Paul Bilokon

Abir Sridi, Paul Bilokon

Stochastic volatility models, where the volatility is a stochastic process, can capture most of the essential stylized facts of implied volatility surfaces and give more realistic dynamics of the volatility smile/skew. However, they come with the significant issue that they take too long to calibrate. Alternative calibration methods based on Deep Learning (DL) techniques have been recently used to build fast and accurate solutions to the calibration problem. Huge and Savine developed a Differential Machine Learning (DML) approach, where Machine Learning models are trained on samples of not only features and labels but also differentials of labels to features. The present work aims to apply the DML technique to price vanilla European options (i.e. the calibration instruments), more specifically, puts when the underlying asset follows a Heston model and then calibrate the model on the trained network. DML allows for fast training and accurate pricing. The trained neural network dramatically reduces Heston calibration's computation time. In this work, we also introduce different regularisation techniques, and we apply them notably in the case of the DML. We compare their performance in reducing overfitting and improving the generalisation error. The DML performance is also compared to the classical DL (without differentiation) one in the case of Feed-Forward Neural Networks. We show that the DML outperforms the DL. The complete code for our experiments is provided in the GitHub repository: https://github.com/asridi/DML-Calibration-Heston-Model

Fazl Barez, Paul Bilokon, Arthur Gervais et al.

This paper explores the novel deep learning Transformers architectures for high-frequency Bitcoin-USDT log-return forecasting and compares them to the traditional Long Short-Term Memory models. A hybrid Transformer model, called \textbf{HFformer}, is then introduced for time series forecasting which incorporates a Transformer encoder, linear decoder, spiking activations, and quantile loss function, and does not use position encoding. Furthermore, possible high-frequency trading strategies for use with the HFformer model are discussed, including trade sizing, trading signal aggregation, and minimal trading threshold. Ultimately, the performance of the HFformer and Long Short-Term Memory models are assessed and results indicate that the HFformer achieves a higher cumulative PnL than the LSTM when trading with multiple signals during backtesting.

Paul Bilokon, Yitao Qiu

With the rapid development of artificial intelligence, long short term memory (LSTM), one kind of recurrent neural network (RNN), has been widely applied in time series prediction. Like RNN, Transformer is designed to handle the sequential data. As Transformer achieved great success in Natural Language Processing (NLP), researchers got interested in Transformer's performance on time series prediction, and plenty of Transformer-based solutions on long time series forecasting have come out recently. However, when it comes to financial time series prediction, LSTM is still a dominant architecture. Therefore, the question this study wants to answer is: whether the Transformer-based model can be applied in financial time series prediction and beat LSTM. To answer this question, various LSTM-based and Transformer-based models are compared on multiple financial prediction tasks based on high-frequency limit order book data. A new LSTM-based model called DLSTM is built and new architecture for the Transformer-based model is designed to adapt for financial prediction. The experiment result reflects that the Transformer-based model only has the limited advantage in absolute price sequence prediction. The LSTM-based models show better and more robust performance on difference sequence prediction, such as price difference and price movement.

Koti S. Jaddu, Paul A. Bilokon

High-frequency trading is prevalent, where automated decisions must be made quickly to take advantage of price imbalances and patterns in price action that forecast near-future movements. While many algorithms have been explored and tested, analytical methods fail to harness the whole nature of the market environment by focusing on a limited domain. With the evergrowing machine learning field, many large-scale end-to-end studies on raw data have been successfully employed to increase the domain scope for profitable trading but are very difficult to replicate. Combining deep learning on the order books with reinforcement learning is one way of breaking down large-scale end-to-end learning into more manageable and lightweight components for reproducibility, suitable for retail trading. The following work focuses on forecasting returns across multiple horizons using order flow imbalance and training three temporal-difference learning models for five financial instruments to provide trading signals. The instruments used are two foreign exchange pairs (GBPUSD and EURUSD), two indices (DE40 and FTSE100), and one commodity (XAUUSD). The performances of these 15 agents are evaluated through backtesting simulation, and successful models proceed through to forward testing on a retail trading platform. The results prove potential but require further minimal modifications for consistently profitable trading to fully handle retail trading costs, slippage, and spread fluctuation.

