The Optimal Robust Portfolio Model Based on CDaR

2013 ◽  
Vol 756-759 ◽  
pp. 2883-2886
Author(s):  
Xing Yu
Keyword(s):  
Numerical Simulation ◽  
Portfolio Risk ◽  
Model Based ◽  
Parameters Uncertainty ◽  
Uncertainty Set ◽  
Robust Portfolio ◽  
Ellipsoidal Uncertainty ◽  
Uncertainty Parameter ◽  
Portfolio Return

This paper proposed a robust portfolio model, using CDaR to measure portfolio risk. Due to uncertainty parameter, we constructed ellipsoidal uncertainty set as the parameters uncertainty set to maximize the portfolio return. We verified the operable of the model with numerical simulation. The result shows that the risk is higher compared to without robust case, which is helpful to cautious investment for investors.

Numerical Simulation Study of Metal Transfer in MIG Welding with Magnetic Control

2014 ◽  
Vol 532 ◽  
pp. 545-548 ◽  
Author(s):  
Chao Yang ◽  
Shu Yuan Jiang ◽  
Hai Bo Bi
Keyword(s):  
Fluid Dynamics ◽  
Numerical Simulation ◽  
Mathematical Model ◽  
Simulation Study ◽  
Electromagnetic Theory ◽  
Metal Transfer ◽  
Experimental Result ◽  
Magnetic Control ◽  
Mig Welding ◽  
Model Based

This paper simulate the mode of metal transfer in MIG magnetic control welding by using CFD software FLUENT, establishing mathematical model based on fluid dynamics and electromagnetic theory, and simulate the form, grow and drop process of metal transfer with and without magnetic. Meanwhile, do experiments to confirm the simulate result, and it is well consistent with the experimental result.

scholarly journals Financial Thought Experiment: A GAN-based Approach to Vast Robust Portfolio Selection

2020 ◽  
Author(s):  
Chi Seng Pun ◽  
Lei Wang ◽  
Hoi Ying Wong
Keyword(s):  
Stock Market ◽  
Thought Experiment ◽  
Empirical Studies ◽  
Synthetic Data ◽  
Risk Minimization ◽  
Portfolio Risk ◽  
Generative Adversarial Network ◽  
Day Trading ◽  
Adversarial Network ◽  
Robust Portfolio

Modern day trading practice resembles a thought experiment, where investors imagine various possibilities of future stock market and invest accordingly. Generative adversarial network (GAN) is highly relevant to this trading practice in two ways. First, GAN generates synthetic data by a neural network that is technically indistinguishable from the reality, which guarantees the reasonableness of the experiment. Second, GAN generates multitudes of fake data, which implements half of the experiment. In this paper, we present a new architecture of GAN and adapt it to portfolio risk minimization problem by adding a regression network to GAN (implementing the second half of the experiment). The new architecture is termed GANr. Battling against two distinctive networks: discriminator and regressor, GANr's generator aims to simulate a stock market that is close to the reality while allow for all possible scenarios. The resulting portfolio resembles a robust portfolio with data-driven ambiguity. Our empirical studies show that GANr portfolio is more resilient to bleak financial scenarios than CLSGAN and LASSO portfolios.

Prediction and Optimization of WAG Flooding by Using LSTM Neural Network Model in Middle East Carbonate Reservoir

2021 ◽  
Author(s):  
Ruijie Huang ◽  
Chenji Wei ◽  
Baozhu Li ◽  
Jian Yang ◽  
Suwei Wu ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Numerical Simulation ◽  
Short Term Memory ◽  
Oil Production ◽  
Simulation Method ◽  
Analysis Data ◽  
Carbonate Reservoir ◽  
Parameters Optimization ◽  
Model Based

Abstract Production prediction continues to play an increasingly significant role in reservoir development adjustment and optimization, especially in water-alternating-gas (WAG) flooding. As artificial intelligence continues to develop, data-driven machine learning method can establish a robust model based on massive data to clarify development risks and challenges, predict development dynamic characteristics in advance. This study gathers over 15 years actual data from targeted carbonate reservoir and establishes a robust Long Short-Term Memory (LSTM) neural network prediction model based on correlation analysis, data cleaning, feature variables selection, hyper-parameters optimization and model evaluation to forecast oil production, gas-oil ratio (GOR), and water cut (WC) of WAG flooding. In comparison to traditional reservoir numerical simulation (RNS), LSTM neural networks have a huge advantage in terms of computational efficiency and prediction accuracy. The calculation time of LSTM method is 864% less than reservoir numerical simulation method, while prediction error of LSTM method is 261% less than RNS method. We classify producers into three types based on the prediction results and propose optimization measures aimed at the risks and challenges they faced. Field implementation indicates promising outcome with better reservoir support, lower GOR, lower WC, and stabler oil production. This study provides a novel direction for application of artificial intelligence in WAG flooding development and optimization.

Sign in / Sign up

Export Citation Format

Share Document