Neural Network Models for Stock Selection Based on Fundamental Analysis

Huang, Yuxuan; Capretz, Luiz Fernando; Ho, Danny

doi:10.1109/ccece.2019.8861550

Cited by 31 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, meta learning methods employ many strategies [31]. Because of the impressive advances in neural networks, machine learning, and deep learning, these methods have broadly replaced traditional feature extraction optimization algorithms in solving financial problems [32], [33]. However, basic algorithms leveraging machine learning and deep learning learn the task using supervised data, which are likely unable to capture market uncertainty.…”

Section: B Portfolio Management Tasks With Traditional and Deep Learning Methodsmentioning

confidence: 99%

Adversarial Attacks Against Reinforcement Learning-Based Portfolio Management Strategy

Chen

Sang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Many researchers have incorporated deep neural networks (DNNs) with reinforcement learning (RL) in automatic trading systems. However, such methods result in complicated algorithmic trading models with several defects, especially when a DNN model is vulnerable to malicious adversarial samples. Researches have rarely focused on planning for long-term attacks against RL-based trading systems. To neutralize these attacks, researchers must consider generating imperceptible perturbations while simultaneously reducing the number of modified steps. In this research, an adversary is used to attack an RLbased trading agent. First, we propose an extension of the ensemble of the identical independent evaluators (EIIE) method, called enhanced EIIE, in which information on the best bids and asks is incorporated. Enhanced EIIE was demonstrated to produce an authoritative trading agent that yields better portfolio performance relative to that of an EIIE agent. Enhanced EIIE was then applied to the adversarial agent for the agent to learn when and how much to attack (in the form of introducing perturbations).In our experiments, our proposed adversarial attack mechanisms were > 30% more effective at reducing accumulated portfolio value relative to the conventional attack mechanisms of the fast gradient sign method (FSGM) and iterative FSGM, which are currently more commonly researched and adapted to compare and improve.

show abstract

Section: B Portfolio Management Tasks With Traditional and Deep Learning Methodsmentioning

confidence: 99%

Adversarial Attacks Against Reinforcement Learning-Based Portfolio Management Strategy

Chen

Sang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…. Also using other algorithms such as fuzzy logic, MLP, FNN, and Decision Boosted Tree [2], [8], [23], [30]. Several studies have compared the best method for clustering, such as [31] comparing Naive Bayes and SVM, and found that Naive Bayes is better than others.…”

Section: Associationmentioning

confidence: 99%

Systematic Literature Review: Stock Price Prediction Using Machine Learning and Deep Learning

Dopi¹,

Hartanto²,

Fauziati³

2021

Advances in Economics, Business and Management Research

View full text Add to dashboard Cite

This research was conducted using a literature review method to analyze various studies that will identify the type of analysis with the attributes used, the methods used, the methods most often used, and the methods that have the best performance. This study collected research from 2016 -July 2021, selected based on predetermined criteria and then collected 40 papers. This review found that there are four research topics, namely estimation, classification, clustering, and association. The findings of this study are four research topics, namely fundamentals, technicals, sentiment analysis, and even a combination of analyzes that use their respective attributes and datasets. There are thirty-one different methods found to be used in predicting stock prices. LSTM, MLP, RF, and SVM are the most widely used methods. In addition, MLP is a method that gives the best performance of 71.63% and LSTM of 70%. The use of combined machine learning methods with ensemble techniques, deep learning, and selection of input attributes in pre-processing is recommended for better accuracy.

show abstract

“…Beside mainstream deep learning methods, other deep learning frameworks have also been applied to predicting stocks. Huang [22] investigated and compared a Feed-forward Neural Network (FNN) and an Adaptive Neural Fuzzy Inference System (ANFIS) in stock prediction using fundamental financial ratios. This study showed that both architectures possess the ability to separate winners and losers from a sample universe of stocks, and the selected portfolios outperformed the benchmark.…”

Section: Related Workmentioning

confidence: 99%

Portfolio Learning Based on Deep Learning

Pan

2020

Future Internet

View full text Add to dashboard Cite

Traditional portfolio theory divides stocks into different categories using indicators such as industry, market value, and liquidity, and then selects representative stocks according to them. In this paper, we propose a novel portfolio learning approach based on deep learning and apply it to China’s stock market. Specifically, this method is based on the similarity of deep features extracted from candlestick charts. First, we obtained whole stock information from Tushare, a professional financial data interface. These raw time series data are then plotted into candlestick charts to make an image dataset for studying the stock market. Next, the method extracts high-dimensional features from candlestick charts through an autoencoder. After that, K-means is used to cluster these high-dimensional features. Finally, we choose one stock from each category according to the Sharpe ratio and a low-risk, high-return portfolio is obtained. Extensive experiments are conducted on stocks in the Chinese stock market for evaluation. The results demonstrate that the proposed portfolio outperforms the market’s leading funds and the Shanghai Stock Exchange Composite Index (SSE Index) in a number of metrics.

show abstract

Neural Network Models for Stock Selection Based on Fundamental Analysis

Cited by 31 publications

References 15 publications

Adversarial Attacks Against Reinforcement Learning-Based Portfolio Management Strategy

Adversarial Attacks Against Reinforcement Learning-Based Portfolio Management Strategy

Systematic Literature Review: Stock Price Prediction Using Machine Learning and Deep Learning

Portfolio Learning Based on Deep Learning

Contact Info

Product

Resources

About