A novel hybrid stock selection method with stock prediction

Yang, Fengmei; Zhi-wen, Chen; Li, Jingjing; Tang, Ling

doi:10.1016/j.asoc.2019.03.028

Cited by 80 publications

(72 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental results showed that this portfolio outperformed the general market from 1992 to 2009, but deteriorated in 2010. Yang et al [28] applied extreme learning machine to predict future stock return, then used the predictive return as a indicator to construct portfolio optimization model combining with other technical indices. Differential evolution algorithms were used to solve the portfolio optimization problem.…”

Section: A Portfolios Based On the Predictive Results Of Machine Leamentioning

confidence: 99%

Prediction-Based Portfolio Optimization Models Using Deep Neural Networks

Han

Wang

2020

IEEE Access

View full text Add to dashboard Cite

Portfolio optimization is a hot research topic, which has attracted many researchers in recent decades. Better portfolio optimization model can help investors earn more stable profits. This paper uses three deep neural networks (DNNs), i.e., deep multilayer perceptron (DMLP), long short memory (LSTM) neural network and convolutional neural network (CNN) to build prediction-based portfolio optimization models which own the advantages of both deep learning technology and modern portfolio theory. These models first use DNNs to predict each stock's future return. Then, predictive errors of DNNs are applied to measure the risk of each stock. Next, the portfolio optimization models are built by integrating the predictive returns and semi-absolute deviation of predictive errors. These models are compared with three equal weighted portfolios, where their stocks are selected by DMLP, LSTM neural network and CNN respectively. Also, two prediction-based portfolio models built with support vector regression are used as benchmarks. This paper applies component stocks of China securities 100 index in Chinese stock market as experimental data. Experimental results present that the prediction-based portfolio model based on DMLP performs the best among these models under different desired portfolio returns, and high desired portfolio return can further improve the performance of this model. This paper presents the promising performance of DNNs in building prediction-based portfolio models. INDEX TERMS Deep neural network, Prediction-based portfolio, Semi-absolute deviation.

show abstract

Section: A Portfolios Based On the Predictive Results Of Machine Leamentioning

confidence: 99%

Prediction-Based Portfolio Optimization Models Using Deep Neural Networks

Han

Wang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Traders in any part of the world are interested in a market that is profitable and uses multiple technical indicators, macroeconomic factors and stock market indexes to study the market. This diverse market drivers' information reflects existing market price characteristics and facilitates prediction of future market price characteristics (Caley, 2013;Yang et al, 2019). As a result, we can prevent anticipated negative changes in the market due to new information about the market.…”

Section: Stock Market Forecastmentioning

confidence: 99%

Ultimate Prediction of Stock Market Price Movement

Nabi¹,

Saeed²,

Harron³

et al. 2019

Journal of Computer Science

View full text Add to dashboard Cite

Investment in the stock market is currently very popular due to its economic gain. Numerous researchers' and academicians' work is focused on financial time series prediction due to its data availability and profitability. Therefore, this study presents the design and implementation of a novel binary classification framework to predict stock market trends. The framework is composed of data preprocessing, feature engineering, feature selection and classification algorithms. The model is built on multiple sector stock market companies' data collected from NASDAQ over a period of ten years. Various feature selection algorithms are applied in combination with several machine learning algorithms. Furthermore, as the new contribution, we have constructed two new features which have been found to be promising in terms of improving overall performance. Ultimately, a collaboration of feature selection and classification techniques is employed. The application of Principal Component Analysis (PCA) with Multilayer Perceptron and Support Vector Machine (SVM) to added featured datasets shows 100% accuracy on the majority of datasets. In summary, an intensive comparison is presented among the various feature selection and classification algorithms.

show abstract

“…In recent years, with the development of artificial intelligence algorithms [8], BPNN [9] and SVR [10] algorithms have also become common methods for predicting time series data. In previous related studies, some scholars used the BPNN [11], [12] algorithm to predict time series data. In some areas, such as automobile sales forecasting, certain results have been achieved.…”

Section: Related Workmentioning

confidence: 99%