Robert Stok, Paul Bilokon

Calculating true volatility is an essential task for option pricing and risk management. However, it is made difficult by market microstructure noise. Particle filtering has been proposed to solve this problem as it favorable statistical properties, but relies on assumptions about underlying market dynamics. Machine learning methods have also been proposed but lack interpretability, and often lag in performance. In this paper we implement the SV-PF-RNN: a hybrid neural network and particle filter architecture. Our SV-PF-RNN is designed specifically with stochastic volatility estimation in mind. We then show that it can improve on the performance of a basic particle filter.

Paul Bilokon, Oleksandr Bilokon, Saeed Amen

Recent advances in data science, machine learning, and artificial intelligence, such as the emergence of large language models, are leading to an increasing demand for data that can be processed by such models. While data sources are application-specific, and it is impossible to produce an exhaustive list of such data sources, it seems that a comprehensive, rather than complete, list would still benefit data scientists and machine learning experts of all levels of seniority. The goal of this publication is to provide just such an (inevitably incomplete) list -- or compendium -- of data sources across multiple areas of applications, including finance and economics, legal (laws and regulations), life sciences (medicine and drug discovery), news sentiment and social media, retail and ecommerce, satellite imagery, and shipping and logistics, and sports.

Paul Alexander Bilokon

Humans have created artificial intelligence (AI), not the other way around. This statement is deceptively obvious. In this note, we decided to challenge this statement as a small, lighthearted Gedankenexperiment. We ask a simple question: in a world driven by evolution by natural selection, would neural networks or humans be likely to evolve first? We compare the Solomonoff--Kolmogorov--Chaitin complexity of the two and find neural networks (even LLMs) to be significantly simpler than humans. Further, we claim that it is unnecessary for any complex human-made equipment to exist for there to be neural networks. Neural networks may have evolved as naturally occurring objects before humans did as a form of chemical reaction-based or enzyme-based computation. Now that we know that neural networks can pass the Turing test and suspect that they may be capable of superintelligence, we ask whether the natural evolution of neural networks could lead from pure evolution by natural selection to what we call evolution-bootstrapped simulation. The evolution of neural networks does not involve irreducible complexity; would easily allow irreducible complexity to exist in the evolution-bootstrapped simulation; is a falsifiable scientific hypothesis; and is independent of / orthogonal to the issue of intelligent design.

Méabh MacMahon, Woochang Hwang, Soorin Yim et al.

Drug repurposing provides an opportunity to redeploy drugs, which ideally are already approved for use in humans, for the treatment of other diseases. For example, the repurposing of dexamethasone and baricitinib has played a crucial role in saving patient lives during the ongoing SARS-CoV-2 pandemic. There remains a need to expand therapeutic approaches to prevent life-threatening complications in patients with COVID-19. Using an in silico approach based on structural similarity to drugs already in clinical trials for COVID-19, potential drugs were predicted for repurposing. For a subset of identified drugs with different targets to their corresponding COVID-19 clinical trial drug, a mechanism of action analysis was applied to establish whether they might have a role in inhibiting the replication of SARS-CoV-2. Of sixty drugs predicted in this study, two with the potential to inhibit SARS-CoV-2 replication were identified using mechanism of action analysis. Triamcinolone is a corticosteroid that is structurally similar to dexamethasone; gallopamil is a calcium channel blocker that is structurally similar to verapamil. In silico approaches indicate possible mechanisms of action for both drugs in inhibiting SARS-CoV-2 replication. The identification of these drugs as potentially useful for patients with COVID-19 who are at a higher risk of developing severe disease supports the use of in silico approaches to facilitate quick and cost-effective drug repurposing. Such drugs could expand the number of treatments available to patients who are not protected by vaccination.