scholarly journals Carteiras de Black Litterman com Análises Baseadas em Redes Neurais

2020 ◽  
Vol 18 (1) ◽  
pp. 60-75
Author(s):  
Diego Guerreiro Bernardes ◽  
Oswaldo Luiz do Valle Costa
Keyword(s):  
Neural Networks ◽  
Portfolio Management ◽  
Good Alternative ◽  
Trading System ◽  
Neural Network Approach ◽  
Inference Models ◽  
Risk Return ◽  
Portfolio Composition ◽  
Great Performance ◽  
Future Return

This paper presents an autonomous portfolio management system. Autonomous investment systems consist of a series of buy and sell rules on financial markets, which can be executed by machines, oriented to maximizing investor gains. The system uses a Neural Network approach for monitoring the market and the Black-Litterman model for portfolio composition. The ten most traded assets from the Bovespa Index are analyzed, with dedicated neural networks, which suggests future return estimates using technical indicators as input. Those estimates are inserted in the Black-Litterman model which proposes daily portfolio composition using long and short positions. The results are compared to a second autonomous trading system without the Black-Litterman approach, referred to as Benchmark. The numerical results show a great performance compared to the Benchmark, especially the risk-return ratio, captured by the Sharpe Index. Such results suggest that the use of Bayesian inference models combined with neural networks may be a good alternative in portfolio management.

Portfolio Selection Models and Their Discrimination

2011 ◽  
Vol 2 (2) ◽  
pp. 65-91 ◽  
Author(s):  
Satadal Ghosh ◽  
Sujit Kumar Majumdar
Keyword(s):  
Portfolio Selection ◽  
Portfolio Management ◽  
Stock Return ◽  
Signal To Noise Ratio ◽  
Selection Models ◽  
Markowitz Model ◽  
Risk Return ◽  
Future Return ◽  
Possibility Distributions ◽  
Portfolio Selection Model

The stochastic nature of financial markets is a barrier for successful portfolio management. Besides traditional Markowitz’s model, many other portfolio selection models in Bayesian and Non-Bayesian frameworks have been developed. Starting with the basic Markowitz model, several cardinal models are used to find optimum portfolios with select stock set. Having developed the regression model of the return of each stock with the market return, the unsystematic part of the uncertainty was used to find the optimum portfolio and efficient risk–return frontier within each portfolio selection model. The average stock return as estimated from its historical data and the forecasted stock return were used for maximizing return with quadratic programming formulation in Markowitz model. In the models involving Fuzzy probability and possibility distributions, the future return was estimated using the similarity grade of past returns. In the interval coefficient models, future return was estimated as interval variable. The optimum portfolios of different models were widely divergent and DEA was used to identify the model giving the best portfolio with higher appraisal, both overall and by peers, and least Maverick behavior. Use of Signal to Noise ratio proved equally efficient for model discrimination and yielded identical results.

Portfolio Selection Models and Their Discrimination

2013 ◽  
pp. 170-195
Author(s):  
Satadal Ghosh ◽  
Sujit Kumar Majumdar
Keyword(s):  
Portfolio Selection ◽  
Portfolio Management ◽  
Stock Return ◽  
Signal To Noise Ratio ◽  
Selection Models ◽  
Markowitz Model ◽  
Risk Return ◽  
Future Return ◽  
Possibility Distributions ◽  
Portfolio Selection Model

The stochastic nature of financial markets is a barrier for successful portfolio management. Besides traditional Markowitz’s model, many other portfolio selection models in Bayesian and Non-Bayesian frameworks have been developed. Starting with the basic Markowitz model, several cardinal models are used to find optimum portfolios with select stock set. Having developed the regression model of the return of each stock with the market return, the unsystematic part of the uncertainty was used to find the optimum portfolio and efficient risk–return frontier within each portfolio selection model. The average stock return as estimated from its historical data and the forecasted stock return were used for maximizing return with quadratic programming formulation in Markowitz model. In the models involving Fuzzy probability and possibility distributions, the future return was estimated using the similarity grade of past returns. In the interval coefficient models, future return was estimated as interval variable. The optimum portfolios of different models were widely divergent and DEA was used to identify the model giving the best portfolio with higher appraisal, both overall and by peers, and least Maverick behavior. Use of Signal to Noise ratio proved equally efficient for model discrimination and yielded identical results.

