Figure 7 - uploaded by Arturo Cifuentes
Content may be subject to copyright.
Context in source publication
Context 1
... optimization model to decide the asset allocation weights is run once a year (in January), based on 5-year lookback periods. In essence, the optimization is based on a sequence of overlapping windows as shown in figure 7. Hence, the first optimization is based on data from the January 2003-December 2007 period. ...
Similar publications
This study explores the intricacies of asset allocation-a critical component of investment strategy that involves the distribution of capital across different asset classes such as stocks, bonds, and cash equivalents. Central to our investigation is the application of Deep Reinforcement Learning (Deep RL), a cutting-edge machine learning technique...
As a core business strategy, sustainability has become increasingly important in today’s rapidly evolving world. The improvement of a firm’s total factor productivity (TFP) is necessary for the realization of sustainable development. The wide variation in the types and sizes of China’s firms can reflect the differences in financial capital allocati...
This study focuses on efficient asset allocations that properly include T-bills, T-bonds, and the S&P 500 stock index. It checks that their annual real rates of linear return are both normal and almost lognormal. It reexamines how efficient portfolios based on the rates of linear return may turn into efficient portfolios based on the rates of logar...
China faces a structural-demographic crisis characterized by low fertility rates, an aging population, and ecological imbalances. Despite policy interventions, fertility intentions remain a concern. This study explores the complex relationship between household financial asset allocation and fertility intentions using CFPS data. The findings reveal...
We build a state-of-the-art dynamic model of private asset allocation that considers five key features of private asset markets: (1) the illiquid nature of private assets, (2) timing lags between capital commitments, capital calls, and eventual distributions, (3) time-varying business cycle conditions, (4) serial correlation in observed private ass...
Citations
... The findings suggest that synthetic credit data can be a useful resource for financial big data training programs, with potential applications in risk assessment and credit scoring. 9 Ramirez et al. (48) Asset allocation and portfolio optimization in public markets. ...
Generative Adversarial Networks (GANs) have emerged as a promising solution for machine learning and artificial intelligence algorithms constrained by data availability and accessibility. Financial markets, alongside healthcare, present significant challenges due to data privacy and confidentiality concerns. GANs enable researchers to generate synthetic financial data that closely mirrors real-world datasets, facilitating advancements in market analysis and modeling. Despite their potential, a comprehensive evaluation of GAN-based financial data generation remains limited, necessitating a systematic assessment of existing methodologies and findings. This paper presents a systematic review of GAN architectures applied to financial data generation and market modeling. Our study is distinguished by its comprehensive exploration of various GAN variants and their specific applications within different facets of financial markets, including stock price prediction, algorithmic trading, portfolio optimization, risk management, and fraud detection. Leveraging thirty relevant papers from four major databases (IEEE Xplore, Web of Science, Scopus, and arXiv), we synthesized key findings, identify challenges, and highlight limitations in the application of GANs for financial data generation. Our findings reveal that while GANs enhance data privacy and accessibility, they also face limitations such as mode collapse, instability during training, and regulatory concerns in financial markets. This qualitative review provides valuable insights for researchers and stakeholders, offering a foundation for future studies and innovative applications of GANs in financial markets.
... In terms of deep probabilistic modeling of financial time series, prior work has applied deep learning approaches to model a single financial time series (e.g., [4,31]), or multivariate time series (e.g., [21,25,27,28,32]). Of this work, Tepelyan and Gopal [28] (BDG 1 ) were the first to scale up to hundreds of stocks through combining machine learning with factor modeling, specifically Fama-French factor modeling. ...
... Mean and Covariance. Unlike prior work that has worked on multivariate generative modeling (e.g., [21,25,27,28,32])), our model is able to compute the mean ( + ) and the covariance matrix without sampling (Σ + Σ ) leading to significant speedup during inference. ...
The use of machine learning for statistical modeling (and thus, generative modeling) has grown in popularity with the proliferation of time series models, text-to-image models, and especially large language models. Fundamentally, the goal of classical factor modeling is statistical modeling of stock returns, and in this work, we explore using deep generative modeling to enhance classical factor models. Prior work has explored the use of deep generative models in order to model hundreds of stocks, leading to accurate risk forecasting and alpha portfolio construction; however, that specific model does not allow for easy factor modeling interpretation in that the factor exposures cannot be deduced. In this work, we introduce NeuralFactors, a novel machine-learning based approach to factor analysis where a neural network outputs factor exposures and factor returns, trained using the same methodology as variational autoencoders. We show that this model outperforms prior approaches both in terms of log-likelihood performance and computational efficiency. Further, we show that this method is competitive to prior work in generating realistic synthetic data, covariance estimation, risk analysis (e.g., value at risk, or VaR, of portfolios), and portfolio optimization. Finally, due to the connection to classical factor analysis, we analyze how the factors our model learns cluster together and show that the factor exposures could be used for embedding stocks.
