Dynamic mode decomposition for financial trading strategies

DOI10.1080/14697688.2016.1170194zbMATH Open1400.91558arXiv1508.04487OpenAlexW1635210704MaRDI QIDQ4554232FDOQ4554232

J. N. Kutz, Jordan Mann

Publication date: 13 November 2018

Published in: Quantitative Finance (Search for Journal in Brave)

Abstract: We demonstrate the application of an algorithmic trading strategy based upon the recently developed dynamic mode decomposition (DMD) on portfolios of financial data. The method is capable of characterizing complex dynamical systems, in this case financial market dynamics, in an equation-free manner by decomposing the state of the system into low-rank terms whose temporal coefficients in time are known. By extracting key temporal coherent structures (portfolios) in its sampling window, it provides a regression to a best fit linear dynamical system, allowing for a predictive assessment of the market dynamics and informing an investment strategy. The data-driven analytics capitalizes on stock market patterns, either real or perceived, to inform buy/sell/hold investment decisions. Critical to the method is an associated learning algorithm that optimizes the sampling and prediction windows of the algorithm by discovering trading hot-spots. The underlying mathematical structure of the algorithms is rooted in methods from nonlinear dynamical systems and shows that the decomposition is an effective mathematical tool for data-driven discovery of market patterns.

Full work available at URL: https://arxiv.org/abs/1508.04487

Recommendations

• Empirical mode decomposition of financial data
• Trading strategies generated by Lyapunov functions
• Towards a nonlinear trading strategy for financial time series
• The adaptive Fourier decomposition for financial time series
• Structural clustering of volatility regimes for dynamic trading strategies
• Neuro-dynamic trading methods
• A multiscale model of high-frequency trading
• Modelling the Dynamic Dependence Structure in Multivariate Financial Time Series

zbMATH Keywords

dynamical systemsequation-freedynamic mode decompositionKoopman operatorfinancial trading

Mathematics Subject Classification ID

Portfolio theory (91G10) Local and nonlocal bifurcation theory for dynamical systems (37G99) Low-dimensional dynamical systems (37E99) Special approximation methods (nonlinear Galerkin, etc.) for infinite-dimensional dissipative dynamical systems (37L65)

Cites Work

• Compressive Sensing and Low-Rank Libraries for Classification of Bifurcation Regimes in Nonlinear Dynamical Systems
• Dynamic mode decomposition of numerical and experimental data
• Spectral analysis of nonlinear flows
• Analysis of Fluid Flows via Spectral Properties of the Koopman Operator
• Thou shalt buy and hold
• Spectral Analysis for Physical Applications
• Pairs trading
• Title not available (Why is that?)
• Basket trading under co-integration with the logistic mixture autoregressive model
• Identifying small mean-reverting portfolios
• Variants of dynamic mode decomposition: boundary condition, Koopman, and Fourier analyses
• On dynamic mode decomposition: theory and applications
• Dynamic mode decomposition with control
• Compressive sensing based machine learning strategy for characterizing the flow around a cylinder with limited pressure measurements
• Compressed sensing and dynamic mode decomposition
• A kernel-based method for data-driven Koopman spectral analysis
• Applications of the dynamic mode decomposition
• Title not available (Why is that?)
• A dynamic analysis of moving average rules
• Title not available (Why is that?)
• Hamiltonian Systems and Transformation in Hilbert Space
• Statistical arbitrage in the US equities market
• Short-term market reaction after extreme price changes of liquid stocks
• Risk and Financial Management
• A computational definition of financial randomness
• Towards a nonlinear trading strategy for financial time series

Cited In (21)

• Study of the thermo-magneto-hydrodynamic flow of micropolar-nanofluid in square enclosure using dynamic mode decomposition and proper orthogonal decomposition
• A multidimensional data-driven sparse identification technique: the sparse proper generalized decomposition
• Time-series forecasting using manifold learning, radial basis function interpolation, and geometric harmonics
• The spatiotemporal coupling in delay-coordinates dynamic mode decomposition
• Time Series Source Separation Using Dynamic Mode Decomposition
• Graph embedded dynamic mode decomposition for stock price prediction
• Cusum techniques for technical trading in financial markets
• Correcting noisy dynamic mode decomposition with Kalman filters
• Trading strategies generated by Lyapunov functions
• Neural dynamic mode decomposition for end-to-end modeling of nonlinear dynamics
• Centering Data Improves the Dynamic Mode Decomposition
• Rigorous data‐driven computation of spectral properties of Koopman operators for dynamical systems
• Dynamic mode decomposition: an alternative algorithm for full-rank datasets
• Phase-amplitude reduction of transient dynamics far from attractors for limit-cycling systems
• High-dimensional time series prediction using kernel-based koopman mode regression
• Machine learning methods for reduced order modeling
• Modern Koopman Theory for Dynamical Systems
• Prediction Accuracy of Dynamic Mode Decomposition
• The mpEDMD Algorithm for Data-Driven Computations of Measure-Preserving Dynamical Systems
• Data-Driven Reduced Model Construction with Time-Domain Loewner Models
• Airfoil self-noise prediction using deep neural networks

Uses Software

• sapa

This page was built for publication: Dynamic mode decomposition for financial trading strategies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4554232)