arXiv subjects

Denise Gorse

Publications and source records attributed to Denise Gorse.

15 recordsLinked to original sources

arXiv2026

Using Seismic Statistical Features and VQ-VAE to Improve Spatiotemporal Seismicity Predictability

In this paper we build upon a previous study in which we demonstrated, using XGBoost and earthquake catalogue data from Japan and Chile, that a set of 60 seismic statistical features (SSFs) had much greater predictive value than a set of 428 generic time series features from the tsfresh package. We here extend this previous work in two key ways, focusing on data from Japan as a large dataset is necessary in order to allow for the training of a deep learning (autoencoder) model. First, we move from whole-region prediction (considering, for each candidate event, the likelihood of an event M $\geq$ 5.0 anywhere in the region in the next 15 days) to localised predictions in which both the region of feature computation and the region of prediction are restricted to a circle of radius 24 km around the candidate event, and we show that performance remains excellent, similar to our previous whole-region study for the same area. Second, we here couple this proven set of SSFs, based on one-dimensional (catalogue) data, with a novel feature based on magnitude-stratified two-dimensional seismic maps, obtained by training a VQ-VAE model to reproduce such maps as output and identifying a measure of its error in doing so with anomalies in magnitude distribution reflecting a localised build-up of crustal stress. We show that while localised prediction based only on a set of SSFs can be effective, with test AUC values as high as those obtained in the case of Japan in our previous whole-region study, the inclusion of the new natively-spatial VQ-VAE-derived feature, top-ranked by SHAP analysis, both improves prediction and points toward a new approach that might allow computationally time-demanding traditional seismic features to be entirely set aside.

cs.LG↗

arXiv2026

Predicting liquid properties and behavior via droplet pinch-off and machine learning

Here we demonstrate that the time-evolving interface observed during droplet formation, and consequently the resulting morphology nearing pinch-off, encode sufficient physical information for machine-learning (ML) frameworks to accurately infer key fluid properties, including viscosity and surface tension. Snapshots of dripping drops at the moment of break-up, together with their liquid properties and the flow rate, are used to form a data set for training ML algorithms. Experiments consisted of visualizing, using high-speed imaging, the process of droplet formation and identifying the frame closest to break-up. Experiments were conducted using Newtonian fluids under controlled flow conditions. In terms of the Reynolds (Re) and Ohnesorge (Oh) numbers, our conditions cover the domains 0.001< Re< 200 and 0.01 < Oh < 20, by using silicon oils, aqueous solutions of ethanol and glycerin, and methanol. For each case, flow parameters were recorded, along with images capturing the final stages of droplet break-up. Supervised regression models were trained to predict fluid parameters from the extracted contours of the breaking droplets. Our data set contains 840 examples. Our results demonstrate that the droplet geometry at pinch-off contains sufficient information to infer fluid properties by machine learning approaches. Our methods can predict surface tension, viscosity, or the droplet shape at pinch-off. These approaches provide alternatives to conventional methods to measure liquid properties while reducing measurement complexity and evaluation time and facilitating integration into automation. Unsupervised clustering is performed; the clusters represent regions in the Re-Oh and Bo-Oh planes, indicating that the latent representation may reveal physical properties and offering insight into droplet dynamics.

physics.flu-dyn↗

arXiv2023

Improving Portfolio Performance Using a Novel Method for Predicting Financial Regimes

This work extends a previous work in regime detection, which allowed trading positions to be profitably adjusted when a new regime was detected, to ex ante prediction of regimes, leading to substantial performance improvements over the earlier model, over all three asset classes considered (equities, commodities, and foreign exchange), over a test period of four years. The proposed new model is also benchmarked over this same period against a hidden Markov model, the most popular current model for financial regime prediction, and against an appropriate index benchmark for each asset class, in the case of the commodities model having a test period cost-adjusted cumulative return over four times higher than that expected from the index. Notably, the proposed model makes use of a contrarian trading strategy, not uncommon in the financial industry but relatively unexplored in machine learning models. The model also makes use of frequent short positions, something not always desirable to investors due to issues of both financial risk and ethics; however, it is discussed how further work could remove this reliance on shorting and allow the construction of a long-only version of the model.

q-fin.RM↗

arXiv2023

Multi-Period Portfolio Optimisation Using a Regime-Switching Predictive Framework

Regime-switching poses both problems and opportunities for portfolio managers. If a switch in the behaviour of the markets is not quickly detected it can be a source of loss, since previous trading positions may be inappropriate in the new regime. However, if a regime-switch can be detected quickly, and especially if it can be predicted ahead of time, these changes in market behaviour can instead be a source of substantial profit. The work of this paper builds on two previous works by the authors, the first of these dealing with regime detection and the second, which is an extension of the first, with regime prediction. Specifically, this work uses our previous regime-prediction model (KMRF) within a framework of multi-period portfolio optimisation, achieved by model predictive control, (MPC), with the KMRF-derived return estimates accuracy-boosted by means of a novel use of a Kalman filter. The resulting proposed model, which we term the KMRF+MPC model, to reflect its constituent methodologies, is demonstrated to outperform industry-standard benchmarks, even though it is restricted, in order to be acceptable to the widest range of investors, to long-only positions.

