In this article, we explore generative models in order to build a market generator. The underlying idea is to simulate artificial multi-dimensional financial time series, whose statistical properties are the same as those observed in the financial markets. In particular, these synthetic data must preserve the first four statistical moments (mean, standard deviation, skewness and kurtosis), the stochastic dependence between the different dimensions (copula structure) and across time (autocorrelation function). The first part of the article reviews the more relevant generative models, which are restricted Boltzmann machines, generative adversarial networks, and convolutional Wasserstein models. The second part of the article is dedicated to financial applications by considering the simulation of multidimensional times series and estimating the probability distribution of backtest statistics. The final objective is to develop a framework for improving the risk management of quantitative investment strategies.
- T. Rowe Price | What Makes an “Impact” Investment Manager
- Robeco | Value investing’s five principles that have stood the test of time
- BlackRock/iShares | Weekly commentary: Fed catches up with restart reality
- Amundi Asset Managers | Global Investment Views
- Northern Trust | 3 Takeaways from Fed Meeting
- Schroders | What do rising bond yields mean for the US stock market?
- State Street Global Advisors | Global Macro Policy Quarterly
- J.P. Morgan Asset Management | The Weekly Brief
- UBS Asset Management | Real Estate Outlook: Inflation protection desirable
- Nuveen | Treasury yields decline on Fed’s hawkish surprise