HFTViz: Visualization for the exploration of high frequency trading data

2021 ◽  
pp. 147387162110649
Author(s):  
Javad Yaali ◽  
Vincent Grégoire ◽  
Thomas Hurtut
Keyword(s):  
Portfolio Management ◽  
High Frequency ◽  
High Speed ◽  
High Frequency Trading ◽  
Domain Experts ◽  
Risk Return ◽  
Visualization Tools ◽  
Liquidity Measures ◽  
Trading Volumes

High Frequency Trading (HFT), mainly based on high speed infrastructure, is a significant element of the trading industry. However, trading machines generate enormous quantities of trading messages that are difficult to explore for financial researchers and traders. Visualization tools of financial data usually focus on portfolio management and the analysis of the relationships between risk and return. Beside risk-return relationship, there are other aspects that attract financial researchers like liquidity and moments of flash crashes in the market. HFT researchers can extract these aspects from HFT data since it shows every detail of the market movement. In this paper, we present HFTViz, a visualization tool designed to help financial researchers explore the HFT dataset provided by NASDAQ exchange. HFTViz provides a comprehensive dashboard aimed at facilitate HFT data exploration. HFTViz contains two sections. It first proposes an overview of the market on a specific date. After selecting desired stocks from overview visualization to investigate in detail, HFTViz also provides a detailed view of the trading messages, the trading volumes and the liquidity measures. In a case study gathering five domain experts, we illustrate the usefulness of HFTViz.

Estimation of Annual Average Daily Traffic on Low-Volume Roads: Factor Approach Versus Neural Networks

2000 ◽  
Vol 1719 (1) ◽  
pp. 103-111 ◽  
Author(s):  
Satish C. Sharma ◽  
Pawan Lingras ◽  
Guo X. Liu ◽  
Fei Xu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Traffic Monitoring ◽  
Network Approach ◽  
Annual Average ◽  
Neural Network Approach ◽  
The Neural Network ◽  
Low Volume Roads ◽  
Annual Average Daily Traffic ◽  
Low Volume

Estimation of the annual average daily traffic (AADT) for low-volume roads is investigated. Artificial neural networks are compared with the traditional factor approach for estimating AADT from short-period traffic counts. Fifty-five automatic traffic recorder (ATR) sites located on low-volume rural roads in Alberta, Canada, are used as study samples. The results of this study indicate that, when a single 48-h count is used for AADT estimation, the factor approach can yield better results than the neural networks if the ATR sites are grouped appropriately and the sample sites are correctly assigned to various ATR groups. Unfortunately, the current recommended practice offers little guidance on how to achieve the assignment accuracy that may be necessary to obtain reliable AADT estimates from a single 48-h count. The neural network approach can be particularly suitable for estimating AADT from two 48-h counts taken at different times during the counting season. In fact, the 95th percentile error values of about 25 percent as obtained in this study for the neural network models compare favorably with the values reported in the literature for low-volume roads using the traditional factor approach. The advantage of the neural network approach is that classification of ATR sites and sample site assignments to ATR groups are not required. The analysis of various groups of low-volume roads presented also leads to a conclusion that, when defining low-volume roads from a traffic monitoring point of view, it is not likely to matter much whether the AADT on the facility is less than 500 vehicles, less than 750 vehicles, or less than 1,000 vehicles.

scholarly journals Statistical and Artificial Neural Networks Models for Electricity Consumption Forecasting in the Brazilian Industrial Sector

Energies ◽  
2022 ◽  
Vol 15 (2) ◽  
pp. 588
Author(s):  
Felipe Leite Coelho da Silva ◽  
Kleyton da Costa ◽  
Paulo Canas Rodrigues ◽  
Rodrigo Salas ◽  
Javier Linkolk López-Gonzales
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Statistical Approach ◽  
Electricity Consumption ◽  
Industrial Sector ◽  
Neural Network Approach ◽  
Artificial Neural ◽  
The One ◽  
Mlp Model

Forecasting the industry’s electricity consumption is essential for energy planning in a given country or region. Thus, this study aims to apply time-series forecasting models (statistical approach and artificial neural network approach) to the industrial electricity consumption in the Brazilian system. For the statistical approach, the Holt–Winters, SARIMA, Dynamic Linear Model, and TBATS (Trigonometric Box–Cox transform, ARMA errors, Trend, and Seasonal components) models were considered. For the approach of artificial neural networks, the NNAR (neural network autoregression) and MLP (multilayer perceptron) models were considered. The results indicate that the MLP model was the one that obtained the best forecasting performance for the electricity consumption of the Brazilian industry under analysis.

scholarly journals Project Selection Frameworks and Methodologies for Reducing Risks in Project Portfolio Management

2017 ◽  
pp. 245-263
Author(s):  
Fabio Nonino
Keyword(s):  
Neural Networks ◽  
Portfolio Management ◽  
Success Factors ◽  
Project Selection ◽  
Project Portfolio ◽  
Project Portfolio Management ◽  
Critical Success ◽  
Innovative Methodology ◽  
Correct Level

Extracting and consolidating knowledge from past projects can help managers in selecting projects with the correct level of riskiness, while market analysis gives directions for reaching the objective of a balanced project portfolio. To this extent, the chapter discusses strategic importance of project selection and the role of risks and uncertainties in project portfolio management and presents some fundamental and innovative frameworks and project selection methodologies for balancing risks. Finally, the chapter proposes a model containing an innovative methodology, based on artificial neural networks, to help managers in balancing project portfolio and assessing projects during the selection phase on the basis of risks, uncertainties and critical success factors.

scholarly journals Artificial Intelligence (AI) techniques to analyze the determinants attributes in housing prices