cs.CE↗

arXiv2022

Axial-LOB: High-Frequency Trading with Axial Attention

Previous attempts to predict stock price from limit order book (LOB) data are mostly based on deep convolutional neural networks. Although convolutions offer efficiency by restricting their operations to local interactions, it is at the cost of potentially missing out on the detection of long-range dependencies. Recent studies address this problem by employing additional recurrent or attention layers that increase computational complexity. In this work, we propose Axial-LOB, a novel fully-attentional deep learning architecture for predicting price movements of stocks from LOB data. By utilizing gated position-sensitive axial attention layers our architecture is able to construct feature maps that incorporate global interactions, while significantly reducing the size of the parameter space. Unlike previous works, Axial-LOB does not rely on hand-crafted convolutional kernels and hence has stable performance under input permutations and the capacity to incorporate additional LOB features. The effectiveness of Axial-LOB is demonstrated on a large benchmark dataset, containing time series representations of millions of high-frequency trading events, where our model establishes a new state of the art, achieving an excellent directional classification performance at all tested prediction horizons.

q-fin.TR↗

arXiv2022

A Novel Multi-Objective Velocity-Free Boolean Particle Swarm Optimization

This paper extends boolean particle swarm optimization to a multi-objective setting, to our knowledge for the first time in the literature. Our proposed new boolean algorithm, MBOnvPSO, is notably simplified by the omission of a velocity update rule and has enhanced exploration ability due to the inclusion of a 'noise' term in the position update rule that prevents particles being trapped in local optima. Our algorithm additionally makes use of an external archive to store non-dominated solutions and implements crowding distance to encourage solution diversity. In benchmark tests, MBOnvPSO produced high quality Pareto fronts, when compared to benchmarked alternatives, for all of the multi-objective test functions considered, with competitive performance in search spaces with up to 600 discrete dimensions.

cs.NE↗

arXiv2022

ASTra: A Novel Algorithm-Level Approach to Imbalanced Classification

We propose a novel output layer activation function, which we name ASTra (Asymmetric Sigmoid Transfer function), which makes the classification of minority examples, in scenarios of high imbalance, more tractable. We combine this with a loss function that helps to effectively target minority misclassification. These two methods can be used together or separately, with their combination recommended for the most severely imbalanced cases. The proposed approach is tested on datasets with IRs from 588.24 to 4000 and very few minority examples (in some datasets, as few as five). Results using neural networks with from two to 12 hidden units are demonstrated to be comparable to, or better than, equivalent results obtained in a recent study that deployed a wide range of complex, hybrid data-level ensemble classifiers.

cs.LG↗

arXiv2022

Improving on the Markov-Switching Regression Model by the Use of an Adaptive Moving Average

Regime detection is vital for the effective operation of trading and investment strategies. However, the most popular means of doing this, the two-state Markov-switching regression model (MSR), is not an optimal solution, as two volatility states do not fully capture the complexity of the market. Past attempts to extend this model to a multi-state MSR have proved unstable, potentially expensive in terms of trading costs, and can only divide the market into states with varying levels of volatility, which is not the only aspect of market dynamics relevant to trading. We demonstrate it is possible and valuable to instead segment the market into more than two states not on the basis of volatility alone, but on a combined basis of volatility and trend, by combining the two-state MSR with an adaptive moving average. A realistic trading framework is used to demonstrate that using two selected states from the four thus generated leads to better trading performance than traditional benchmarks, including the two-state MSR. In addition, the proposed model could serve as a label generator for machine learning tasks used in predicting financial regimes ex ante.

cs.CE↗

arXiv2022

Portfolio Transformer for Attention-Based Asset Allocation

Traditional approaches to financial asset allocation start with returns forecasting followed by an optimization stage that decides the optimal asset weights. Any errors made during the forecasting step reduce the accuracy of the asset weightings, and hence the profitability of the overall portfolio. The Portfolio Transformer (PT) network, introduced here, circumvents the need to predict asset returns and instead directly optimizes the Sharpe ratio, a risk-adjusted performance metric widely used in practice. The PT is a novel end-to-end portfolio optimization framework, inspired by the numerous successes of attention mechanisms in natural language processing. With its full encoder-decoder architecture, specialized time encoding layers, and gating components, the PT has a high capacity to learn long-term dependencies among portfolio assets and hence can adapt more quickly to changing market conditions such as the COVID-19 pandemic. To demonstrate its robustness, the PT is compared against other algorithms, including the current LSTM-based state of the art, on three different datasets, with results showing that it offers the best risk-adjusted performance.

q-fin.PM↗

arXiv2022

Deep vs. Shallow Learning: A Benchmark Study in Low Magnitude Earthquake Detection

