Equities

Detecting and Triaging Spoofing using Temporal Convolutional Networks ArXiv ID: 2403.13429 “View on arXiv” Authors: Unknown Abstract As algorithmic trading and electronic markets continue to transform the landscape of financial markets, detecting and deterring rogue agents to maintain a fair and efficient marketplace is crucial. The explosion of large datasets and the continually changing tricks of the trade make it difficult to adapt to new market conditions and detect bad actors. To that end, we propose a framework that can be adapted easily to various problems in the space of detecting market manipulation. Our approach entails initially employing a labelling algorithm which we use to create a training set to learn a weakly supervised model to identify potentially suspicious sequences of order book states. The main goal here is to learn a representation of the order book that can be used to easily compare future events. Subsequently, we posit the incorporation of expert assessment to scrutinize specific flagged order book states. In the event of an expert’s unavailability, recourse is taken to the application of a more complex algorithm on the identified suspicious order book states. We then conduct a similarity search between any new representation of the order book against the expert labelled representations to rank the results of the weak learner. We show some preliminary results that are promising to explore further in this direction ...

Modeling stock price dynamics on the Ghana Stock Exchange: A Geometric Brownian Motion approach ArXiv ID: 2403.13192 “View on arXiv” Authors: Unknown Abstract Modeling financial data often relies on assumptions that may prove insufficient or unrealistic in practice. The Geometric Brownian Motion (GBM) model is frequently employed to represent stock price processes. This study investigates whether the behavior of weekly and monthly returns of selected equities listed on the Ghana Stock Exchange conforms to the GBM model. Parameters of the GBM model were estimated for five equities, and forecasts were generated for three months. Evaluation of estimation accuracy was conducted using mean square error (MSE). Results indicate that the expected prices from the modeled equities closely align with actual stock prices observed on the Exchange. Furthermore, while some deviations were observed, the actual prices consistently fell within the estimated confidence intervals. ...

Advanced Statistical Arbitrage with Reinforcement Learning ArXiv ID: 2403.12180 “View on arXiv” Authors: Unknown Abstract Statistical arbitrage is a prevalent trading strategy which takes advantage of mean reverse property of spread of paired stocks. Studies on this strategy often rely heavily on model assumption. In this study, we introduce an innovative model-free and reinforcement learning based framework for statistical arbitrage. For the construction of mean reversion spreads, we establish an empirical reversion time metric and optimize asset coefficients by minimizing this empirical mean reversion time. In the trading phase, we employ a reinforcement learning framework to identify the optimal mean reversion strategy. Diverging from traditional mean reversion strategies that primarily focus on price deviations from a long-term mean, our methodology creatively constructs the state space to encapsulate the recent trends in price movements. Additionally, the reward function is carefully tailored to reflect the unique characteristics of mean reversion trading. ...

From Factor Models to Deep Learning: Machine Learning in Reshaping Empirical Asset Pricing ArXiv ID: 2403.06779 “View on arXiv” Authors: Unknown Abstract This paper comprehensively reviews the application of machine learning (ML) and AI in finance, specifically in the context of asset pricing. It starts by summarizing the traditional asset pricing models and examining their limitations in capturing the complexities of financial markets. It explores how 1) ML models, including supervised, unsupervised, semi-supervised, and reinforcement learning, provide versatile frameworks to address these complexities, and 2) the incorporation of advanced ML algorithms into traditional financial models enhances return prediction and portfolio optimization. These methods can adapt to changing market dynamics by modeling structural changes and incorporating heterogeneous data sources, such as text and images. In addition, this paper explores challenges in applying ML in asset pricing, addressing the growing demand for explainability in decision-making and mitigating overfitting in complex models. This paper aims to provide insights into novel methodologies showcasing the potential of ML to reshape the future of quantitative finance. ...

Entropy corrected geometric Brownian motion ArXiv ID: 2403.06253 “View on arXiv” Authors: Unknown Abstract The geometric Brownian motion (GBM) is widely employed for modeling stochastic processes, yet its solutions are characterized by the log-normal distribution. This comprises predictive capabilities of GBM mainly in terms of forecasting applications. Here, entropy corrections to GBM are proposed to go beyond log-normality restrictions and better account for intricacies of real systems. It is shown that GBM solutions can be effectively refined by arguing that entropy is reduced when deterministic content of considered data increases. Notable improvements over conventional GBM are observed for several cases of non-log-normal distributions, ranging from a dice roll experiment to real world data. ...

