Stock-Index Tracking Optimization Using Auto-Encoders

Zhang, Chi; Liang, Shuang; Lyu, Fei; Fang, Libing

doi:10.3389/fphy.2020.00388

Cited by 17 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is a generative network structure based on a Gaussian mixed model that uses variational Bayesian inference (Goodfellow et al, 2016) [ 46 ]. In the fields of economics and finance, due to its powerful data generation capability, VAE is widely used for data synthesis (Koenecke and Varian, 2020) [ 47 ], time series forecasting (Jin et al, 2022) [ 48 ], big data processing (Sarduie et al, 2020) [ 49 ], risk management and control (Arian et al, 2020) [ 50 ], stock index tracking (Zhang et al, 2020) [ 51 ], education quality improvement (Wang et al, 2021) [ 52 ], etc.…”

Section: Data and Variablesmentioning

confidence: 99%

The role amenities play in spatial sorting of migrants and their impact on welfare: Evidence from China

Zhang

2023

PLoS ONE

View full text Add to dashboard Cite

From 2005 to 2015, China’s high-skilled labor was increasingly concentrated in cities with high wages and high rents, while a narrowing of the wage gap between high- and low-skilled labor showed an opposite trend to an increase in geographic sorting. In this research, I estimated a spatial equilibrium structural model to identify the causes of this phenomenon and its impact on welfare. Changes in local labor demand essentially led to an increase in skill sorting, and changes in urban amenities further contributed to this trend. An agglomeration of high-skilled labor raised local productivity, increased wages for all workers, reduced the real wage gap, and widened the welfare gap between workers with different skills. In contrast to the welfare effects of changes in the wage gap driven by exogenous productivity changes, changes in urban wages, rents, and amenities increased welfare inequality between high- and low-skilled workers, but this is mainly because the utility of low-skilled workers from urban amenities is constrained by migration costs; if migration costs caused by China’s household registration policy were eliminated, changes in urban wages, rents, and amenities would reduce welfare inequality between high- and low-skilled workers to a greater extent than a reduction in the real wage gap between these two groups.

show abstract

Section: Data and Variablesmentioning

confidence: 99%

The role amenities play in spatial sorting of migrants and their impact on welfare: Evidence from China

Zhang

2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…There are also important works on methods for stock selection, which have different foundations, from operations research methods (e.g., [18], [22]) to approaches originated in modern portfolio theory (mean-variance model) (e.g., [18], [23]) and soft computing methods (e.g., [16], [24]), including hybrid approaches (e.g., [17], [21], [53]).…”

Section: Stock Selectionmentioning

confidence: 99%

“…In [53], a fusion approach of a classifier, based on machine learning, with the SVM method and the main variance method, is proposed for portfolio selection. In [16], the authors propose the application of several autoencoder deep-learning architectures for selecting representative stocks from the index constituents.…”

Section: Stock Selectionmentioning

confidence: 99%

A Comprehensive Soft Computing-Based Approach to Portfolio Management by Discarding Undesirable Stocks

et al. 2022

View full text Add to dashboard Cite

Stock markets play a crucial role in modern society. Many individuals and organizations try to improve their performance in these markets by exploiting approaches that consider different types of factors. However, although there are great complexities involved, practitioners often use simplistic methodologies that neglect relevant features of the problem. That is, they leave out some activities that are essential to obtain better results in the related decision-making problem. Here, we propose to use a soft computing-based approach to comprehensively address the main activities of stock investments. We present a novel method for modeling expert knowledge through fuzzy logic that allows the investor to discard undesirable stocks (i.e., stocks that are not suitable for investment); thus, reducing computational complexity in the search process and likely improving the performance of the final stock portfolio. Extensive experiments allowed us to conclude that discarding undesirable stocks by exploiting the proposed method produces portfolios that outperform the benchmarks. Therefore, the proposal is a promising alternative to complement current approaches.

show abstract

“…In [ 110 ], they looked at the index tracking performance of various autoencoder models, including the sparse AE, contractive AE, stacked AE, DAE, and VAE. These were used to find the relationships between stocks and construct tracking portfolios.…”

Section: Applicationsmentioning

confidence: 99%

An Overview of Variational Autoencoders for Source Separation, Finance, and Bio-Signal Applications

Singh

Ogunfunmi

2021

Entropy

View full text Add to dashboard Cite

Autoencoders are a self-supervised learning system where, during training, the output is an approximation of the input. Typically, autoencoders have three parts: Encoder (which produces a compressed latent space representation of the input data), the Latent Space (which retains the knowledge in the input data with reduced dimensionality but preserves maximum information) and the Decoder (which reconstructs the input data from the compressed latent space). Autoencoders have found wide applications in dimensionality reduction, object detection, image classification, and image denoising applications. Variational Autoencoders (VAEs) can be regarded as enhanced Autoencoders where a Bayesian approach is used to learn the probability distribution of the input data. VAEs have found wide applications in generating data for speech, images, and text. In this paper, we present a general comprehensive overview of variational autoencoders. We discuss problems with the VAEs and present several variants of the VAEs that attempt to provide solutions to the problems. We present applications of variational autoencoders for finance (a new and emerging field of application), speech/audio source separation, and biosignal applications. Experimental results are presented for an example of speech source separation to illustrate the powerful application of variants of VAE: VAE, β-VAE, and ITL-AE. We conclude the paper with a summary, and we identify possible areas of research in improving performance of VAEs in particular and deep generative models in general, of which VAEs and generative adversarial networks (GANs) are examples.

show abstract

Stock-Index Tracking Optimization Using Auto-Encoders

Cited by 17 publications

References 37 publications

The role amenities play in spatial sorting of migrants and their impact on welfare: Evidence from China

The role amenities play in spatial sorting of migrants and their impact on welfare: Evidence from China

A Comprehensive Soft Computing-Based Approach to Portfolio Management by Discarding Undesirable Stocks

An Overview of Variational Autoencoders for Source Separation, Finance, and Bio-Signal Applications

Contact Info

Product

Resources

About