While deep learning models have seen recent high uptake in the geosciences, and are appealing in their ability to learn from minimally processed input data, as black box models they do not provide an easy means to understand how a decision is reached, which in safety-critical tasks especially can be problematical. An alternative route is to use simpler, more transparent white box models, in which task-specific feature construction replaces the more opaque feature discovery process performed automatically within deep learning models. Using data from the Groningen Gas Field in the Netherlands, we build on an existing logistic regression model by the addition of four further features discovered using elastic net driven data mining within the catch22 time series analysis package. We then evaluate the performance of the augmented logistic regression model relative to a deep (CNN) model, pre-trained on the Groningen data, on progressively increasing noise-to-signal ratios. We discover that, for each ratio, our logistic regression model correctly detects every earthquake, while the deep model fails to detect nearly 20 % of seismic events, thus justifying at least a degree of caution in the application of deep models, especially to data with higher noise-to-signal ratios.

cs.LG↗

arXiv2021

A Meta-Method for Portfolio Management Using Machine Learning for Adaptive Strategy Selection

This work proposes a novel portfolio management technique, the Meta Portfolio Method (MPM), inspired by the successes of meta approaches in the field of bioinformatics and elsewhere. The MPM uses XGBoost to learn how to switch between two risk-based portfolio allocation strategies, the Hierarchical Risk Parity (HRP) and more classical Naïve Risk Parity (NRP). It is demonstrated that the MPM is able to successfully take advantage of the best characteristics of each strategy (the NRP's fast growth during market uptrends, and the HRP's protection against drawdowns during market turmoil). As a result, the MPM is shown to possess an excellent out-of-sample risk-reward profile, as measured by the Sharpe ratio, and in addition offers a high degree of interpretability of its asset allocation decisions.

q-fin.PM↗

arXiv2021

Intra-Day Price Simulation with Generative Adversarial Modelling of the Order Flow

Intra-day price variations in financial markets are driven by the sequence of orders, called the order flow, that is submitted at high frequency by traders. This paper introduces a novel application of the Sequence Generative Adversarial Networks framework to model the order flow, such that random sequences of the order flow can then be generated to simulate the intra-day variation of prices. As a benchmark, a well-known parametric model from the quantitative finance literature is selected. The models are fitted, and then multiple random paths of the order flow sequences are sampled from each model. Model performances are then evaluated by using the generated sequences to simulate price variations, and we compare the empirical regularities between the price variations produced by the generated and real sequences. The empirical regularities considered include the distribution of the price log-returns, the price volatility, and the heavy-tail of the log-returns distributions. The results show that the order sequences from the generative model are better able to reproduce the statistical behaviour of real price variations than the sequences from the benchmark.

q-fin.ST↗

arXiv2020

Deep Probabilistic Modelling of Price Movements for High-Frequency Trading

In this paper we propose a deep recurrent architecture for the probabilistic modelling of high-frequency market prices, important for the risk management of automated trading systems. Our proposed architecture incorporates probabilistic mixture models into deep recurrent neural networks. The resulting deep mixture models simultaneously address several practical challenges important in the development of automated high-frequency trading strategies that were previously neglected in the literature: 1) probabilistic forecasting of the price movements; 2) single objective prediction of both the direction and size of the price movements. We train our models on high-frequency Bitcoin market data and evaluate them against benchmark models obtained from the literature. We show that our model outperforms the benchmark models in both a metric-based test and in a simulated trading scenario

q-fin.ST↗

arXiv2020

Deep Recurrent Modelling of Stationary Bitcoin Price Formation Using the Order Flow

In this paper we propose a deep recurrent model based on the order flow for the stationary modelling of the high-frequency directional prices movements. The order flow is the microsecond stream of orders arriving at the exchange, driving the formation of prices seen on the price chart of a stock or currency. To test the stationarity of our proposed model we train our model on data before the 2017 Bitcoin bubble period and test our model during and after the bubble. We show that without any retraining, the proposed model is temporally stable even as Bitcoin trading shifts into an extremely volatile "bubble trouble" period. The significance of the result is shown by benchmarking against existing state-of-the-art models in the literature for modelling price formation using deep learning.

q-fin.ST↗

arXiv2018

Mutual-Excitation of Cryptocurrency Market Returns and Social Media Topics

Cryptocurrencies have recently experienced a new wave of price volatility and interest; activity within social media communities relating to cryptocurrencies has increased significantly. There is currently limited documented knowledge of factors which could indicate future price movements. This paper aims to decipher relationships between cryptocurrency price changes and topic discussion on social media to provide, among other things, an understanding of which topics are indicative of future price movements. To achieve this a well-known dynamic topic modelling approach is applied to social media communication to retrieve information about the temporal occurrence of various topics. A Hawkes model is then applied to find interactions between topics and cryptocurrency prices. The results show particular topics tend to precede certain types of price movements, for example the discussion of 'risk and investment vs trading' being indicative of price falls, the discussion of 'substantial price movements' being indicative of volatility, and the discussion of 'fundamental cryptocurrency value' by technical communities being indicative of price rises. The knowledge of topic relationships gained here could be built into a real-time system, providing trading or alerting signals.

cs.SI↗