustering-driven methodology for robust detection of lead-lag relationships in lagged multi-factor models. Within our framework, the envisioned pipeline takes as input a set of time series, and creates an enlarged universe of extracted subsequence time series from each input time series, via a sliding window approach. This is then followed by an application of various clustering techniques, (such as k-means++ and spectral clustering), employing a variety of pairwise similarity measures, including nonlinear ones. Once the clusters have been extracted, lead-lag estimates across clusters are robustly aggregated to enhance the identification of the consistent relationships in the original universe. We establish connections to the multireference alignment problem for both the homogeneous and heterogeneous settings. Since multivariate time series are ubiquitous in a wide range of domains, we demonstrate that our method is not only able to robustly detect lead-lag relationships in financial markets, but can also yield insightful results when applied to an environmental data set.

stat.ML↗
arXiv2023

Dynamic Time Warping for Lead-Lag Relationships in Lagged Multi-Factor Models

In multivariate time series systems, lead-lag relationships reveal dependencies between time series when they are shifted in time relative to each other. Uncovering such relationships is valuable in downstream tasks, such as control, forecasting, and clustering. By understanding the temporal dependencies between different time series, one can better comprehend the complex interactions and patterns within the system. We develop a cluster-driven methodology based on dynamic time warping for robust detection of lead-lag relationships in lagged multi-factor models. We establish connections to the multireference alignment problem for both the homogeneous and heterogeneous settings. Since multivariate time series are ubiquitous in a wide range of domains, we demonstrate that our algorithm is able to robustly detect lead-lag relationships in financial markets, which can be subsequently leveraged in trading strategies with significant economic benefits.

q-fin.ST↗
arXiv2023

On statistical arbitrage under a conditional factor model of equity returns

We consider a conditional factor model for a multivariate portfolio of United States equities in the context of analysing a statistical arbitrage trading strategy. A state space framework underlies the factor model whereby asset returns are assumed to be a noisy observation of a linear combination of factor values and latent factor risk premia. Filter and state prediction estimates for the risk premia are retrieved in an online way. Such estimates induce filtered asset returns that can be compared to measurement observations, with large deviations representing candidate mean reversion trades. Further, in that the risk premia are modelled as time-varying quantities, non-stationarity in returns is de facto captured. We study an empirical trading strategy respectful of transaction costs, and demonstrate performance over a long history of 29 years, for both a linear and a non-linear state space model. Our results show that the model is competitive relative to the results of other methods, including simple benchmarks and other cutting-edge approaches as published in the literature. Also of note, while strategy performance degradation is noticed through time -- especially for the most recent years -- the strategy continues to offer compelling economics, and has scope for further advancement.

q-fin.ST↗
arXiv2023

JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading

Financial exchanges across the world use limit order books (LOBs) to process orders and match trades. For research purposes it is important to have large scale efficient simulators of LOB dynamics. LOB simulators have previously been implemented in the context of agent-based models (ABMs), reinforcement learning (RL) environments, and generative models, processing order flows from historical data sets and hand-crafted agents alike. For many applications, there is a requirement for processing multiple books, either for the calibration of ABMs or for the training of RL agents. We showcase the first GPU-enabled LOB simulator designed to process thousands of books in parallel, with a notably reduced per-message processing time. The implementation of our simulator - JAX-LOB - is based on design choices that aim to best exploit the powers of JAX without compromising on the realism of LOB-related mechanisms. We integrate JAX-LOB with other JAX packages, to provide an example of how one may address an optimal execution problem with reinforcement learning, and to share some preliminary results from end-to-end RL training on GPUs.

q-fin.TR↗
arXiv2023

Learning to Learn Financial Networks for Optimising Momentum Strategies

Network momentum provides a novel type of risk premium, which exploits the interconnections among assets in a financial network to predict future returns. However, the current process of constructing financial networks relies heavily on expensive databases and financial expertise, limiting accessibility for small-sized and academic institutions. Furthermore, the traditional approach treats network construction and portfolio optimisation as separate tasks, potentially hindering optimal portfolio performance. To address these challenges, we propose L2GMOM, an end-to-end machine learning framework that simultaneously learns financial networks and optimises trading signals for network momentum strategies. The model of L2GMOM is a neural network with a highly interpretable forward propagation architecture, which is derived from algorithm unrolling. The L2GMOM is flexible and can be trained with diverse loss functions for portfolio performance, e.g. the negative Sharpe ratio. Backtesting on 64 continuous future contracts demonstrates a significant improvement in portfolio profitability and risk control, with a Sharpe ratio of 1.74 across a 20-year period.

