@article {Franco-Pedroso55, author = {Javier Franco-Pedroso and Joaquin Gonzalez-Rodriguez and Jorge Cubero and Maria Planas and Rafael Cobo and Fernando Pablos}, title = {Generating Virtual Scenarios of Multivariate Financial Data for Quantitative Trading Applications}, volume = {1}, number = {2}, pages = {55--77}, year = {2019}, doi = {10.3905/jfds.2019.1.003}, publisher = {Institutional Investor Journals Umbrella}, abstract = {In this article, the authors present a novel approach to the generation of virtual scenarios of multivariate financial data of arbitrary length and composition of assets. With this approach, decades of realistic time-synchronized data can be simulated for a large number of assets, producing diverse scenarios to test and improve quantitative investment strategies. The authors{\textquoteright} approach is based on the analysis and synthesis of the time-dependent individual and joint characteristics of real financial time series, using stochastic sequences of market trends to draw multivariate returns from time-dependent probability functions that preserve both distributional properties of asset returns and time-dependent correlation among time series. Moreover, new time-synchronized assets can be arbitrarily generated through a principal component analysis{\textendash}based procedure to obtain any number of assets in the final virtual scenario. The validation of such a simulation is tested with an extensive set of measurements and shows a significant degree of agreement with the reference performance of real financial series{\textemdash}better than that obtained with other classical and state-of-the-art approaches.TOPICS: Simulations, performance measurement}, issn = {2640-3943}, URL = {https://jfds.pm-research.com/content/1/2/55}, eprint = {https://jfds.pm-research.com/content/1/2/55.full.pdf}, journal = {The Journal of Financial Data Science} }