Equities

Correlation emergence in two coupled simulated limit order books ArXiv ID: 2408.03181 “View on arXiv” Authors: Unknown Abstract We use random walks to simulate the fluid limit of two coupled diffusive limit order books to model correlation emergence. The model implements the arrival, cancellation and diffusion of orders coupled by a pairs trader profiting from the mean-reversion between the two order books in the fluid limit for a Lit order book with vanishing boundary conditions and order volume conservation. We are able to demonstrate the recovery of an Epps effect from this. We discuss how various stylised facts depend on the model parameters and the numerical scheme and discuss the various strengths and weaknesses of the approach. We demonstrate how the Epps effect depends on different choices of time and price discretisation. This shows how an Epps effect can emerge without recourse to market microstructure noise relative to a latent model but can rather be viewed as an emergent property arising from trader interactions in a world of asynchronous events. ...

NeuralBeta: Estimating Beta Using Deep Learning ArXiv ID: 2408.01387 “View on arXiv” Authors: Unknown Abstract Traditional approaches to estimating beta in finance often involve rigid assumptions and fail to adequately capture beta dynamics, limiting their effectiveness in use cases like hedging. To address these limitations, we have developed a novel method using neural networks called NeuralBeta, which is capable of handling both univariate and multivariate scenarios and tracking the dynamic behavior of beta. To address the issue of interpretability, we introduce a new output layer inspired by regularized weighted linear regression, which provides transparency into the model’s decision-making process. We conducted extensive experiments on both synthetic and market data, demonstrating NeuralBeta’s superior performance compared to benchmark methods across various scenarios, especially instances where beta is highly time-varying, e.g., during regime shifts in the market. This model not only represents an advancement in the field of beta estimation, but also shows potential for applications in other financial contexts that assume linear relationships. ...

Inferring financial stock returns correlation from complex network analysis ArXiv ID: 2407.20380 “View on arXiv” Authors: Unknown Abstract Financial stock returns correlations have been studied in the prism of random matrix theory, to distinguish the signal from the “noise”. Eigenvalues of the matrix that are above the rescaled Marchenko Pastur distribution can be interpreted as collective modes behavior while the modes under are usually considered as noise. In this analysis we use complex network analysis to simulate the “noise” and the “market” component of the return correlations, by introducing some meaningful correlations in simulated geometric Brownian motion for the stocks. We find that the returns correlation matrix is dominated by stocks with high eigenvector centrality and clustering found in the network. We then use simulated “market” random walks to build an optimal portfolio and find that the overall return performs better than using the historical mean-variance data, up to 50% on short time scale. ...

Contrastive Learning of Asset Embeddings from Financial Time Series ArXiv ID: 2407.18645 “View on arXiv” Authors: Unknown Abstract Representation learning has emerged as a powerful paradigm for extracting valuable latent features from complex, high-dimensional data. In financial domains, learning informative representations for assets can be used for tasks like sector classification, and risk management. However, the complex and stochastic nature of financial markets poses unique challenges. We propose a novel contrastive learning framework to generate asset embeddings from financial time series data. Our approach leverages the similarity of asset returns over many subwindows to generate informative positive and negative samples, using a statistical sampling strategy based on hypothesis testing to address the noisy nature of financial data. We explore various contrastive loss functions that capture the relationships between assets in different ways to learn a discriminative representation space. Experiments on real-world datasets demonstrate the effectiveness of the learned asset embeddings on benchmark industry classification and portfolio optimization tasks. In each case our novel approaches significantly outperform existing baselines highlighting the potential for contrastive learning to capture meaningful and actionable relationships in financial data. ...

TCGPN: Temporal-Correlation Graph Pre-trained Network for Stock Forecasting ArXiv ID: 2407.18519 “View on arXiv” Authors: Unknown Abstract Recently, the incorporation of both temporal features and the correlation across time series has become an effective approach in time series prediction. Spatio-Temporal Graph Neural Networks (STGNNs) demonstrate good performance on many Temporal-correlation Forecasting Problem. However, when applied to tasks lacking periodicity, such as stock data prediction, the effectiveness and robustness of STGNNs are found to be unsatisfactory. And STGNNs are limited by memory savings so that cannot handle problems with a large number of nodes. In this paper, we propose a novel approach called the Temporal-Correlation Graph Pre-trained Network (TCGPN) to address these limitations. TCGPN utilize Temporal-correlation fusion encoder to get a mixed representation and pre-training method with carefully designed temporal and correlation pre-training tasks. Entire structure is independent of the number and order of nodes, so better results can be obtained through various data enhancements. And memory consumption during training can be significantly reduced through multiple sampling. Experiments are conducted on real stock market data sets CSI300 and CSI500 that exhibit minimal periodicity. We fine-tune a simple MLP in downstream tasks and achieve state-of-the-art results, validating the capability to capture more robust temporal correlation patterns. ...

