Signature Methods in Finance

Inhaltsverzeichnis

1. Frontmatter

   PDF-Version jetzt herunterladen

2. Introduction to Signatures in Machine Learning

   1. Frontmatter

   2. A Primer on the Signature Method in Machine Learning

      • Open Access

      Ilya Chevyrev, Andrey Kormilitzin

      Abstract

      We provide an introduction to the signature method, focusing on its theoretical properties and machine learning applications. Our presentation is divided into two parts. In the first part, we present the definition and fundamental properties of the signature of a path. The signature is a sequence of numbers associated with a path that captures many of its important analytic and geometric properties. As a sequence of numbers, the signature serves as a compact description (dimension reduction) of a path. In presenting its theoretical properties, we assume only familiarity with classical real analysis and integration, and supplement theory with straightforward examples. We also mention several advanced topics, including the role of the signature in rough path theory. In the second part, we present practical applications of the signature to the area of machine learning. The signature method is a non-parametric way of transforming data into a set of features that can be used in machine learning tasks. In this method, data are converted into multi-dimensional paths, by means of embedding algorithms, of which the signature is then computed. We describe this pipeline in detail, making a link with the properties of the signature presented in the first part. We furthermore review some of the developments of the signature method in machine learning and, as an illustrative example, present a detailed application of the method to handwritten digit classification.

      PDF-Version jetzt herunterladen

   3. An Introduction to Tensors for Path Signatures

      • Open Access

      Jack Beda, Gonçalo dos Reis, Nikolas Tapia

      Abstract

      We present a fit-for-purpose introduction to tensors and their operations. It is envisaged to help the reader become acquainted with its underpinning concepts for the study of path signatures. The text includes exercises, solutions and many intuitive explanations. The material discusses direct sums and tensor products as two possible operations that make the Cartesian product of vectors spaces a vector space. The difference lies in linear vs. multilinear structures—the latter being the suitable one to deal with path signatures. The presentation is offered to understand tensors in a sense deeper than just a multidimensional array. The text concludes with the prime example of an algebra in relation to path signatures: the tensor algebra.

      PDF-Version jetzt herunterladen

   4. The Signature Kernel

      • Open Access

      Darrick Lee, Harald Oberhauser

      Abstract

      The signature kernel is a positive definite kernel for sequential data. It inherits theoretical guarantees from stochastic analysis, has efficient algorithms for computation, and shows strong empirical performance. In this chapter, we provide an introduction to the signature kernel by highlighting the analytic connection between the path signature and ordinary monomials. In particular, both the classical monomials and the path signature are universal and characteristic on compact domains: they can approximate functions, and characterize probability measures. However, issues arise in practice due to unbounded domains, computational complexity, and non-robustness. We show that these issues can be avoided via kernelization and robustification. To address the computational complexity, we provide an overview of the kernel trick: algorithms to efficiently compute the signature kernel which avoid direct computations of the signature. Furthermore, the signature kernel is highly flexible, and provides a canonical way to turn a given kernel on any domain into a kernel for sequences in that domain, while retaining its theoretical and computational properties. Finally, we survey applications and recent developments of the signature kernel.

      PDF-Version jetzt herunterladen

3. Applications of Signatures

   1. Frontmatter

   2. Market Generators: A Paradigm Shift in Financial Modeling

      • Open Access

      Blanka Horvath, Jonathan Plenk, Milena Vuletić

      Abstract

      Market Generators are a rapidly evolving class of neural-network-based models to simulate financial market behavior, offering a powerful alternative to classical stochastic models. These deep learning models are trained to encode the underlying distribution of financial data and generate new synthetic market scenarios from the learned distribution. Though the expressions “Market Generator” and its related form “Market Simulator” have only entered the vocabulary of financial modeling around 2019, by today, the modeling techniques related to them have already grown into an area in their own right. This growing interest is matched by a dramatic rise in research, publications and an accelerating rate of innovation in the ambient technological arena of generative modeling. Recently, this trend has culminated in the emergence of large generative networks, particularly GPT-type language models, which are proving to be driving one of the biggest disruptions in the history of technology.

      PDF-Version jetzt herunterladen

   3. Signature Maximum Mean Discrepancy Two-Sample Statistical Tests

      • Open Access

      Andrew Alden, Blanka Horvath, Zacharia Issa

      Abstract

      Maximum Mean Discrepancy (MMD) is a widely used concept in machine learning research which has gained popularity in recent years as a highly effective tool for comparing (finite-dimensional) distributions. Since it is designed as a kernel-based method, the MMD can be extended to path space valued distributions using the signature kernel. The resulting signature MMD (sig-MMD) can be used to define a metric between distributions on path space. Similarly to the original use case of the MMD as a test statistic within a two-sample testing framework, the sig-MMD can be applied to determine if two sets of paths are drawn from the same stochastic process. This chapter is dedicated to understanding the possibilities and challenges associated with applying the sig-MMD as a statistical tool in practice. We introduce and explain the sig-MMD, and provide easily accessible and verifiable examples for its practical use. We present examples that can lead to Type 2 errors in the hypothesis test, falsely indicating that samples have been drawn from the same underlying process (which generally occurs in a limited data setting). We then present techniques to mitigate the occurrence of this type of error.

