scholarly journals Particle Filter Recurrent Neural Networks

2020 ◽  
Vol 34 (04) ◽  
pp. 5101-5108
Author(s):  
Xiao Ma ◽  
Peter Karkus ◽  
David Hsu ◽  
Wee Sun Lee
Keyword(s):  
Neural Networks ◽  
Particle Filter ◽  
Real World ◽  
Recurrent Neural Networks ◽  
Stock Price ◽  
Sequential Data ◽  
State Distribution ◽  
Real World Data ◽  
Stock Price Prediction ◽  
Particle Filter Algorithm

Recurrent neural networks (RNNs) have been extraordinarily successful for prediction with sequential data. To tackle highly variable and multi-modal real-world data, we introduce Particle Filter Recurrent Neural Networks (PF-RNNs), a new RNN family that explicitly models uncertainty in its internal structure: while an RNN relies on a long, deterministic latent state vector, a PF-RNN maintains a latent state distribution, approximated as a set of particles. For effective learning, we provide a fully differentiable particle filter algorithm that updates the PF-RNN latent state distribution according to the Bayes rule. Experiments demonstrate that the proposed PF-RNNs outperform the corresponding standard gated RNNs on a synthetic robot localization dataset and 10 real-world sequence prediction datasets for text classification, stock price prediction, etc.

scholarly journals Comparative Analysis of Recurrent Neural Networks in Stock Price Prediction for Different Frequency Domains

Algorithms ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 251
Author(s):  
Polash Dey ◽  
Emam Hossain ◽  
Md. Ishtiaque Hossain ◽  
Mohammed Armanuzzaman Chowdhury ◽  
Md. Shariful Alam ◽  
...  
Keyword(s):  
Neural Networks ◽  
Comparative Analysis ◽  
Recurrent Neural Networks ◽  
Stock Price ◽  
Short Term Memory ◽  
Time Intervals ◽  
Stock Price Prediction ◽  
Price Prediction ◽  
Frequency Domains ◽  
Time Series Analyses

Investors in the stock market have always been in search of novel and unique techniques so that they can successfully predict stock price movement and make a big profit. However, investors continue to look for improved and new techniques to beat the market instead of old and traditional ones. Therefore, researchers are continuously working to build novel techniques to supply the demand of investors. Different types of recurrent neural networks (RNN) are used in time series analyses, especially in stock price prediction. However, since not all stocks’ prices follow the same trend, a single model cannot be used to predict the movement of all types of stock’s price. Therefore, in this research we conducted a comparative analysis of three commonly used RNNs—simple RNN, Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU)—and analyzed their efficiency for stocks having different stock trends and various price ranges and for different time frequencies. We considered three companies’ datasets from 30 June 2000 to 21 July 2020. The stocks follow different trends of price movements, with price ranges of $30, $50, and $290 during this period. We also analyzed the performance for one-day, three-day, and five-day time intervals. We compared the performance of RNN, LSTM, and GRU in terms of R2 value, MAE, MAPE, and RMSE metrics. The results show that simple RNN is outperformed by LSTM and GRU because RNN is susceptible to vanishing gradient problems, while the other two models are not. Moreover, GRU produces lesser errors comparing to LSTM. It is also evident from the results that as the time intervals get smaller, the models produce lower errors and higher reliability.

Integrating metaheuristics and Artificial Neural Networks for improved stock price prediction

2016 ◽  
Vol 44 ◽  
pp. 320-331 ◽  
Author(s):  
Mustafa Göçken ◽  
Mehmet Özçalıcı ◽  
Aslı Boru ◽  
Ayşe Tuğba Dosdoğru
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Stock Price ◽  
Stock Price Prediction ◽  
Price Prediction ◽  
Artificial Neural

scholarly journals OPTIMISING THE SMOOTHNESS AND ACCURACY OF MOVING AVERAGE FOR STOCK PRICE DATA

2018 ◽  
Vol 24 (3) ◽  
pp. 984-1003 ◽  
Author(s):  
Aistis RAUDYS ◽  
Židrina PABARŠKAITĖ
Keyword(s):  
Time Series ◽  
Real World ◽  
Stock Price ◽  
Weather Forecasting ◽  
Moving Average ◽  
New Method ◽  
Traffic Prediction ◽  
Real World Data ◽  
Price Series ◽  
Unseen Data

Smoothing time series allows removing noise. Moving averages are used in finance to smooth stock price series and forecast trend direction. We propose optimised custom moving average that is the most suitable for stock time series smoothing. Suitability criteria are defined by smoothness and accuracy. Previous research focused only on one of the two criteria in isolation. We define this as multi-criteria Pareto optimisation problem and compare the proposed method to the five most popular moving average methods on synthetic and real world stock data. The comparison was performed using unseen data. The new method outperforms other methods in 99.5% of cases on synthetic and in 91% on real world data. The method allows better time series smoothing with the same level of accuracy as traditional methods, or better accuracy with the same smoothness. Weights optimised on one stock are very similar to weights optimised for any other stock and can be used interchangeably. Traders can use the new method to detect trends earlier and increase the profitability of their strategies. The concept is also applicable to sensors, weather forecasting, and traffic prediction where both the smoothness and accuracy of the filtered signal are important.

