Related Experiment Videos
A Hybrid Method Based on Extreme Learning Machine and Wavelet Transform Denoising for Stock Prediction.
Dingming Wu1, Xiaolong Wang1, Shaocong Wu1
1College of Computer Science and Technology, Harbin Institute of Technology, Shenzhen 518055, China.
Entropy (Basel, Switzerland)
|April 30, 2021
Summary
Discrete wavelet transform (DWT) denoising improves stock trend prediction by removing noise. Combining DWT with extreme learning machine (ELM) offers superior stock trend forecasting accuracy compared to other machine learning methods.
Area of Science:
- Computational Finance
- Machine Learning
- Signal Processing
Background:
- Stock market trend prediction is challenging due to high noise from short-term fluctuations caused by accidental factors.
- Traditional methods struggle to isolate stable trends from random market noise, hindering accurate forecasting.
Purpose of the Study:
- To investigate the efficacy of discrete wavelet transform (DWT)-based denoising for enhancing stock trend prediction.
- To propose and evaluate a novel hybrid model combining DWT denoising with the Extreme Learning Machine (ELM) for stock trend forecasting.
Main Methods:
- Applied discrete wavelet transform (DWT) to denoise stock market data, effectively removing short-term noise and stabilizing trend characteristics.
- Utilized the Extreme Learning Machine (ELM), a fast and efficient algorithm for single-hidden-layer feedforward neural networks, for trend prediction.
- Integrated DWT denoising with ELM to create a hybrid model for predicting stock trends.
Main Results:
- Denoised stock data exhibited significantly more stable trend characteristics and smoothness compared to raw data.
- The proposed DWT-ELM hybrid model demonstrated excellent performance in predicting stock trends for 400 Chinese stocks.
- The hybrid model outperformed 12 other machine learning algorithms, including Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM).
Conclusions:
- DWT-based denoising is highly effective in mitigating the impact of short-term market noise on stock trend analysis.
- The combination of DWT denoising and ELM provides a robust and accurate approach for stock trend prediction.
- This hybrid methodology offers a significant advancement over existing machine learning techniques for financial market forecasting.
Related Concept Videos
01:30Classification of Signals
1.1K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.1K
01:03Prediction Intervals
2.6K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.6K