Decision-making for financial trading: A fusion approach of machine learning and portfolio selection

Paiva, Felipe Dias; Cardoso, Rodrigo T. N.; Hanaoka, Gustavo Peixoto; Duarte, Wendel Moreira

doi:10.1016/j.eswa.2018.08.003

Cited by 178 publications

(86 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, incorporating forecasting theory into the portfolio formation will be promising in financial investment (Kolm et al, 2014). Forecasting financial time-series is always regarded as one of the most challenging tasks because of the dynamic, nonlinear, unstable and complex nature with longterm fluctuations of the financial market (Chen and Hao, 2018;Paiva et al, 2019). But a reliable investment decision should rely on long-term observations and patterns of behaviour of asset data rather than short-term (Chourmouziadis and Chatzoglou 2016;Chong et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

“…However, this important point is always ignored by current researches. For instance, some apply early machine learning methods, GA (Huang, 2012), SVM (Huang, 2012;Paiva et al, 2019), to predict and select good assets, but fail to capture long-term dependencies of financial time-series data. To overcome this limitation, we present a novel method for portfolio formation in conjunction to the asset preselection, in which long-term dependences of financial time-series data are duly considered.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Portfolio formation with preselection using deep learning from long-term financial data

Wang

Zhang

et al. 2020

Expert Systems with Applications

125

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Portfolio formation with preselection using deep learning from long-term financial data

Wang

Zhang

et al. 2020

Expert Systems with Applications

125

View full text Add to dashboard Cite

show abstract

“…Paiva et al [ 34 ] proposed a fusion approach of a Support Vector Machine and the mean-variance optimization for portfolio selection, testing for data from the Brazilian market and analyzing the effects of brokerage and transactions costs. Petropoulos et al [ 35 ] applied five machine learning algorithms (Support Vector Machine, Random Forest, Deep Artificial Neural Networks, Bayesian Autoregressive Trees, and Naïve Bayes) to build a model for FOREX portfolio management, combining the aforementioned methods in a stacked generalization system.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Between Nonlinearities, Complexity, and Noises: An Application on Portfolio Selection Using Kernel Principal Component Analysis

Peng

Albuquerque

Nascimento

et al. 2019

Entropy

View full text Add to dashboard Cite

This paper discusses the effects of introducing nonlinear interactions and noise-filtering to the covariance matrix used in Markowitz’s portfolio allocation model, evaluating the technique’s performances for daily data from seven financial markets between January 2000 and August 2018. We estimated the covariance matrix by applying Kernel functions, and applied filtering following the theoretical distribution of the eigenvalues based on the Random Matrix Theory. The results were compared with the traditional linear Pearson estimator and robust estimation methods for covariance matrices. The results showed that noise-filtering yielded portfolios with significantly larger risk-adjusted profitability than its non-filtered counterpart for almost half of the tested cases. Moreover, we analyzed the improvements and setbacks of the nonlinear approaches over linear ones, discussing in which circumstances the additional complexity of nonlinear features seemed to predominantly add more noise or predictive performance.

show abstract

“…Weng et al [6] developed a financial expert system for predicting short term stock prices based on counts and sentiment scores of news articles. Another system to assist users in financial trading has also been proposed, to predict stock trading patterns by integrating the support vector machine and portfolio selection theory [16].…”

Section: Financial Decision-making Support Systemmentioning

confidence: 99%

Developing an Risk Signal Detection System Based on Opinion Mining for Financial Decision Support

et al. 2019

View full text Add to dashboard Cite

Companies have long sought to detect financial risks and prevent crises in their business activities. Investors also have a great need to identify risks and utilize them for investment. Thus, several studies have attempted to detect financial risk. However, these studies had limitations in that various data were not exploited and diverse perspectives of the firm were not reflected. This can lead to wrong choices for investment. Thus, the purpose of this study was to propose risk signal prediction models based on firm data and opinion mining, reflecting both the perspectives of firms and investors. Furthermore, we developed a process to obtain real time firm related data and convenience visualization. To develop this process, a credit event was defined as an event that led to a critical risk of the firm. In the next step, the firm risk score was calculated for a firm having a possible credit event. This score was calculated by combining the firm activity score and opinion mining score. The firm activity score was calculated based on a financial statement and disclosure data indicator, while the opinion mining score was calculated based on a sentiment analysis of news and social data. As a result, the total firm risk grade was derived, and the risk level was proposed. These processes were developed into a system and illustrated by real firm data. The results of this study demonstrate that it is possible to derive risk signals through integrated monitoring indicators and provide useful information to users. This study can help users make decisions. It also provides users an opportunity to identify new investment momentums.

show abstract

Decision-making for financial trading: A fusion approach of machine learning and portfolio selection

Cited by 178 publications

References 47 publications

Portfolio formation with preselection using deep learning from long-term financial data

Portfolio formation with preselection using deep learning from long-term financial data

Between Nonlinearities, Complexity, and Noises: An Application on Portfolio Selection Using Kernel Principal Component Analysis

Developing an Risk Signal Detection System Based on Opinion Mining for Financial Decision Support

Contact Info

Product

Resources

About