q-fin.PM↗
arXiv2023

Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network

Developing a generative model of realistic order flow in financial markets is a challenging open problem, with numerous applications for market participants. Addressing this, we propose the first end-to-end autoregressive generative model that generates tokenized limit order book (LOB) messages. These messages are interpreted by a Jax-LOB simulator, which updates the LOB state. To handle long sequences efficiently, the model employs simplified structured state-space layers to process sequences of order book states and tokenized messages. Using LOBSTER data of NASDAQ equity LOBs, we develop a custom tokenizer for message data, converting groups of successive digits to tokens, similar to tokenization in large language models. Out-of-sample results show promising performance in approximating the data distribution, as evidenced by low model perplexity. Furthermore, the mid-price returns calculated from the generated order flow exhibit a significant correlation with the data, indicating impressive conditional forecast performance. Due to the granularity of generated data, and the accuracy of the model, it offers new application areas for future work beyond forecasting, e.g. acting as a world model in high-frequency financial reinforcement learning applications. Overall, our results invite the use and extension of the model in the direction of autoregressive large financial models for the generation of high-frequency financial data and we commit to open-sourcing our code to facilitate future research.

q-fin.TR↗
arXiv2023

Network Momentum across Asset Classes

We investigate the concept of network momentum, a novel trading signal derived from momentum spillover across assets. Initially observed within the confines of pairwise economic and fundamental ties, such as the stock-bond connection of the same company and stocks linked through supply-demand chains, momentum spillover implies a propagation of momentum risk premium from one asset to another. The similarity of momentum risk premium, exemplified by co-movement patterns, has been spotted across multiple asset classes including commodities, equities, bonds and currencies. However, studying the network effect of momentum spillover across these classes has been challenging due to a lack of readily available common characteristics or economic ties beyond the company level. In this paper, we explore the interconnections of momentum features across a diverse range of 64 continuous future contracts spanning these four classes. We utilise a linear and interpretable graph learning model with minimal assumptions to reveal the intricacies of the momentum spillover network. By leveraging the learned networks, we construct a network momentum strategy that exhibits a Sharpe ratio of 1.5 and an annual return of 22%, after volatility scaling, from 2000 to 2022. This paper pioneers the examination of momentum spillover across multiple asset classes using only pricing data, presents a multi-asset investment strategy based on network momentum, and underscores the effectiveness of this strategy through robust empirical analysis.

q-fin.PM↗
arXiv2023

Wisdom of the Crowds or Ignorance of the Masses? A data-driven guide to WSB

A trite yet fundamental question in economics is: What causes large asset price fluctuations? A tenfold rise in the price of GameStop equity, between the 22nd and 28th of January 2021, demonstrated that herding behaviour among retail investors is an important contributing factor. This paper presents a data-driven guide to the forum that started the hype -- WallStreetBets (WSB). Our initial experiments decompose the forum using a large language topic model and network tools. The topic model describes the evolution of the forum over time and shows the persistence of certain topics (such as the market / S\&P500 discussion), and the sporadic interest in others, such as COVID or crude oil. Network analysis allows us to decompose the landscape of retail investors into clusters based on their posting and discussion habits; several large, correlated asset discussion clusters emerge, surrounded by smaller, niche ones. A second set of experiments assesses the impact that WSB discussions have had on the market. We show that forum activity has a Granger-causal relationship with the returns of several assets, some of which are now commonly classified as `meme stocks', while others have gone under the radar. The paper extracts a set of short-term trade signals from posts and long-term (monthly and weekly) trade signals from forum dynamics, and considers their predictive power at different time horizons. In addition to the analysis, the paper presents the dataset, as well as an interactive dashboard, in order to promote further research.

econ.GN↗
arXiv2023

Multi-Factor Inception: What to Do with All of These Features?

Cryptocurrency trading represents a nascent field of research, with growing adoption in industry. Aided by its decentralised nature, many metrics describing cryptocurrencies are accessible with a simple Google search and update frequently, usually at least on a daily basis. This presents a promising opportunity for data-driven systematic trading research, where limited historical data can be augmented with additional features, such as hashrate or Google Trends. However, one question naturally arises: how to effectively select and process these features? In this paper, we introduce Multi-Factor Inception Networks (MFIN), an end-to-end framework for systematic trading with multiple assets and factors. MFINs extend Deep Inception Networks (DIN) to operate in a multi-factor context. Similar to DINs, MFIN models automatically learn features from returns data and output position sizes that optimise portfolio Sharpe ratio. Compared to a range of rule-based momentum and reversion strategies, MFINs learn an uncorrelated, higher-Sharpe strategy that is not captured by traditional, hand-crafted factors. In particular, MFIN models continue to achieve consistent returns over the most recent years (2022-2023), where traditional strategies and the wider cryptocurrency market have underperformed.

