Application Research of Spline Interpolation and ARIMA in the Field of Stock Market Forecasting ArXiv ID: 2311.10759 “View on arXiv” Authors: Unknown Abstract The ARIMA (Autoregressive Integrated Moving Average model) has extensive applications in the field of time series forecasting. However, the predictive performance of the ARIMA model is limited when dealing with data gaps or significant noise. Based on previous research, we have found that cubic spline interpolation performs well in capturing the smooth changes of stock price curves, especially when the market trends are relatively stable. Therefore, this paper integrates the two approaches by taking the time series data in stock trading as an example, establishes a time series forecasting model based on cubic spline interpolation and ARIMA. Through validation, the model has demonstrated certain guidance and reference value for short-term time series forecasting. ...

Natural Language Processing for Financial Regulation ArXiv ID: 2311.08533 “View on arXiv” Authors: Unknown Abstract This article provides an understanding of Natural Language Processing techniques in the framework of financial regulation, more specifically in order to perform semantic matching search between rules and policy when no dataset is available for supervised learning. We outline how to outperform simple pre-trained sentences-transformer models using freely available resources and explain the mathematical concepts behind the key building blocks of Natural Language Processing. ...

A Gaussian Process Based Method with Deep Kernel Learning for Pricing High-dimensional American Options ArXiv ID: 2311.07211 “View on arXiv” Authors: Unknown Abstract In this work, we present a novel machine learning approach for pricing high-dimensional American options based on the modified Gaussian process regression (GPR). We incorporate deep kernel learning and sparse variational Gaussian processes to address the challenges traditionally associated with GPR. These challenges include its diminished reliability in high-dimensional scenarios and the excessive computational costs associated with processing extensive numbers of simulated paths Our findings indicate that the proposed method surpasses the performance of the least squares Monte Carlo method in high-dimensional scenarios, particularly when the underlying assets are modeled by Merton’s jump diffusion model. Moreover, our approach does not exhibit a significant increase in computational time as the number of dimensions grows. Consequently, this method emerges as a potential tool for alleviating the challenges posed by the curse of dimensionality. ...

Error Analysis of Option Pricing via Deep PDE Solvers: Empirical Study ArXiv ID: 2311.07231 “View on arXiv” Authors: Unknown Abstract Option pricing, a fundamental problem in finance, often requires solving non-linear partial differential equations (PDEs). When dealing with multi-asset options, such as rainbow options, these PDEs become high-dimensional, leading to challenges posed by the curse of dimensionality. While deep learning-based PDE solvers have recently emerged as scalable solutions to this high-dimensional problem, their empirical and quantitative accuracy remains not well-understood, hindering their real-world applicability. In this study, we aimed to offer actionable insights into the utility of Deep PDE solvers for practical option pricing implementation. Through comparative experiments, we assessed the empirical performance of these solvers in high-dimensional contexts. Our investigation identified three primary sources of errors in Deep PDE solvers: (i) errors inherent in the specifications of the target option and underlying assets, (ii) errors originating from the asset model simulation methods, and (iii) errors stemming from the neural network training. Through ablation studies, we evaluated the individual impact of each error source. Our results indicate that the Deep BSDE method (DBSDE) is superior in performance and exhibits robustness against variations in option specifications. In contrast, some other methods are overly sensitive to option specifications, such as time to expiration. We also find that the performance of these methods improves inversely proportional to the square root of batch size and the number of time steps. This observation can aid in estimating computational resources for achieving desired accuracies with Deep PDE solvers. ...

Optimal portfolio allocation with uncertain covariance matrix ArXiv ID: 2311.07478 “View on arXiv” Authors: Unknown Abstract In this paper, we explore the portfolio allocation problem involving an uncertain covariance matrix. We calculate the expected value of the Constant Absolute Risk Aversion (CARA) utility function, marginalized over a distribution of covariance matrices. We show that marginalization introduces a logarithmic dependence on risk, as opposed to the linear dependence assumed in the mean-variance approach. Additionally, it leads to a decrease in the allocation level for higher uncertainties. Our proposed method extends the mean-variance approach by considering the uncertainty associated with future covariance matrices and expected returns, which is important for practical applications. ...

