Optimal Execution Using Reinforcement Learning ArXiv ID: 2306.17178 “View on arXiv” Authors: Unknown Abstract This work is about optimal order execution, where a large order is split into several small orders to maximize the implementation shortfall. Based on the diversity of cryptocurrency exchanges, we attempt to extract cross-exchange signals by aligning data from multiple exchanges for the first time. Unlike most previous studies that focused on using single-exchange information, we discuss the impact of cross-exchange signals on the agent’s decision-making in the optimal execution problem. Experimental results show that cross-exchange signals can provide additional information for the optimal execution of cryptocurrency to facilitate the optimal execution process. ...

Temporal Data Meets LLM – Explainable Financial Time Series Forecasting ArXiv ID: 2306.11025 “View on arXiv” Authors: Unknown Abstract This paper presents a novel study on harnessing Large Language Models’ (LLMs) outstanding knowledge and reasoning abilities for explainable financial time series forecasting. The application of machine learning models to financial time series comes with several challenges, including the difficulty in cross-sequence reasoning and inference, the hurdle of incorporating multi-modal signals from historical news, financial knowledge graphs, etc., and the issue of interpreting and explaining the model results. In this paper, we focus on NASDAQ-100 stocks, making use of publicly accessible historical stock price data, company metadata, and historical economic/financial news. We conduct experiments to illustrate the potential of LLMs in offering a unified solution to the aforementioned challenges. Our experiments include trying zero-shot/few-shot inference with GPT-4 and instruction-based fine-tuning with a public LLM model Open LLaMA. We demonstrate our approach outperforms a few baselines, including the widely applied classic ARMA-GARCH model and a gradient-boosting tree model. Through the performance comparison results and a few examples, we find LLMs can make a well-thought decision by reasoning over information from both textual news and price time series and extracting insights, leveraging cross-sequence information, and utilizing the inherent knowledge embedded within the LLM. Additionally, we show that a publicly available LLM such as Open-LLaMA, after fine-tuning, can comprehend the instruction to generate explainable forecasts and achieve reasonable performance, albeit relatively inferior in comparison to GPT-4. ...

Detecting Depegs: Towards Safer Passive Liquidity Provision on Curve Finance ArXiv ID: 2306.10612 “View on arXiv” Authors: Unknown Abstract We consider a liquidity provider’s (LP’s) exposure to stablecoin and liquid staking derivative (LSD) depegs on Curve’s StableSwap pools. We construct a suite of metrics designed to detect potential asset depegs based on price and trading data. Using our metrics, we fine-tune a Bayesian Online Changepoint Detection (BOCD) algorithm to alert LPs of potential depegs before or as they occur. We train and test our changepoint detection algorithm against Curve LP token prices for 13 StableSwap pools throughout 2022 and 2023, focusing on relevant stablecoin and LSD depegs. We show that our model, trained on 2022 UST data, is able to detect the USDC depeg in March of 2023 at 9pm UTC on March 10th, approximately 5 hours before USDC dips below 99 cents, with few false alarms in the 17 months on which it is tested. Finally, we describe how this research may be used by Curve’s liquidity providers, and how it may be extended to dynamically de-risk Curve pools by modifying parameters in anticipation of potential depegs. This research underpins an API developed to alert Curve LPs, in real-time, when their positions might be at risk. ...

Machine Learning and Hamilton-Jacobi-Bellman Equation for Optimal Decumulation: a Comparison Study ArXiv ID: 2306.10582 “View on arXiv” Authors: Unknown Abstract We propose a novel data-driven neural network (NN) optimization framework for solving an optimal stochastic control problem under stochastic constraints. Customized activation functions for the output layers of the NN are applied, which permits training via standard unconstrained optimization. The optimal solution yields a multi-period asset allocation and decumulation strategy for a holder of a defined contribution (DC) pension plan. The objective function of the optimal control problem is based on expected wealth withdrawn (EW) and expected shortfall (ES) that directly targets left-tail risk. The stochastic bound constraints enforce a guaranteed minimum withdrawal each year. We demonstrate that the data-driven approach is capable of learning a near-optimal solution by benchmarking it against the numerical results from a Hamilton-Jacobi-Bellman (HJB) Partial Differential Equation (PDE) computational framework. ...

Quantum computer based Feature Selection in Machine Learning ArXiv ID: 2306.10591 “View on arXiv” Authors: Unknown Abstract The problem of selecting an appropriate number of features in supervised learning problems is investigated in this paper. Starting with common methods in machine learning, we treat the feature selection task as a quadratic unconstrained optimization problem (QUBO), which can be tackled with classical numerical methods as well as within a quantum computing framework. We compare the different results in small-sized problem setups. According to the results of our study, whether the QUBO method outperforms other feature selection methods depends on the data set. In an extension to a larger data set with 27 features, we compare the convergence behavior of the QUBO methods via quantum computing with classical stochastic optimization methods. Due to persisting error rates, the classical stochastic optimization methods are still superior. ...