Calibrated rank volatility stabilized models for large equity markets ArXiv ID: 2403.04674 “View on arXiv” Authors: Unknown Abstract In the framework of stochastic portfolio theory we introduce rank volatility stabilized models for large equity markets over long time horizons. These models are rank-based extensions of the volatility stabilized models introduced by Fernholz & Karatzas in 2005. On the theoretical side we establish global existence of the model and ergodicity of the induced ranked market weights. We also derive explicit expressions for growth-optimal portfolios and show the existence of relative arbitrage with respect to the market portfolio. On the empirical side we calibrate the model to sixteen years of CRSP US equity data matching (i) rank-based volatilities, (ii) stock turnover as measured by market weight collisions, (iii) the average market rate of return and (iv) the capital distribution curve. Assessment of model fit and error analysis is conducted both in and out of sample. To the best of our knowledge this is the first model exhibiting relative arbitrage that has statistically been shown to have a good quantitative fit with the empirical features (i)-(iv). We additionally simulate trajectories of the calibrated model and compare them to historical trajectories, both in and out of sample. ...

RVRAE: A Dynamic Factor Model Based on Variational Recurrent Autoencoder for Stock Returns Prediction ArXiv ID: 2403.02500 “View on arXiv” Authors: Unknown Abstract In recent years, the dynamic factor model has emerged as a dominant tool in economics and finance, particularly for investment strategies. This model offers improved handling of complex, nonlinear, and noisy market conditions compared to traditional static factor models. The advancement of machine learning, especially in dealing with nonlinear data, has further enhanced asset pricing methodologies. This paper introduces a groundbreaking dynamic factor model named RVRAE. This model is a probabilistic approach that addresses the temporal dependencies and noise in market data. RVRAE ingeniously combines the principles of dynamic factor modeling with the variational recurrent autoencoder (VRAE) from deep learning. A key feature of RVRAE is its use of a prior-posterior learning method. This method fine-tunes the model’s learning process by seeking an optimal posterior factor model informed by future data. Notably, RVRAE is adept at risk modeling in volatile stock markets, estimating variances from latent space distributions while also predicting returns. Our empirical tests with real stock market data underscore RVRAE’s superior performance compared to various established baseline methods. ...

Transformer for Times Series: an Application to the S&P500 ArXiv ID: 2403.02523 “View on arXiv” Authors: Unknown Abstract The transformer models have been extensively used with good results in a wide area of machine learning applications including Large Language Models and image generation. Here, we inquire on the applicability of this approach to financial time series. We first describe the dataset construction for two prototypical situations: a mean reverting synthetic Ornstein-Uhlenbeck process on one hand and real S&P500 data on the other hand. Then, we present in detail the proposed Transformer architecture and finally we discuss some encouraging results. For the synthetic data we predict rather accurately the next move, and for the S&P500 we get some interesting results related to quadratic variation and volatility prediction. ...

“Digitwashing”: The Gap between Words and Deeds in Digital Transformation and Stock Price Crash Risk ArXiv ID: 2403.01360 “View on arXiv” Authors: Unknown Abstract The contrast between companies’ “fleshy” promises and the “skeletal” performance in digital transformation may lead to a higher risk of stock price crash. This paper selects a sample of Shanghai and Shenzhen A-share listed companies from 2010 to 2021, empirically analyses the specific impact of the gap between words and deeds in digital transformation (GDT) on the stock price crash risk, and explores the possible causes of GDT. We found that GDT significantly increases the stock price crash risk, and this finding is still valid after a series of robustness tests. In a further study, a deeper examination of the causes of GDT reveals that firms’ perceptions of economic policy uncertainty significantly increase GDT, and the effect is more pronounced in the sample of loss-making firms. At the same time, the results of the heterogeneity test suggest that investors are more tolerant of state-owned enterprises when they are in the GDT situation. Taken together, we provide a concrete bridge between the two measures of digital transformation - digital text frequency and digital technology share - and offer new insights to enhance capital market stability. ...

Dimensionality reduction techniques to support insider trading detection ArXiv ID: 2403.00707 “View on arXiv” Authors: Unknown Abstract Identification of market abuse is an extremely complicated activity that requires the analysis of large and complex datasets. We propose an unsupervised machine learning method for contextual anomaly detection, which allows to support market surveillance aimed at identifying potential insider trading activities. This method lies in the reconstruction-based paradigm and employs principal component analysis and autoencoders as dimensionality reduction techniques. The only input of this method is the trading position of each investor active on the asset for which we have a price sensitive event (PSE). After determining reconstruction errors related to the trading profiles, several conditions are imposed in order to identify investors whose behavior could be suspicious of insider trading related to the PSE. As a case study, we apply our method to investor resolved data of Italian stocks around takeover bids. ...