scholarly journals Predictive Monitoring with Logic-Calibrated Uncertainty for Cyber-Physical Systems

2021 ◽  
Vol 20 (5s) ◽  
pp. 1-25
Author(s):  
Meiyi Ma ◽  
John Stankovic ◽  
Ezio Bartocci ◽  
Lu Feng
Keyword(s):  
Neural Networks ◽  
Real World ◽  
Recurrent Neural Networks ◽  
Cyber Physical Systems ◽  
Uncertainty Estimation ◽  
Physical Systems ◽  
Confidence Levels ◽  
Novel Approach ◽  
Infinite Set

Predictive monitoring—making predictions about future states and monitoring if the predicted states satisfy requirements—offers a promising paradigm in supporting the decision making of Cyber-Physical Systems (CPS). Existing works of predictive monitoring mostly focus on monitoring individual predictions rather than sequential predictions. We develop a novel approach for monitoring sequential predictions generated from Bayesian Recurrent Neural Networks (RNNs) that can capture the inherent uncertainty in CPS, drawing on insights from our study of real-world CPS datasets. We propose a new logic named Signal Temporal Logic with Uncertainty (STL-U) to monitor a flowpipe containing an infinite set of uncertain sequences predicted by Bayesian RNNs. We define STL-U strong and weak satisfaction semantics based on whether all or some sequences contained in a flowpipe satisfy the requirement. We also develop methods to compute the range of confidence levels under which a flowpipe is guaranteed to strongly (weakly) satisfy an STL-U formula. Furthermore, we develop novel criteria that leverage STL-U monitoring results to calibrate the uncertainty estimation in Bayesian RNNs. Finally, we evaluate the proposed approach via experiments with real-world CPS datasets and a simulated smart city case study, which show very encouraging results of STL-U based predictive monitoring approach outperforming baselines.

scholarly journals Neural Networks in Credit Risk Classification of Companies in the Construction Sector

2018 ◽  
Vol 2 (2) ◽  
pp. 63-77 ◽  
Author(s):  
Aleksandra Wójcicka
Keyword(s):  
Neural Networks ◽  
Decision Making ◽  
Credit Risk ◽  
Financial Institutions ◽  
Real World ◽  
Decision Making Process ◽  
Construction Sector ◽  
Real World Data ◽  
Input Variables

The financial sector (banks, financial institutions, etc.) is the sector most exposed to financial and credit risk, as one of the basic objectives of banks' activity (as a specific enterprise) is granting credit and loans. Because credit risk is one of the problems constantly faced by banks, identification of potential good and bad customers is an extremely important task. This paper investigates the use of different structures of neural networks to support the preliminary credit risk decision-making process. The results are compared among the models and juxtaposed with real-world data. Moreover, different sets and subsets of entry data are analyzed to find the best input variables (financial ratios).

scholarly journals Comparison of Stock Price Prediction Models using Pre-trained Neural Networks

2021 ◽  
Vol 3 (2) ◽  
pp. 122-134
Author(s):  
C Anand
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Stock Price ◽  
Linear Models ◽  
Moving Average ◽  
Stock Price Prediction ◽  
Price Prediction ◽  
Data Prediction ◽  
Comparison Results ◽  
Auto Regressive

Several intelligent data mining approaches, including neural networks, have been widely employed by academics during the last decade. In today's rapidly evolving economy, stock market data prediction and analysis play a significant role. Several non-linear models like neural network, generalized autoregressive conditional heteroskedasticity (GARCH) and autoregressive conditional heteroscedasticity (ARCH) as well as linear models like Auto-Regressive Integrated Moving Average (ARIMA), Moving Average (MA) and Auto Regressive (AR) may be used for stock forecasting. The deep learning architectures inclusive of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN), Multilayer Perceptron (MLP) and Support Vector Machine (SVM) are used in this paper for stock price prediction of an organization by using the previously available stock prices. The National Stock Exchange (NSE) of India dataset is used for training the model with day-wise closing price. Data prediction is performed for a few sample companies selected on a random basis. Based on the comparison results, it is evident that the existing models are outperformed by CNN. The network can also perform stock predictions for other stock markets despite being trained with single market data as a common inner dynamics that has been shared between certain stock markets. When compared to the existing linear models, the neural network model outperforms them in a significant manner, which can be observed from the comparison results.

Sign in / Sign up

Export Citation Format

Share Document