      PDF-Version jetzt herunterladen

   4. Signature and the Functional Taylor Expansion

      • Open Access

      Bruno Dupire, Valentin Tissot-Daguette

      Abstract

      This chapter links the path signature to the functional Itô calculus (Dupire, Functional Itô calculus. SSRN (2009). Republished in Quantitative Finance 19(5), 721–729, 2019). The junction is the functional Taylor expansion (FTE), discussed in Sect. 5, which is a powerful tool to approximate functionals after an observed path.

      In particular, the FTE decomposes the functional from future scenarios. In risk analysis, the FTE leads to new Greeks, one of particular importance being the Lie bracket between the space and time functional derivatives, which we call Libra. Once paired with the Lévy area, the Libra can be used to speed up the computation of risk measures such as Value at Risk and Expected Shortfall as explained in Sect. 6.1. In Sect. 6.3, we explain how the FTE can quantify the hedging error of replicating portfolios in a robust manner. In the context of financial derivatives, we demonstrate in Sect. 6.4 how the FTE generates approximations of exotic payoffs. The relevance of the FTE for cubature methods is finally outlined in Sect. 6.5.

      PDF-Version jetzt herunterladen

   5. Signature-Based Models in Finance

      • Open Access

      Christa Cuchiero, Guido Gazzani, Janka Möller, Sara Svaluto-Ferro

      Abstract

      We consider two classes of asset price models where either the price or the volatility dynamics are described by a linear function of the (time extended) signature of a primary process, in general a multidimensional continuous semimartingale. These model classes are universal in the sense that classical models can be approximated arbitrarily well or are simply nested in our setup. Under the additional assumption that the primary process is polynomial, we obtain tractable option pricing formulas for so-called sig-payoffs in the first class and closed form expressions for the VIX squared and the log-price in the second one. In both cases the signature samples can be easily precomputed, hence the calibration task can be split into an offline sampling and a standard optimization. We present several applications, in particular the successfully solved joint SPX/VIX calibration problem.

      PDF-Version jetzt herunterladen

   6. Signature Trading Strategies

      • Open Access

      Owen Futter, Magnus Wiese

      Abstract

      In this chapter, the primary objective is to recall the concept of a trading strategy and to extend this concept to the setting of signatures. We discuss how one can extend classical methods of optimal trading by tackling stochastic control problems through the lens of signatures, in order to incorporate path-dependencies. First introduced in (Signatures in machine learning and finance. PhD thesis, University of Oxford, 2020), the notion of a signature trading strategy allows to solve path-dependent optimization problems in a simple and explicit way. We first outline the key concepts of signature trading and highlight its associated benefits. Additionally, we present a solution to the mean-variance criterion and illustrate the advantages of signature-based methods using intuitive examples. Finally, we explore how signature trading strategies can be applied to obtain approximate solutions to optimal execution problems.

      PDF-Version jetzt herunterladen

   7. Optimal Stopping for Non-Markovian Asset Price Processes

      • Open Access

      Christian Bayer, Paul P. Hager, Sebastian Riedel

      Abstract

      Some of the most liquidly traded options in equity markets are American and Bermudan options, whose owner may choose the option’s exercise date—within a certain range. Hence, these options are optimal stopping problems from a mathematical perspective. There is a huge literature on solving optimal stopping problems, and most of the prevalent methods (e.g., solving the Hamilton-Jacobi-Bellman PDE, least squares Monte Carlo, dual martingale methods) strongly rely on the Markov property for the underlying dynamics, to avoid the curse of dimensionality. In this chapter, we will show how the signature can be used to adopt classical, Markovian numerical methods for the non-Markovian case.

      PDF-Version jetzt herunterladen

   8. Adapted Topologies and Higher-Rank Signatures

      • Open Access

      Chong Liu, Gudmund Pammer

      Abstract

      Two stochastic processes can have similar laws but yield a vastly different outcome in applications such as optimal stopping or stochastic programming. The reason is that the usual weak topology does not account for the different available information in time that is stored in the filtration of the underlying process. To address the resulting discontinuities, Aldous introduced the extended weak topology, and subsequently, Hoover and Keisler showed that both, weak topology as well as extended weak topology, are just the first two topologies in a sequence of the so-called adapted weak topologies that get increasingly finer. In this short survey, we give a brief introduction to the recent advances of the applications of signature theory, in particular the higher-rank (expected) signatures, in adapted weak topologies and related fields, and highlight theoretical and computational properties.

      PDF-Version jetzt herunterladen

   9. On Expected Signatures and Signature Cumulants in Semimartingale Models

      • Open Access

      Peter K. Friz, Paul P. Hager, Nikolas Tapia

      Abstract

      The signature transform, a Cartan type development, translates paths into high-dimensional feature vectors, capturing their intrinsic characteristics. Under natural conditions, the expectation of the signature determines the law of the signature, providing a statistical summary of the data distribution. This property facilitates robust modeling and inference in machine learning and stochastic processes. Building on previous work by the present authors (Friz et al., Unified signature cumulants and generalized Magnus expansions. In Forum of Mathematics, Sigma, vol. 10, p. e42, 2022) we here revisit the actual computation of expected signatures, in a general semimartingale setting. Several new formulae are given. A log-transform of (expected) signatures leads to log-signatures (signature cumulants), offering a significant reduction in complexity.

      PDF-Version jetzt herunterladen