Revisiting Cont’s Stylized Facts for Modern Stock Markets ArXiv ID: 2311.07738 “View on arXiv” Authors: Unknown Abstract In 2001, Rama Cont introduced a now-widely used set of ‘stylized facts’ to synthesize empirical studies of financial price changes (returns), resulting in 11 statistical properties common to a large set of assets and markets. These properties are viewed as constraints a model should be able to reproduce in order to accurately represent returns in a market. It has not been established whether the characteristics Cont noted in 2001 still hold for modern markets following significant regulatory shifts and technological advances. It is also not clear whether a given time series of financial returns for an asset will express all 11 stylized facts. We test both of these propositions by attempting to replicate each of Cont’s 11 stylized facts for intraday returns of the individual stocks in the Dow 30, using the same authoritative data as that used by the U.S. regulator from October 2018 - March 2019. We find conclusive evidence for eight of Cont’s original facts and no support for the remaining three. Our study represents the first test of Cont’s 11 stylized facts against a consistent set of stocks, therefore providing insight into how these stylized facts should be viewed in the context of modern stock markets. ...

Dynamic portfolio selection for nonlinear law-dependent preferences ArXiv ID: 2311.06745 “View on arXiv” Authors: Unknown Abstract This paper addresses the portfolio selection problem for nonlinear law-dependent preferences in continuous time, which inherently exhibit time inconsistency. Employing the method of stochastic maximum principle, we establish verification theorems for equilibrium strategies, accommodating both random market coefficients and incomplete markets. We derive the first-order condition (FOC) for the equilibrium strategies, using a notion of functional derivatives with respect to probability distributions. Then, with the help of the FOC we obtain the equilibrium strategies in closed form for two classes of implicitly defined preferences: CRRA and CARA betweenness preferences, with deterministic market coefficients. Finally, to show applications of our theoretical results to problems with random market coefficients, we examine the weighted utility. We reveal that the equilibrium strategy can be described by a coupled system of Quadratic Backward Stochastic Differential Equations (QBSDEs). The well-posedness of this system is generally open but is established under the special structures of our problem. ...

Portfolio diversification with varying investor abilities ArXiv ID: 2311.06519 “View on arXiv” Authors: Unknown Abstract We introduce new mathematical methods to study the optimal portfolio size of investment portfolios over time, considering investors with varying skill levels. First, we explore the benefit of portfolio diversification on an annual basis for poor, average and strong investors defined by the 10th, 50th and 90th percentiles of risk-adjusted returns, respectively. Second, we conduct a thorough regression experiment examining quantiles of risk-adjusted returns as a function of portfolio size across investor ability, testing for trends and curvature within these functions. Finally, we study the optimal portfolio size for poor, average and strong investors in a continuously temporal manner using more than 20 years of data. We show that strong investors should hold concentrated portfolios, poor investors should hold diversified portfolios; average investors have a less obvious distribution with the optimal number varying materially over time. ...

Relative entropy-regularized robust optimal order execution ArXiv ID: 2311.06476 “View on arXiv” Authors: Unknown Abstract The problem of order execution is cast as a relative entropy-regularized robust optimal control problem in this article. The order execution agent’s goal is to maximize an objective functional associated with his profit-and-loss of trading and simultaneously minimize the execution risk and the market’s liquidity and uncertainty. We model the market’s liquidity and uncertainty by the principle of least relative entropy associated with the market volume. The problem of order execution is made into a relative entropy-regularized stochastic differential game. Standard argument of dynamic programming yields that the value function of the differential game satisfies a relative entropy-regularized Hamilton-Jacobi-Isaacs (rHJI) equation. Under the assumptions of linear-quadratic model with Gaussian prior, the rHJI equation reduces to a system of Riccati and linear differential equations. Further imposing constancy of the corresponding coefficients, the system of differential equations can be solved in closed form, resulting in analytical expressions for optimal strategy and trajectory as well as the posterior distribution of market volume. Numerical examples illustrating the optimal strategies and the comparisons with conventional trading strategies are conducted. ...

Withdrawal Success Optimization ArXiv ID: 2311.06665 “View on arXiv” Authors: Unknown Abstract For $n$ assets and discrete-time rebalancing, the probability to complete a given schedule of investments and withdrawals is maximized over progressively measurable portfolio weight functions. Applications consider two assets, namely the S&P Composite Index and an inflation-protected bond. The maximum probability and optimal portfolio weight functions are computed for annually rebalanced schedules involving an arbitrary initial investment and then equal annual withdrawals over the remainder of the time period. Applications also consider annually rebalanced schedules that start with dollar cost averaging (equal annual investments) and then shift to equal annual withdrawals. Results indicate noticeable improvements in the probability to complete a given schedule when optimal portfolio weights are used instead of constant portfolio weights like the standard of keeping 90% in the S&P Composite Index and 10% in inflation-protected bonds. ...