article · Neural Computing and Applications
Predicting stock market movements is challenging for investors due to data noise and limited price shifts. A new deep-learning framework, termed stock market prediction based on deep learning (SMP-DL), addresses this challenge by forecasting closing prices through a two-stage process. The first stage cleans and prepares input data through missing value detection and rejection, feature selection, and normalisation. The second stage applies a hybrid predictive model combining long short-term memory networks with bidirectional gated recurrent units. When evaluated across multiple datasets, this architecture achieved an R-squared value of 0.9948, along with low error rates across standard metrics, outperforming existing comparative methods.
Financial markets involve high levels of noise that make accurate price forecasting difficult for market participants. By coupling rigorous data cleaning with dual recurrent neural network architectures, this framework offers a more dependable mechanism for anticipating closing price trends, potentially aiding risk assessment and investment planning in volatile market environments.
This approach could enable algorithmic trading modules and decision-support software for financial analysts and investors seeking closing price projections. Because the work is validated only across historical datasets in a research context, it represents an early-stage computational method that requires live-market testing and software integration before reaching commercial readiness.
AI-generated from the published abstract. Always read the original work before citing.
Abstract As the economy has grown rapidly in recent years, more and more people have begun putting their money into the stock market. Thus, predicting trends in the stock market is regarded as a crucial endeavor, and one that has proven to be more fruitful than others. Profitable investments will result in rising stock prices. Investors face significant difficulties making stock market-related predictions due to the lack of movement and noise in the data. In this paper, a new system for predicting stock market prices is introduced, namely stock market prediction based on deep leaning (SMP-DL). SMP-DL splits into two stages, which are (i) data preprocessing (DP) and (ii) stock price’s prediction (SP 2 ). In the first stage, data are preprocessed to obtain cleaned ones through several stages which are detect and reject missing value, feature selection, and data normalization. Then, in the second stage (e.g., SP 2 ), the cleaned data will pass through the used predicted model. In SP 2 , long short-term memory (LSTM) combined with bidirectional gated recurrent unit (BiGRU) to predict the closing price of stock market. The obtained results showed that the proposed system perform well when compared to other existing methods. As RMSE, MSE, MAE, and R 2 values are 0.2883, 0.0831, 0.2099, and 0.9948. Moreover, the proposed method was applied using different datasets and it performs well.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00521-023-09179-4
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
