Precious Metal Price Prediction Based on Deep Regularization Self-Attention Regression

Abstract

It is non-trivial to predict the prices of precious metals since a number of factors can affect the fluctuations of precious metal prices. Either parametric models or machine learning models cannot accurately forecast the precious metal prices. Though deep learning approaches show their strengths in extracting key features from complicated data, they have the limitations of learning localization and losing some temporal and spatial features. The recent advances in attention mechanisms bring the opportunities to overcome the limitation of deep learning models. In this paper, we originally propose a Regularization Self-Attention Regression Model for precious metal price prediction. In particular, the proposed RSAR model consists of convolutional neural network (CNN) component and Long Short-Term Memory Neural Networks (LSTM) component. Integrating with self-attention mechanism, this model can extract both spatial and temporal features from precious metal price data. Meanwhile, the proper configuration of regularization functions can also lead to the further performance improvement. Extensive experiments on realistic precious metal price dataset show that our proposed approach outperforms other conventional machine learning and deep learning methods. INDEX TERMS Long short-term memory, convolutional neural network, attention mechanism, financial data analysis, deep learning.

A Novel Deep-Learning-Based Framework for the Classification of Cardiac Arrhythmia

“…Then, attention map and matrix are multiplied to derive the attention feature matrix. The attention mechanism used is similar to the self-attention mechanism used in [ 32 ]. However, we have not used linear regulizers.…”

Proposed Bayesian Optimization Based LSTM-CNN Model for Stock Trend Prediction

“…The authors in [11,31] found that the ARIMA model is more robust in short-term prediction. However, it cannot achieve convergence in the long term [33]. This means that the prediction accuracy of ARIMA will get worse in the long run.…”

“…This assumption makes it fail to capture the non-linear pattern from financial time-series data. Secondly, it does not converge to the financial time-series in the long-term causing more computational cost [33]. Lastly, it only accepts univariate time-series data, thus means it is challenging for ARIMA to imitate technical traders by using technical indicators and stock prices.…”

Early Warning of Telecom Customer Churn Based on Multialgorithm Model Optimization

“…In summary, most researchers mainly use an algorithm model for customer churn early warning, but they have not used a variety of algorithm models for customer churn prediction and comparison (Buenano-Fernandez et al, 2020;Zhou et al, 2020). Some scholars specifically include control variable analysis for large-scale multiobjective optimization problems (Ma et al, 2021b), Some scholars summarize multidisciplinary writing styles and then predict author identification (Tai et al, 2020).…”