Machine learning vs deep learning in stock market investment: an international evidence

Hao, Jing; He, Feng; Ma, Feng; Zhang, Shibo; Zhang, Xiaotao

doi:10.1007/s10479-023-05286-6

Cited by 5 publications

(2 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Training models with reliable datasets is the primary and foremost step, as it enables the models to learn the input they get and apply its experience to segregate and predict things. To be speci c, this paper includes four deep learning algorithms named Long Short-Term Memory (LSTM), Auto Regressive Integrated Moving Average (ARIMA), Bi-directional Long Short-Term Memory (Bi-LSTM), and Gate Recurrent Units (GRU) [6]- [9]. It highlights all the aspects in depth related to these algorithms, starting from their origin, explaining all the methodologies, which was followed by its implementation in the analysis, and their comparison with each other in order to draw reliable and accurate conclusions.…”

Section: Motivationmentioning

confidence: 99%

Stock Closing Price Prediction of Indian Tech Companies using Deep Neural Networks

Divyansh,

Moonis,

Raghav

et al. 2023

Preprint

View full text Add to dashboard Cite

In today’s economic world forecast and study of stock market data have got a vital role but, stock price forecasting has been hampered by its nonlinearity and high volatility of financial time series, to maximize the profits and reduce the risk involved the investors are eager to find different ways to forecast upcoming trends. It’s a challenging task to crack stock portfolio allocation in such a suitable way to invest in selected stocks that efficiently minimize the risk involved while capitalizing on profit. The effects of rival stocks in the stock market and the impact of mutation points on the precision of target stock predictions are rarely considered as market sentiment by the current prediction models. To validate which deep learning algorithm is best suited for stock market prediction analysis, we have espoused four deep learning algorithms namely Long Short-Term Memory (LSTM), Autoregressive Integrated Memory (ARIMA), Bi-directional Long Short-Term Memory (Bi-LSTM), and Gate Recurrent Units (GRU). On the basis of these mentioned evaluation parameters i.e., Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Percentage Error (MAPE) we have done the accuracy tests of the listed deep learning algorithms with evaluative stock prediction graph. Results have shown Bi-LSTM to perform exceptionally well for time series analysis. Regarding LSTM and GRU, the results have more or less stayed the same. While ARIMA gave an un-stable performance thus rendering its usefulness for our analysis.

show abstract

Section: Motivationmentioning

confidence: 99%

Stock Closing Price Prediction of Indian Tech Companies using Deep Neural Networks

Divyansh,

Moonis,

Raghav

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Machine learning and deep learning can help us deal with these complex market data and improve the accuracy of predictions [7], [18], [19], [20], [21], [22]. Lim et al [23] proposed deep momentum networks by combining trading rules based on deep learning with time series momentum strategies.…”

Section: Related Work a Quantitative Portfoliomentioning

confidence: 99%

Mercury: A Deep Reinforcement Learning-Based Investment Portfolio Strategy for Risk-Return Balance

et al. 2023

View full text Add to dashboard Cite

Stock portfolio is a hard issue in the Fintech field due to the diversity of data characteristics and the dynamic complexity of the market. Despite advances in deep learning that have made great progress in the complex and highly stochastic portfolio problem, the existing research still faces significant limitations. They either consider only investment returns or simply use some macro-market data to guide their models against risk. The preferred direction of the market greatly affects the choice of stock. And in practice, investors are more inclined to portfolios with low correlation between assets because of the ripple relationships between related things. In this paper, we propose a novel framework, called Mercury, which views stock screening as a reinforcement learning process. In particular, to enhance the ability to perceive changes in the market and generate higher returns, our framework models the sensitivity of the market preferences and learns dynamic temporal and spatial dependency patterns between assets from historical trading data. Additionally, the framework employs reinforcement learning to screen the overall low-correlation portfolio, which can better improve the ability to withstand investment risks while guaranteeing returns. The daily dataset of China's A-share market is used as the research sample to verify the effectiveness and robustness of Mercury, and our framework has strong generalization ability, which can be easily generalized to other trading procedures.INDEX TERMS Deep reinforcement learning, risk-return balanced portfolio strategy, market preferences, low-correlation assets.

show abstract

Short-term prediction of bank deposit flows: do textual features matter?

Katsafados,

Anastasiou

2024

Ann Oper Res

View full text Add to dashboard Cite

The purpose of this study is twofold. First, to construct short-term prediction models for bank deposit flows in the Euro area peripheral countries, employing machine learning techniques. Second, to examine whether textual features enhance the predictive ability of our models. We find that Random Forest models including both textual features and macroeconomic variables outperform those that include only macro factors or textual features. Monetary policy authorities or macroprudential regulators could adopt our approach to timely predict potential excessive bank deposit outflows and assess the resilience of the whole banking sector in the Euro area peripheral countries.

show abstract

Machine learning vs deep learning in stock market investment: an international evidence

Cited by 5 publications

References 45 publications

Stock Closing Price Prediction of Indian Tech Companies using Deep Neural Networks

Stock Closing Price Prediction of Indian Tech Companies using Deep Neural Networks

Mercury: A Deep Reinforcement Learning-Based Investment Portfolio Strategy for Risk-Return Balance

Short-term prediction of bank deposit flows: do textual features matter?

Contact Info

Product

Resources

About