scholarly journals Neural network regression for Bermudan option pricing

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Bernard Lapeyre ◽  
Jérôme Lelong
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Least Square ◽  
Dynamic Programming Principle ◽  
Regression Methods ◽  
Finite Dimensional Vector Space ◽  
Finite Dimensional ◽  
Conditional Expectations ◽  
Regression Techniques ◽  
Bermudan Option

Abstract The pricing of Bermudan options amounts to solving a dynamic programming principle, in which the main difficulty, especially in high dimension, comes from the conditional expectation involved in the computation of the continuation value. These conditional expectations are classically computed by regression techniques on a finite-dimensional vector space. In this work, we study neural networks approximations of conditional expectations. We prove the convergence of the well-known Longstaff and Schwartz algorithm when the standard least-square regression is replaced by a neural network approximation, assuming an efficient algorithm to compute this approximation. We illustrate the numerical efficiency of neural networks as an alternative to standard regression methods for approximating conditional expectations on several numerical examples.

A Cooperative Recurrent Neural Network for Solving L1 Estimation Problems with General Linear Constraints

2008 ◽  
Vol 20 (3) ◽  
pp. 844-872 ◽  
Author(s):  
Youshen Xia ◽  
Mohamed S. Kamel
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Recurrent Neural Network ◽  
Parallel Implementation ◽  
Linear Constraints ◽  
Estimation Problem ◽  
Least Square ◽  
General Linear ◽  
Attractive Alternative ◽  
Estimation Problems

The constrained L1 estimation is an attractive alternative to both the unconstrained L1 estimation and the least square estimation. In this letter, we propose a cooperative recurrent neural network (CRNN) for solving L1 estimation problems with general linear constraints. The proposed CRNN model combines four individual neural network models automatically and is suitable for parallel implementation. As a special case, the proposed CRNN includes two existing neural networks for solving unconstrained and constrained L1 estimation problems, respectively. Unlike existing neural networks, with penalty parameters, for solving the constrained L1 estimation problem, the proposed CRNN is guaranteed to converge globally to the exact optimal solution without any additional condition. Compared with conventional numerical algorithms, the proposed CRNN has a low computational complexity and can deal with the L1 estimation problem with degeneracy. Several applied examples show that the proposed CRNN can obtain more accurate estimates than several existing algorithms.

scholarly journals Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spaces

2020 ◽  
Vol 34 (04) ◽  
pp. 5306-5314
Author(s):  
Takamasa Okudono ◽  
Masaki Waga ◽  
Taro Sekiyama ◽  
Ichiro Hasuo
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Recurrent Neural Network ◽  
Recurrent Neural Networks ◽  
Learning Algorithm ◽  
Internal State ◽  
State Spaces ◽  
Regression Methods ◽  
Weighted Automata ◽  
Equivalence Queries

We present a method to extract a weighted finite automaton (WFA) from a recurrent neural network (RNN). Our method is based on the WFA learning algorithm by Balle and Mohri, which is in turn an extension of Angluin's classic L* algorithm. Our technical novelty is in the use of regression methods for the so-called equivalence queries, thus exploiting the internal state space of an RNN to prioritize counterexample candidates. This way we achieve a quantitative/weighted extension of the recent work by Weiss, Goldberg and Yahav that extracts DFAs. We experimentally evaluate the accuracy, expressivity and efficiency of the extracted WFAs.

Modelling of a Novel Gas Strut Using Neural Networks

2004 ◽  
Author(s):  
B. Gao ◽  
J. Darling ◽  
D. G. Tilley ◽  
R. A. Williams ◽  
A. Bean ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Mathematical Model ◽  
Least Square ◽  
Operation Conditions ◽  
The Neural Network ◽  
Wide Range ◽  
Non Linear ◽  
Vehicle Suspension System ◽  
And Control

The strut is one of the most important components in a vehicle suspension system. Since it is highly non-linear it is difficult to predict its performance characteristics using a physical mathematical model. However, neural networks have been successfully used as universal ‘black-box’ models in the identification and control of non-linear systems. This approach has been used to model a novel gas strut and the neural network was trained with experimental data obtained in the laboratory from simulated road profiles. The results obtained from the neural network demonstrated good agreement with the experimental results over a wide range of operation conditions. In contrast a linearised mathematical model using least square estimates of system parameters was shown to perform badly due to the highly non-linear nature of the system. A quarter car mathematical model was developed to predict strut behavior. It was shown that the two models produced different predictions of ride performance and it was argued that the neural network was preferable as it included the effects of non-linearities. Although the neural network model does not provide a good understanding of the physical behavior of the strut it is a useful tool for assessing vehicle ride and NVH performance due to its good computational efficiency and accuracy.