2016 ◽  
Vol 19 (58) ◽  
pp. 23 ◽  
Author(s):  
Julia M. Núñez Tabale ◽  
Francisco J. Rey Carmona ◽  
José Mª Caridad y Ocerin
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Explanatory Variable ◽  
Housing Prices ◽  
Good Alternative ◽  
Marginal Prices ◽  
Using Data ◽  
Econometric Approach ◽  
Hedonic Approach

The econometric approach to obtain the value of a property began with hedonic modelling, which were based on a set of property attributes, internal or external, associated to each particular dwelling. The final sale value can be estimated, and also the marginal prices of each exogenous explanatory variable. A good alternative to the hedonic approach is based on several Artificial Intelligence (AI) techniques, such as artificial neural networks (ANN), these tend to be more precise. Both methodologies are compared, and a case study is developed using data from Seville, the larger town in the South of Spain.

Introduction to Expert Systems, Fuzzy Logic, Neural Networks, and Chaos Theory

2021 ◽  
pp. 1-10
Keyword(s):  
Neural Networks ◽  
Fuzzy Logic ◽  
Expert Systems ◽  
Chaos Theory ◽  
Classifier Systems ◽  
Biologically Inspired ◽  
Trading System ◽  
The World ◽  
Computational Procedures ◽  
Near Future

The power of genetic algorithms (GAs) and related expert systems such as fuzzy logic, neural networks, and chaos theory and other classifier systems is truly infinite in nature. The above stated procedures are sure to happen in the near future, and there is no chance for it not to occur. GAs, fuzzy logic, neural networks, and chaos theory are all biologically-inspired algorithmic procedures, as they all are linked to the world of biology in some way. Market represents the ideas of traders. In the present environment, the market is driven by the ideas generated by the use of these AI-based expert systems and it is causing huge competition in making profits. This chapter is planned to be a detailed introduction of various popular expert systems such as GAs, neural networks, fuzzy logic, and chaos theory and their usages. Researchers in the past have proved that these computational procedures could have far reaching effects in the stock trading system.

scholarly journals Chestnut (Castanea sativa Mill.) cultivar classification: an artificial neural network approach

2020 ◽  
Vol 48 (1) ◽  
pp. 366-377 ◽  
Author(s):  
Yeşim Benal ÖZTEKİN ◽  
Alper TANER ◽  
Hüseyin DURAN
Keyword(s):  
Neural Networks ◽  
Transfer Functions ◽  
Geometric Mean ◽  
Back Propagation ◽  
Castanea Sativa ◽  
Average Error ◽  
Ann Model ◽  
Neural Network Approach ◽  
Castanea Sativa Mill ◽  
Artificial Neural

The present study investigated the possible use of artificial neural networks (ANN) to classify five chestnut (Castanea sativa Mill.) varieties. For chestnut classification, back-propagation neural networks were framed on the basis of physical and mechanical parameters. Seven physical and mechanical characteristics (geometric mean diameter, sphericity, volume of nut, surface area, shell thickness, shearing force and strength) of chestnut were determined. It was found that these characteristics were statistically different and could be used in the classification of species. In the developed ANN model, the design of the network is 7-(5-6)-1 and it consists of 7 input, 2 hidden and 1 output layers. Tansig transfer functions were used in both hidden layers, while linear transfer functions were used in the output layer. In ANN model, R2 value was obtained as 0.99999 and RMSE value was obtained as 0.000083 for training. For testing, R2 value was found as 0.99999 and RMSE value was found as 0.00031. In the approximation of values obtained with ANN model to the values measured, average error was found as 0.011%. It was found that the results found with ANN model were very compatible with the measured data. It was found that the ANN model obtained can classify chestnut varieties in a fast and reliable way.

Individualizing Displays through the Use of Neural Networks

1997 ◽  
Vol 41 (1) ◽  
pp. 269-273
Author(s):  
Kai-Chun Cheng ◽  
Ray E. Eberts
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Intelligent Vehicle ◽  
Network Approach ◽  
Neural Network Approach ◽  
Traveler Information ◽  
Gas Stations ◽  
The Neural Network ◽  
Advanced Traveler Information System ◽  
Near Future

An Advanced Traveler Information System (ATIS), a key component of Intelligent Vehicle highway Systems (IVHS) in the near future, will help travelers find locations of restaurants, lodging, gas stations, and rest stops. On typical ATIS displays, which are now being incorporated in some advanced vehicles, the choices for these traveler services are presented to the vehicle occupants alphabetically. An experiment was conducted to determine whether individualizing the display through the use of neural networks enhanced performance when choosing restaurants. The neural network ATIS was compared to an ATIS that displayed the most frequently chosen restaurants at the top, one that alphabetized the list of restaurants, and one that randomly displayed the restaurant choices. The time to choose a restaurant was significantly faster for the individualized displays (neural network and frequency) when compared to the nonindividualized displays (alphabetical and random). When the two individualized displays were compared, choice time was significantly faster for the neural network approach.

Sign in / Sign up

Export Citation Format

Share Document