Stock Price Prediction using Dynamic Neural Networks ArXiv ID: 2306.12969 “View on arXiv” Authors: Unknown Abstract This paper will analyze and implement a time series dynamic neural network to predict daily closing stock prices. Neural networks possess unsurpassed abilities in identifying underlying patterns in chaotic, non-linear, and seemingly random data, thus providing a mechanism to predict stock price movements much more precisely than many current techniques. Contemporary methods for stock analysis, including fundamental, technical, and regression techniques, are conversed and paralleled with the performance of neural networks. Also, the Efficient Market Hypothesis (EMH) is presented and contrasted with Chaos theory using neural networks. This paper will refute the EMH and support Chaos theory. Finally, recommendations for using neural networks in stock price prediction will be presented. ...

Testing for intrinsic multifractality in the global grain spot market indices: A multifractal detrended fluctuation analysis ArXiv ID: 2306.10496 “View on arXiv” Authors: Unknown Abstract Grains account for more than 50% of the calories consumed by people worldwide, and military conflicts, pandemics, climate change, and soaring grain prices all have vital impacts on food security. However, the complex price behavior of the global grain spot markets has not been well understood. A recent study performed multifractal moving average analysis (MF-DMA) of the Grains & Oilseeds Index (GOI) and its sub-indices of wheat, maize, soyabeans, rice, and barley and found that only the maize and barley sub-indices exhibit an intrinsic multifractal nature with convincing evidence. Here, we utilize multifractal fluctuation analysis (MF-DFA) to investigate the same problem. Extensive statistical tests confirm the presence of intrinsic multifractality in the maize and barley sub-indices and the absence of intrinsic multifractality in the wheat and rice sub-indices. Different from the MF-DMA results, the MF-DFA results suggest that there is also intrinsic multifractality in the GOI and soyabeans sub-indices. Our comparative analysis does not provide conclusive information about the GOI and soyabeans and highlights the high complexity of the global grain spot markets. ...

Successive one-sided Hodrick-Prescott filter with incremental filtering algorithm for nonlinear economic time series ArXiv ID: 2306.12439 “View on arXiv” Authors: Unknown Abstract We propose a successive one-sided Hodrick-Prescott (SOHP) filter from multiple time scale decomposition perspective to derive trend estimate for a time series. The idea is to apply the one-sided HP (OHP) filter recursively on the updated cyclical component to extract the trend residual on multiple time scales, thereby to improve the trend estimate. To address the issue of optimization with a moving horizon as that of the SOHP filter, we present an incremental HP filtering algorithm, which greatly simplifies the involved inverse matrix operation and reduces the computational demand of the basic HP filtering. Actually, the new algorithm also applies effectively to other HP-type filters, especially for large-size or expanding data scenario. Numerical examples on real economic data show the better performance of the SOHP filter in comparison with other known HP-type filters. ...

DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting ArXiv ID: 2306.09862 “View on arXiv” Authors: Unknown Abstract Stock trend forecasting is a fundamental task of quantitative investment where precise predictions of price trends are indispensable. As an online service, stock data continuously arrive over time. It is practical and efficient to incrementally update the forecast model with the latest data which may reveal some new patterns recurring in the future stock market. However, incremental learning for stock trend forecasting still remains under-explored due to the challenge of distribution shifts (a.k.a. concept drifts). With the stock market dynamically evolving, the distribution of future data can slightly or significantly differ from incremental data, hindering the effectiveness of incremental updates. To address this challenge, we propose DoubleAdapt, an end-to-end framework with two adapters, which can effectively adapt the data and the model to mitigate the effects of distribution shifts. Our key insight is to automatically learn how to adapt stock data into a locally stationary distribution in favor of profitable updates. Complemented by data adaptation, we can confidently adapt the model parameters under mitigated distribution shifts. We cast each incremental learning task as a meta-learning task and automatically optimize the adapters for desirable data adaptation and parameter initialization. Experiments on real-world stock datasets demonstrate that DoubleAdapt achieves state-of-the-art predictive performance and shows considerable efficiency. ...

The Chebyshev Polynomials Of The First Kind For Analysis Rates Shares Of Enterprises ArXiv ID: 2307.08465 “View on arXiv” Authors: Unknown Abstract Chebyshev polynomials of the first kind have long been used to approximate experimental data in solving various technical problems. Within the framework of this study, the dynamics of shares of eight Czech enterprises was analyzed by the Chebyshev polynomial decomposition: CEZ A.S. (CEZP), Colt CZ Group SE (CZG), Erste Bank (ERST), Komercni Banka (BKOM), Moneta Money Bank A.S. (MONET), Photon (PENP), Vienna insurance group (VIGR) in 2021. An investor, when making a decision to purchase a security , is guided largely by an heuristic approach . And variance and correlation are not observed by human senses. The vectors of decomposition of time series of exchange values of securities allow analyzing the dynamics of exchange values of securities more effectively if their dynamics does not correspond to the normal distribution law. The proposed model allows analyzing the dynamics of the exchange value of a securities portfolio without calculating variance and correlation. This model can be useful if the dynamics of the exchange values of securities does not obey, due to certain circumstances, the normal law of distribution. ...