scholarly journals Exchange Rate Forecasting Based on Deep Learning and NSGA-II Models

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Jun Chen ◽  
Chenyang Zhao ◽  
Kaikai Liu ◽  
Jingjing Liang ◽  
Huan Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Exchange Rate ◽  
Exchange Market ◽  
Investment Portfolio ◽  
Nsga Ii ◽  
Investment Portfolios ◽  
Exchange Rate Prediction ◽  
Global Exchange ◽  
Deep Learning Model ◽  
Selection Of

Today, the global exchange market has been the world’s largest trading market, whose volume could reach nearly 5.345 trillion US dollars, attracting a large number of investors. Based on the perspective of investors and investment institutions, this paper combines theory with practice and creatively puts forward an innovative model of double objective optimization measurement of exchange forecast analysis portfolio. To be more specific, this paper proposes two algorithms to predict the volatility of exchange, which are deep learning and NSGA-II-based dual-objective measurement optimization algorithms for the exchange investment portfolio. Compared with typical traditional exchange rate prediction algorithms, the deep learning model has more accurate results and the NSGA-II-based model further optimizes the selection of investment portfolios and finally gives investors a more reasonable investment portfolio plan. In summary, the proposal of this article can effectively help investors make better investments and decision-making in the exchange market.

scholarly journals Research on Robustness of Related Images for Power Equipment Inspection

2021 ◽  
Vol 2113 (1) ◽  
pp. 012045
Author(s):  
Chunlei Zhou ◽  
Xiangzhou Chen ◽  
Wenli Liu ◽  
Tianyu Dong ◽  
Huang Yun
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Feature Fusion ◽  
Power Equipment ◽  
Actual Measurement ◽  
Practical Applications ◽  
Detection Algorithms ◽  
Traction Substations ◽  
Deep Learning Model ◽  
Selection Of

Abstract With the increase in the number of traction substations year by year, manual inspections are gradually being replaced by unattended inspections. Target detection algorithms based on deep learning are more widely used in intelligent inspections of power equipment. However, in practical applications, it is found that due to the small target to be detected, the accuracy of the deep learning model will decrease when the shooting angle is inclined and the light conditions are poor. This is because the algorithm’s robustness is low, and the detection ability of the model will be seriously affected when the angle or illumination difference with the sample is large. Based on this, the feature fusion part of the YOLOv3 algorithm and the selection of the loss function and the size of the anchor frame are improved, and the improved ASFF fusion method is used to classify various images in the power equipment. Actual measurement and repeated experiments show that the proposed method can be effectively applied to image recognition of various power equipment, optimize robustness, and greatly improve the image recognition efficiency of power equipment.

scholarly journals Linear and non-linear optimization models for the selection of investment portfolio

2021 ◽  
Vol 47 ◽  
Author(s):  
Sigutė Vakrinienė ◽  
Gintautas Misevičius
Keyword(s):  
Linear Programming ◽  
Risk Evaluation ◽  
Statistical Data ◽  
Linear Optimization ◽  
Investment Portfolio ◽  
Non Linear Programming ◽  
Non Linear ◽  
The Baltic ◽  
Investment Portfolios ◽  
Selection Of

This research suggests a maxmin model for the selection of investment portfolios. The risk evaluation coefficients are introduced. The components of portfolio are found by solving linear programming task in onemodel and non-linear programming task in the other.  In the experimental part of the research ineffective portfolios exerted from these models are tested referring to the statistical data of the Baltic stock market. Realizations of the suggested portfolios with different risk coefficient values are compared to realizations of effective (Pareto optimal) portfolios.

Deep Learning-Based Exchange Rate Prediction during the COVID-19

2020 ◽  
Author(s):  
Md Akhtaruzzaman ◽  
Mahmudul Hasan Moon ◽  
Helmi Hammami ◽  
Mohammad Zoynul Abedin
Keyword(s):  
Deep Learning ◽  
Exchange Rate ◽  
Rate Prediction ◽  
Exchange Rate Prediction

scholarly journals Bimatrix game model for the selection of investment portfolio

2009 ◽  
Vol 50 ◽  
Author(s):  
Sigutė Vakarinienė ◽  
Gintautas Misevičius
Keyword(s):  
Linear Programming ◽  
Nash Equilibria ◽  
Statistical Data ◽  
Game Model ◽  
Investment Portfolio ◽  
Bimatrix Game ◽  
Experimental Part ◽  
Investment Portfolios ◽  
Market Indexes ◽  
Selection Of

This research suggests a Nash equilibria model for the selection of investment portfolios. The components of portfolio are found by solving linear programming task with binary variables. In the experimental part of the research ineffective portfolios exerted from this model are tested referring to the statistical data of the stock market indexes of several countries. Realizations of the suggested portfolios are compared to realizations of effective portfolios.

scholarly journals The Application of genetic algorithms for the selection of WSE companies in Warsaw for the investment portfolio.

2020 ◽  
Vol 14 (1) ◽  
Author(s):  
Beata Basiura ◽  
Joanna Motyczyńska
Keyword(s):  
Genetic Algorithms ◽  
Time Window ◽  
Stock Exchange ◽  
Selection Function ◽  
Investment Portfolio ◽  
Short Processing Time ◽  
Simulation Based ◽  
Warsaw Stock Exchange ◽  
Investment Portfolios ◽  
Selection Of

Portfolio analysis is a tool particularly intended for investors. Risk assessment and risk specification make the investor able to properly diversify and offset the portfolio. Broadly speaking, there are multiple tools destined for building up an efficient set of portfolios.One of them is Markowitz’s model theory postulating building up a portfolio determined on the basis of equilibrium between expected profit level as well as accepted level of risk assessment.In the context of this paper, the objective is to shed some light on creating investment portfolios based on either Markowitz's portfolio theory or evolutionary algorithm. The simulation based methods for building up a portfolio of approximately 40-50 companies listed out in the primary marketof the Warsaw Stock Exchange using the selection function proposed in the BA thesis were presented.Portfolio profit values have been evaluated in a dynamically shifted time window. The conducted analysis showed shifts in the economy at certain periods of time. The implemented genetic algorithms smoothly handled the optimization with a relatively short processing time of the task result.

Deep Learning Model Selection of Suboptimal Complexity

2018 ◽  
Vol 79 (8) ◽  
pp. 1474-1488
Author(s):  
O. Yu. Bakhteev ◽  
V. V. Strijov
Keyword(s):  
Deep Learning ◽  
Model Selection ◽  
Learning Model ◽  
Deep Learning Model ◽  
Selection Of
Sign in / Sign up

Export Citation Format

Share Document