q-fin.TR↗
arXiv2023

Canonical Portfolios: Optimal Asset and Signal Combination

This paper presents a novel framework for analyzing the optimal asset and signal combination problem. Our approach builds upon the dynamic portfolio selection problem introduced by Brandt and Santa-Clara (2006) and consists of two stages. First, we reformulate their original investment problem into a tractable one that allows us to derive a closed-form expression for the optimal portfolio policy that is scalable to large cross-sectional financial applications. Second, we recast the problem of selecting a portfolio of correlated assets and signals into selecting a set of uncorrelated managed portfolios through the lens of Canonical Correlation Analysis of Hotelling (1936). The new investment environment of uncorrelated managed portfolios offers unique economic insights into the joint correlation structure of our optimal portfolio policy. We also operationalize our theoretical framework to bridge the gap between theory and practice, showcasing the improved performance of our proposed method over natural competing benchmarks.

q-fin.PM↗
arXiv2023

Deep Inception Networks: A General End-to-End Framework for Multi-asset Quantitative Strategies

We introduce Deep Inception Networks (DINs), a family of Deep Learning models that provide a general framework for end-to-end systematic trading strategies. DINs extract time series (TS) and cross sectional (CS) features directly from daily price returns. This removes the need for handcrafted features, and allows the model to learn from TS and CS information simultaneously. DINs benefit from a fully data-driven approach to feature extraction, whilst avoiding overfitting. Extending prior work on Deep Momentum Networks, DIN models directly output position sizes that optimise Sharpe ratio, but for the entire portfolio instead of individual assets. We propose a novel loss term to balance turnover regularisation against increased systemic risk from high correlation to the overall market. Using futures data, we show that DIN models outperform traditional TS and CS benchmarks, are robust to a range of transaction costs and perform consistently across random seeds. To balance the general nature of DIN models, we provide examples of how attention and Variable Selection Networks can aid the interpretability of investment decisions. These model-specific methods are particularly useful when the dimensionality of the input is high and variable importance fluctuates dynamically over time. Finally, we compare the performance of DIN models on other asset classes, and show how the space of potential features can be customised.

q-fin.TR↗
arXiv2023

Graphical Structures for Design and Verification of Quantum Error Correction

We introduce a high-level graphical framework for designing and analysing quantum error correcting codes, centred on what we term the coherent parity check (CPC). The graphical formulation is based on the diagrammatic tools of the zx-calculus of quantum observables. The resulting framework leads to a construction for stabilizer codes that allows us to design and verify a broad range of quantum codes based on classical ones, and that gives a means of discovering large classes of codes using both analytical and numerical methods. We focus in particular on the smaller codes that will be the first used by near-term devices. We show how CSS codes form a subset of CPC codes and, more generally, how to compute stabilizers for a CPC code. As an explicit example of this framework, we give a method for turning almost any pair of classical [n,k,3] codes into a [[2n - k + 2, k, 3]] CPC code. Further, we give a simple technique for machine search which yields thousands of potential codes, and demonstrate its operation for distance 3 and 5 codes. Finally, we use the graphical tools to demonstrate how Clifford computation can be performed within CPC codes. As our framework gives a new tool for constructing small- to medium-sized codes with relatively high code rates, it provides a new source for codes that could be suitable for emerging devices, while its zx-calculus foundations enable natural integration of error correction with graphical compiler toolchains. It also provides a powerful framework for reasoning about all stabilizer quantum error correction codes of any size.

quant-ph↗
arXiv2023

Deep Attentive Survival Analysis in Limit Order Books: Estimating Fill Probabilities with Convolutional-Transformers

One of the key decisions in execution strategies is the choice between a passive (liquidity providing) or an aggressive (liquidity taking) order to execute a trade in a limit order book (LOB). Essential to this choice is the fill probability of a passive limit order placed in the LOB. This paper proposes a deep learning method to estimate the filltimes of limit orders posted in different levels of the LOB. We develop a novel model for survival analysis that maps time-varying features of the LOB to the distribution of filltimes of limit orders. Our method is based on a convolutional-Transformer encoder and a monotonic neural network decoder. We use proper scoring rules to compare our method with other approaches in survival analysis, and perform an interpretability analysis to understand the informativeness of features used to compute fill probabilities. Our method significantly outperforms those typically used in survival analysis literature. Finally, we carry out a statistical analysis of the fill probability of orders placed in the order book (e.g., within the bid-ask spread) for assets with different queue dynamics and trading activity.

q-fin.ST↗
arXiv2023

Transfer Ranking in Finance: Applications to Cross-Sectional Momentum with Data Scarcity