scholarly journals Short-Term Electricity Demand Forecasting: Impact Analysis of Temperature for Thailand

Energies ◽  
2020 ◽  
Vol 13 (10) ◽  
pp. 2498 ◽  
Author(s):  
Kamal Chapagain ◽  
Somsak Kittipiyakul ◽  
Pisut Kulthanavit
Keyword(s):  
Neural Network ◽  
Demand Forecasting ◽  
Electricity Demand ◽  
Least Square ◽  
Weather Variables ◽  
Forecasting Accuracy ◽  
Regression Methods ◽  
Electricity Demand Forecasting ◽  
Selection Of Variables ◽  
The Impact

Accurate electricity demand forecasting for a short horizon is very important for day-to-day control, scheduling, operation, planning, and stability of the power system. The main factors that affect the forecasting accuracy are deterministic variables and weather variables such as types of days and temperature. Due to the tropical climate of Thailand, the marginal impact of weather variables on electricity demand is worth analyzing. Therefore, this paper primarily focuses on the impact of temperature and other deterministic variables on Thai electricity demand. Accuracy improvement is also considered during model design. Based on the characteristics of demand, the overall dataset is divided into four different subgroups and models are developed for each subgroup. The regression models are estimated using Ordinary Least Square (OLS) methods for uncorrelated errors, and General Least Square (GLS) methods for correlated errors, respectively. While Feed Forward Artificial Neural Network (FF-ANN) as a simple Deep Neural Network (DNN) is estimated to compare the accuracy with regression methods, several experiments conducted for determination of training length, selection of variables, and the number of neurons show some major findings. The first finding is that regression methods can have better forecasting accuracy than FF-ANN for Thailand’s dataset. Unlike much existing literature, the temperature effect on Thai electricity demand is very interesting because of their linear relationship. The marginal impacts of temperature on electricity demand are also maximal at night hours. The maximum impact of temperature during night hours happens at 11 p.m., is 300 MW/ ° C, about 4 % rise in demand while during day hours, the temperature impact is only 10 MW/ ° C to 200 MW/ ° C about 1.4 % to 2.6 % rise.

Complementary Use of Partial Least-Squares and Artificial Neural Networks for the Annual Electricity Consumption Forecast

2012 ◽  
Vol 512-515 ◽  
pp. 1113-1116 ◽  
Author(s):  
Hui Feng Jiang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Electricity Consumption ◽  
Least Square Method ◽  
Partial Least Square ◽  
Least Square ◽  
Factors Affecting ◽  
The Neural Network ◽  
Proposed Model ◽  
Partial Least Square Method

A model for predicting annual electricity consumption based on the combination of neural network and partial least square method was proposed. The factors affecting the annual electricity consumption are analyzed by means of partial least square method to extract the most important components so that not only the problem of multi-correlation among variables can be solves but also the amount of input dimensions of the neural network can be reduced. Besides, the application of neural network helps to solve the problem of non-linearity of the model. The application example shows that the proposed model has high precision.

scholarly journals Identifying Skeletal Maturity from X-rays using Deep Neural Networks

2021 ◽  
Vol 15 (1) ◽  
pp. 141-148
Author(s):  
Suprava Patnaik ◽  
Sourodip Ghosh ◽  
Richik Ghosh ◽  
Shreya Sahay
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Skeletal Maturity ◽  
Bone Age ◽  
Network Architectures ◽  
X Rays ◽  
X Ray ◽  
Regression Techniques

Skeletal maturity estimation is routinely evaluated by pediatrics and radiologists to assess growth and hormonal disorders. Methods integrated with regression techniques are incompatible with low-resolution digital samples and generate bias, when the evaluation protocols are implemented for feature assessment on coarse X-Ray hand images. This paper proposes a comparative analysis between two deep neural network architectures, with the base models such as Inception-ResNet-V2 and Xception-pre-trained networks. Based on 12,611 hand X-Ray images of RSNA Bone Age database, Inception-ResNet-V2 and Xception models have achieved R-Squared value of 0.935 and 0.942 respectively. Further, in the same order, the MAE accomplished by the two models are 12.583 and 13.299 respectively, when subjected to very few training instances with negligible chances of overfitting.