Financial Statement Analysis with Large Language Models ArXiv ID: 2407.17866 “View on arXiv” Authors: Unknown Abstract We investigate whether large language models (LLMs) can successfully perform financial statement analysis in a way similar to a professional human analyst. We provide standardized and anonymous financial statements to GPT4 and instruct the model to analyze them to determine the direction of firms’ future earnings. Even without narrative or industry-specific information, the LLM outperforms financial analysts in its ability to predict earnings changes directionally. The LLM exhibits a relative advantage over human analysts in situations when the analysts tend to struggle. Furthermore, we find that the prediction accuracy of the LLM is on par with a narrowly trained state-of-the-art ML model. LLM prediction does not stem from its training memory. Instead, we find that the LLM generates useful narrative insights about a company’s future performance. Lastly, our trading strategies based on GPT’s predictions yield a higher Sharpe ratio and alphas than strategies based on other models. Our results suggest that LLMs may take a central role in analysis and decision-making. ...

Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflow ArXiv ID: 2407.18103 “View on arXiv” Authors: Unknown Abstract Large language models (LLMs) and their fine-tuning techniques have demonstrated superior performance in various language understanding and generation tasks. This paper explores fine-tuning LLMs for stock return forecasting with financial newsflow. In quantitative investing, return forecasting is fundamental for subsequent tasks like stock picking, portfolio optimization, etc. We formulate the model to include text representation and forecasting modules. We propose to compare the encoder-only and decoder-only LLMs, considering they generate text representations in distinct ways. The impact of these different representations on forecasting performance remains an open question. Meanwhile, we compare two simple methods of integrating LLMs’ token-level representations into the forecasting module. The experiments on real news and investment universes reveal that: (1) aggregated representations from LLMs’ token-level embeddings generally produce return predictions that enhance the performance of long-only and long-short portfolios; (2) in the relatively large investment universe, the decoder LLMs-based prediction model leads to stronger portfolios, whereas in the small universes, there are no consistent winners. Among the three LLMs studied (DeBERTa, Mistral, Llama), Mistral performs more robustly across different universes; (3) return predictions derived from LLMs’ text representations are a strong signal for portfolio construction, outperforming conventional sentiment scores. ...

Estimation of bid-ask spreads in the presence of serial dependence ArXiv ID: 2407.17401 “View on arXiv” Authors: Unknown Abstract Starting from a basic model in which the dynamic of the transaction prices is a geometric Brownian motion disrupted by a microstructure white noise, corresponding to the random alternation of bids and asks, we propose moment-based estimators along with their statistical properties. We then make the model more realistic by considering serial dependence: we assume a geometric fractional Brownian motion for the price, then an Ornstein-Uhlenbeck process for the microstructure noise. In these two cases of serial dependence, we propose again consistent and asymptotically normal estimators. All our estimators are compared on simulated data with existing approaches, such as Roll, Corwin-Schultz, Abdi-Ranaldo, or Ardia-Guidotti-Kroencke estimators. ...

Hopfield Networks for Asset Allocation ArXiv ID: 2407.17645 “View on arXiv” Authors: Unknown Abstract We present the first application of modern Hopfield networks to the problem of portfolio optimization. We performed an extensive study based on combinatorial purged cross-validation over several datasets and compared our results to both traditional and deep-learning-based methods for portfolio selection. Compared to state-of-the-art deep-learning methods such as Long-Short Term Memory networks and Transformers, we find that the proposed approach performs on par or better, while providing faster training times and better stability. Our results show that Modern Hopfield Networks represent a promising approach to portfolio optimization, allowing for an efficient, scalable, and robust solution for asset allocation, risk management, and dynamic rebalancing. ...

Multi-Industry Simplex 2.0 : Temporally-Evolving Probabilistic Industry Classification ArXiv ID: 2407.16437 “View on arXiv” Authors: Unknown Abstract Accurate industry classification is critical for many areas of portfolio management, yet the traditional single-industry framework of the Global Industry Classification Standard (GICS) struggles to comprehensively represent risk for highly diversified multi-sector conglomerates like Amazon. Previously, we introduced the Multi-Industry Simplex (MIS), a probabilistic extension of GICS that utilizes topic modeling, a natural language processing approach. Although our initial version, MIS-1, was able to improve upon GICS by providing multi-industry representations, it relied on an overly simple architecture that required prior knowledge about the number of industries and relied on the unrealistic assumption that industries are uncorrelated and independent over time. We improve upon this model with MIS-2, which addresses three key limitations of MIS-1 : we utilize Bayesian Non-Parametrics to automatically infer the number of industries from data, we employ Markov Updating to account for industries that change over time, and we adjust for correlated and hierarchical industries allowing for both broad and niche industries (similar to GICS). Further, we provide an out-of-sample test directly comparing MIS-2 and GICS on the basis of future correlation prediction, where we find evidence that MIS-2 provides a measurable improvement over GICS. MIS-2 provides portfolio managers with a more robust tool for industry classification, empowering them to more effectively identify and manage risk, particularly around multi-sector conglomerates in a rapidly evolving market in which new industries periodically emerge. ...