Cross-sectional strategies are a classical and popular trading style, with recent high performing variants incorporating sophisticated neural architectures. While these strategies have been applied successfully to data-rich settings involving mature assets with long histories, deploying them on instruments with limited samples generally produce over-fitted models with degraded performance. In this paper, we introduce Fused Encoder Networks -- a novel and hybrid parameter-sharing transfer ranking model. The model fuses information extracted using an encoder-attention module operated on a source dataset with a similar but separate module focused on a smaller target dataset of interest. This mitigates the issue of models with poor generalisability that are a consequence of training on scarce target data. Additionally, the self-attention mechanism enables interactions among instruments to be accounted for, not just at the loss level during model training, but also at inference time. Focusing on momentum applied to the top ten cryptocurrencies by market capitalisation as a demonstrative use-case, the Fused Encoder Networks outperforms the reference benchmarks on most performance measures, delivering a three-fold boost in the Sharpe ratio over classical momentum as well as an improvement of approximately 50% against the best benchmark model without transaction costs. It continues outperforming baselines even after accounting for the high transaction costs associated with trading cryptocurrencies.

q-fin.TR↗
arXiv2023

Spatio-Temporal Momentum: Jointly Learning Time-Series and Cross-Sectional Strategies

We introduce Spatio-Temporal Momentum strategies, a class of models that unify both time-series and cross-sectional momentum strategies by trading assets based on their cross-sectional momentum features over time. While both time-series and cross-sectional momentum strategies are designed to systematically capture momentum risk premia, these strategies are regarded as distinct implementations and do not consider the concurrent relationship and predictability between temporal and cross-sectional momentum features of different assets. We model spatio-temporal momentum with neural networks of varying complexities and demonstrate that a simple neural network with only a single fully connected layer learns to simultaneously generate trading signals for all assets in a portfolio by incorporating both their time-series and cross-sectional momentum features. Backtesting on portfolios of 46 actively-traded US equities and 12 equity index futures contracts, we demonstrate that the model is able to retain its performance over benchmarks in the presence of high transaction costs of up to 5-10 basis points. In particular, we find that the model when coupled with least absolute shrinkage and turnover regularization results in the best performance over various transaction cost scenarios.

q-fin.PM↗
arXiv2023

View fusion vis-à-vis a Bayesian interpretation of Black-Litterman for portfolio allocation

The Black-Litterman model extends the framework of the Markowitz Modern Portfolio Theory to incorporate investor views. We consider a case where multiple view estimates, including uncertainties, are given for the same underlying subset of assets at a point in time. This motivates our consideration of data fusion techniques for combining information from multiple sources. In particular, we consider consistency-based methods that yield fused view and uncertainty pairs; such methods are not common to the quantitative finance literature. We show a relevant, modern case of incorporating machine learning model-derived view and uncertainty estimates, and the impact on portfolio allocation, with an example subsuming Arbitrage Pricing Theory. Hence we show the value of the Black-Litterman model in combination with information fusion and artificial intelligence-grounded prediction methods.

q-fin.PM↗
arXiv2023

Estimation of Large Financial Covariances: A Cross-Validation Approach

We introduce a novel covariance estimator for portfolio selection that adapts to the non-stationary or persistent heteroskedastic environments of financial time series by employing exponentially weighted averages and nonlinearly shrinking the sample eigenvalues through cross-validation. Our estimator is structure agnostic, transparent, and computationally feasible in large dimensions. By correcting the biases in the sample eigenvalues and aligning our estimator to more recent risk, we demonstrate that our estimator performs well in large dimensions against existing state-of-the-art static and dynamic covariance shrinkage estimators through simulations and with an empirical application in active portfolio management.

stat.ML↗
arXiv2022

Understanding stock market instability via graph auto-encoders

Understanding stock market instability is a key question in financial management as practitioners seek to forecast breakdowns in asset co-movements which expose portfolios to rapid and devastating collapses in value. The structure of these co-movements can be described as a graph where companies are represented by nodes and edges capture correlations between their price movements. Learning a timely indicator of co-movement breakdowns (manifested as modifications in the graph structure) is central in understanding both financial stability and volatility forecasting. We propose to use the edge reconstruction accuracy of a graph auto-encoder (GAE) as an indicator for how spatially homogeneous connections between assets are, which, based on financial network literature, we use as a proxy to infer market volatility. Our experiments on the S&P 500 over the 2015-2022 period show that higher GAE reconstruction error values are correlated with higher volatility. We also show that out-of-sample autoregressive modeling of volatility is improved by the addition of the proposed measure. Our paper contributes to the literature of machine learning in finance particularly in the context of understanding stock market instability.

cs.CE↗