scholarly journals Power Generation Forecasting of Dual-Axis Solar Tracked PV System Based on Averaging and Simple Weighting Ensemble Neural Networks

2018 ◽  
Vol 6 (2) ◽  
pp. 275-288
Author(s):  
Budiman Putra Asma'ur Rohman ◽  
Catur Hilman ◽  
Erik Tridianto ◽  
Teguh Hady Ariwibowo
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Power Generation ◽  
Solar Power ◽  
Human Life ◽  
Least Square ◽  
Pv System ◽  
Pv Systems ◽  
Output Uncertainty ◽  
Efficient Power

Solar power is a renewable energy interest many researchers around the world to be explored for human life beneficial especially for electric power generation. Photovoltaic (PV) is one of technology developed massively to exploit the solar power for this purpose. However, its performance is very sensitive to environmental condition such as solar irradiance, weather, and climatic behavior. Thus, the hybrid power generation systems are developed to solve this output uncertainty problem. To support this such hybrid system, this paper proposes an ensemble neural network based forecaster of the power output of PV systems which will lead an efficient power management. The object of this research is the PV systems equipped with two axes automated solar tracking with peak power 10Wp. The proposed ensemble forecaster model employs four multi-layer perceptron neural networks with two hidden layers as base forecasters while the input number of historical data is varied in order to exploit the forecaster diversity. The final prediction is calculated both by conventional averaging and simple weighting optimized by the least square fitting technique. According to the research results, the both proposed approaches provide low error rate. Moreover, in term of comparison, the ensemble model with averaging combining technique gives the highest accuracy comparing to the other ensemble and conventional neural network structures.

scholarly journals On the use of neural networks for energy reconstruction in high-granularity calorimeters

2021 ◽  
Vol 16 (12) ◽  
pp. P12036
Author(s):  
N. Akchurin ◽  
C. Cowden ◽  
J. Damgov ◽  
A. Hussain ◽  
S. Kunori
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Substantial Improvement ◽  
Regression Methods ◽  
Real World Application ◽  
Current State ◽  
Energy Reconstruction ◽  
Simple Simulation ◽  
Latent Features ◽  
Shower Development

Abstract We contrasted the performance of deep neural networks — Convolutional Neural Network (CNN) and Graph Neural Network (GNN) — to current state of the art energy regression methods in a finely 3D-segmented calorimeter simulated by GEANT4. This comparative benchmark gives us some insight to assess the particular latent signals neural network methods exploit to achieve superior resolution. A CNN trained solely on a pure sample of pions achieved substantial improvement in the energy resolution for both single pions and jets over the conventional approaches. It maintained good performance for electron and photon reconstruction. We also used the Graph Neural Network (GNN) with edge convolution to assess the importance of timing information in the shower development for improved energy reconstruction. We implement a simple simulation based correction to the energy sum derived from the fraction of energy deposited in the electromagnetic shower component. This serves as an approximate dual-readout analogue for our benchmark comparison. Although this study does not include the simulation of detector effects, such as electronic noise, the margin of improvement seems robust enough to suggest these benefits will endure in real-world application. We also find reason to infer that the CNN/GNN methods leverage latent features that concur with our current understanding of the physics of calorimeter measurement.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Color Space Transformation using Neural Networks

2019 ◽  
Vol 2019 (1) ◽  
pp. 153-158
Author(s):  
Lindsay MacDonald
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Color Space ◽  
Reflectance Spectra ◽  
Network Architectures ◽  
Color Spaces ◽  
Natural Materials ◽  
Space Transformation ◽  
Color Space Transformation

We investigated how well a multilayer neural network could implement the mapping between two trichromatic color spaces, specifically from camera R,G,B to tristimulus X,Y,Z. For training the network, a set of 800,000 synthetic reflectance spectra was generated. For testing the network, a set of 8,714 real reflectance spectra was collated from instrumental measurements on textiles, paints and natural materials. Various network architectures were tested, with both linear and sigmoidal activations. Results show that over 85% of all test samples had color errors of less than 1.0 ΔE2000 units, much more accurate than could be achieved by regression.

Sign in / Sign up

Export Citation Format

Share Document