Novel Online Portfolio Selection Algorithm Using Deep Sequence Features and Reversal Information

34 Pages Posted: 19 Dec 2023

See all articles by Hong-Liang Dai

Hong-Liang Dai

Guangzhou University

Fei-Tong Lai

Guangzhou University

Cui-Yin Huang

Guangzhou University

Xiao-Ting Lv

Guangzhou University

Fatima Sehar Sehar Zaidi

Guangzhou University

Abstract

Computational finance combines machine learning with financial needs to provide more efficient solutions for investment analysis and automated trading. In previous studies, traditional online portfolio selection (OLPS) algorithms were found to be overly reliant on artificially designed, subjective financial features. To address this issue, we propose a new predictive price tracking algorithm based on deep sequence features and reversal information (DSF-RI-PPT) for OLPS, extending a hybrid stock prediction algorithm to a multi-asset trading algorithm. We respectively employ the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), principal component analysis (PCA) algorithms and long short-term memory (LSTM) network to perform decomposition, feature extraction and prediction on financial data. Further, we supplement the reversal information by modifying the predicted prices with a reversal indicator-rate of change (ROC). Finally, a fast error backpropagation algorithm is introduced to feedback the modified predicted prices into the investment ratio through gradient projection. Through empirical comparison and statistic analysis of the DSF-RI-PPT algorithm, price-tracking algorithmswith similar prediction models, and nine classic OLPS algorithms in nine portfolio data sets under three financial indexes, it can be found that the DSF-RIPPTalgorithm is profitable and generalizable.

Keywords: Online portfolio selection, Empirical mode decomposition, Principal component analysis, Long short-term memory network, Gradient projection.

Suggested Citation

Dai, Hong-Liang and Lai, Fei-Tong and Huang, Cui-Yin and Lv, Xiao-Ting and Zaidi, Fatima Sehar Sehar, Novel Online Portfolio Selection Algorithm Using Deep Sequence Features and Reversal Information. Available at SSRN: https://ssrn.com/abstract=4669850 or http://dx.doi.org/10.2139/ssrn.4669850

Hong-Liang Dai (Contact Author)

Guangzhou University ( email )

Guangzhou Higher Education Mega Center
Waihuanxi Road 230
Guangzhou, 510006
China

Fei-Tong Lai

Guangzhou University ( email )

Guangzhou Higher Education Mega Center
Waihuanxi Road 230
Guangzhou, 510006
China

Cui-Yin Huang

Guangzhou University ( email )

Guangzhou Higher Education Mega Center
Waihuanxi Road 230
Guangzhou, 510006
China

Xiao-Ting Lv

Guangzhou University ( email )

Guangzhou Higher Education Mega Center
Waihuanxi Road 230
Guangzhou, 510006
China

Fatima Sehar Sehar Zaidi

Guangzhou University ( email )

Guangzhou Higher Education Mega Center
Waihuanxi Road 230
Guangzhou, 510006
China

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
82
Abstract Views
901
Rank
565,850
PlumX Metrics