scholarly journals Digital Signal Processing for Predicting Stock Prices

2021 ◽  
Vol 4 (2) ◽  
pp. 12-21
Author(s):  
Bello A.O. ◽  
Kabari L.G.
Keyword(s):  
Signal Processing ◽  
Stock Market ◽  
Digital Signal Processing ◽  
Stock Prices ◽  
Stock Price ◽  
Digital Signal ◽  
Stock Market Forecasting ◽  
Predictive Algorithms ◽  
Mathematical Techniques ◽  
Speed Accuracy

With the exponential growth of big data and data warehousing, the amount of data collected from various stock markets around the world has increased significantly. It is now impossible to process and analyze data using mathematical techniques and basic statistical calculations to forecast trends such as closing and opening prices, as well as daily stock market lows and highs. The development of smart and automated stock market forecasting systems has made significant progress in recent years. Digital signal processing is required for analysis and preprocessing because of the accuracy and speed with which these large amounts of data must be processed and analyzed. In this paper, we evaluate some of these predictive algorithms based on three parameters such as speed, accuracy and complexity, we analyze the data using the dataset from kaggle.com and we implement these algorithms using pythons. The results of our analysis in this paper shows a significant correlation between the yearly prices until the year 2018 where there is a significant increase in stock price.

scholarly journals Stock Prediction Based on Optimized LSTM and GRU Models

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Ya Gao ◽  
Rong Wang ◽  
Enmin Zhou
Keyword(s):  
Stock Market ◽  
Dimension Reduction ◽  
Stock Prices ◽  
Stock Price ◽  
Investor Sentiment ◽  
Prediction Ability ◽  
Stock Market Forecasting ◽  
Important Research Topic ◽  
Reduction Methods ◽  
The Many

Stock market prediction has always been an important research topic in the financial field. In the past, inventors used traditional analysis methods such as K-line diagrams to predict stock trends, but with the progress of science and technology and the development of market economy, the price trend of a stock is disturbed by various factors. The traditional analysis method is far from being able to resolve the stock price fluctuations in the hidden important information. So, the prediction accuracy is greatly reduced. In this paper, we design a new model for optimizing stock forecasting. We incorporate a range of technical indicators, including investor sentiment indicators and financial data, and perform dimension reduction on the many influencing factors of the retrieved stock price using depth learning LASSO and PCA approaches. In addition, a comparison of the performances of LSTM and GRU for stock market forecasting under various parameters was performed. Our experiments show that (1) both LSTM and GRU models can predict stock prices efficiently, not one better than the other, and (2) for the two different dimension reduction methods, both the two neural models using LASSO reflect better prediction ability than the models using PCA.

Method of estimation of hidden correlation of narrowband noise signals

2019 ◽  
pp. 34-39 ◽  
Author(s):  
E.I. Chernov ◽  
N.E. Sobolev ◽  
A.A. Bondarchuk ◽  
L.E. Aristarhova
Keyword(s):  
Signal Processing ◽  
Digital Signal Processing ◽  
New Technology ◽  
Digital Signal ◽  
Measuring Instruments ◽  
Central Frequency ◽  
Pearson Criterion ◽  
Useful Signal ◽  
Band Limited ◽  
Narrowband Noise

The concept of hidden correlation of noise signals is introduced. The existence of a hidden correlation between narrowband noise signals isolated simultaneously from broadband band-limited noise is theoretically proved. A method for estimating the latent correlation of narrowband noise signals has been developed and experimentally investigated. As a result of the experiment, where a time frag ent of band-limited noise, the basis of which is shot noise, is used as the studied signal, it is established: when applying the Pearson criterion, there is practically no correlation between the signal at the Central frequency and the sum of signals at mirror frequencies; when applying the proposed method for the analysis of the same signals, a strong hidden correlation is found. The proposed method is useful for researchers, engineers and metrologists engaged in digital signal processing, as well as developers of measuring instruments using a new technology for isolating a useful signal from noise – the method of mirror noise images.

Sign in / Sign up

Export Citation Format

Share Document