Abstract: By systematically applying different engineering
methods, difficult financial problems become approachable. Using a
combination of theory and techniques such as wavelet transform,
time series data mining, Markov chain based discrete stochastic
optimization, and evolutionary algorithms, this work formulated a
strategy to characterize and forecast non-linear time series. It
attempted to extract typical features from the volatility data sets of
S&P100 and S&P500 indices that include abrupt drops, jumps and
other non-linearity. As a result, accuracy of forecasting has reached
an average of over 75% surpassing any other publicly available
results on the forecast of any financial index.
Abstract: Estimates of temperature values at a specific time of day, from daytime and daily profiles, are needed for a number of environmental, ecological, agricultural and technical applications, ranging from natural hazards assessments, crop growth forecasting to design of solar energy systems. The scope of this research is to investigate the efficiency of data mining techniques in estimating minimum, maximum and mean temperature values. For this reason, a number of experiments have been conducted with well-known regression algorithms using temperature data from the city of Patras in Greece. The performance of these algorithms has been evaluated using standard statistical indicators, such as Correlation Coefficient, Root Mean Squared Error, etc.
Abstract: Social-economic variables influence transportation
demand largely. Analyses of discrete choice model consider
social-economic variables to study traveler-s mode choice and
demand. However, to calibrate the discrete choice model needs to have
plenty of questionnaire survey. Also, an aggregative model is
proposed. The historical data of passenger volumes for high speed rail
and domestic civil aviation are employed to calibrate and validate the
model. In this study, models with different social-economic variables,
which are oil price, GDP per capita, CPI and economic growth rate,
are compared. From the results, the model with the oil price is better
than models with the other social-economic variables.
Abstract: Ranking of fuzzy numbers play an important role in
decision making, optimization, forecasting etc. Fuzzy numbers must
be ranked before an action is taken by a decision maker. In this
paper, with the help of several counter examples it is proved that
ranking method proposed by Chen and Chen (Expert Systems with
Applications 36 (2009) 6833-6842) is incorrect. The main aim of this
paper is to propose a new approach for the ranking of generalized
trapezoidal fuzzy numbers. The main advantage of the proposed
approach is that the proposed approach provide the correct ordering
of generalized and normal trapezoidal fuzzy numbers and also the
proposed approach is very simple and easy to apply in the real life
problems. It is shown that proposed ranking function satisfies all
the reasonable properties of fuzzy quantities proposed by Wang and
Kerre (Fuzzy Sets and Systems 118 (2001) 375-385).
Abstract: Financial forecasting using machine learning techniques has received great efforts in the last decide . In this ongoing work, we show how machine learning of graphical models will be able to infer a visualized causal interactions between different banks in the Saudi equities market. One important discovery from such learned causal graphs is how companies influence each other and to what extend. In this work, a set of graphical models named Gaussian graphical models with developed ensemble penalized feature selection methods that combine ; filtering method, wrapper method and a regularizer will be shown. A comparison between these different developed ensemble combinations will also be shown. The best ensemble method will be used to infer the causal relationships between banks in Saudi equities market.
Abstract: The paper evaluates several hundred one-day-ahead
VaR forecasting models in the time period between the years 2004
and 2009 on data from six world stock indices - DJI, GSPC, IXIC,
FTSE, GDAXI and N225. The models model mean using the ARMA
processes with up to two lags and variance with one of GARCH,
EGARCH or TARCH processes with up to two lags. The models are
estimated on the data from the in-sample period and their forecasting
accuracy is evaluated on the out-of-sample data, which are more
volatile. The main aim of the paper is to test whether a model
estimated on data with lower volatility can be used in periods with
higher volatility. The evaluation is based on the conditional coverage
test and is performed on each stock index separately. The primary
result of the paper is that the volatility is best modelled using a
GARCH process and that an ARMA process pattern cannot be found
in analyzed time series.
Abstract: Due to the liberalization of countless electricity markets, load forecasting has become crucial to all public utilities for which electricity is a strategic variable. With the goal of contributing to the forecasting process inside public utilities, this paper addresses the issue of applying the Holt-Winters exponential smoothing technique and the time series analysis for forecasting the hourly electricity load curve of the Italian railways. The results of the analysis confirm the accuracy of the two models and therefore the relevance of forecasting inside public utilities.
Abstract: Time series models have been used to make predictions of academic enrollments, weather, road accident, casualties and stock prices, etc. Based on the concepts of quartile regression models, we have developed a simple time variant quantile based fuzzy time series forecasting method. The proposed method bases the forecast using prediction of future trend of the data. In place of actual quantiles of the data at each point, we have converted the statistical concept into fuzzy concept by using fuzzy quantiles using fuzzy membership function ensemble. We have given a fuzzy metric to use the trend forecast and calculate the future value. The proposed model is applied for TAIFEX forecasting. It is shown that proposed method work best as compared to other models when compared with respect to model complexity and forecasting accuracy.
Abstract: In this paper, based on the past project cost and time
performance, a model for forecasting project cost performance is
developed. This study presents a probabilistic project control concept
to assure an acceptable forecast of project cost performance. In this
concept project activities are classified into sub-groups entitled
control accounts. Then obtain the Stochastic S-Curve (SS-Curve), for
each sub-group and the project SS-Curve is obtained by summing
sub-groups- SS-Curves. In this model, project cost uncertainties are
considered through Beta distribution functions of the project
activities costs required to complete the project at every selected time
sections through project accomplishment, which are extracted from a
variety of sources. Based on this model, after a percentage of the
project progress, the project performance is measured via Earned
Value Management to adjust the primary cost probability distribution
functions. Then, accordingly the future project cost performance is
predicted by using the Monte-Carlo simulation method.
Abstract: With the prevalence of computer and development of information technology, Geographic Information Systems (GIS) have long used for a variety of applications in electrical engineering. GIS are designed to support the analysis, management, manipulation and mapping of spatial data. This paper presents several usages of GIS in power utilities such as automated route selection for the construction of new power lines which uses a dynamic programming model for route optimization, load forecasting and optimizing planning of substation-s location and capacity with comprehensive algorithm which involves an accurate small-area electric load forecasting procedure and simulates the different cost functions of substations.
Abstract: Nowadays, precipitation prediction is required for proper planning and management of water resources. Prediction with neural network models has received increasing interest in various research and application domains. However, it is difficult to determine the best neural network architecture for prediction since it is not immediately obvious how many input or hidden nodes are used in the model. In this paper, neural network model is used as a forecasting tool. The major aim is to evaluate a suitable neural network model for monthly precipitation mapping of Myanmar. Using 3-layerd neural network models, 100 cases are tested by changing the number of input and hidden nodes from 1 to 10 nodes, respectively, and only one outputnode used. The optimum model with the suitable number of nodes is selected in accordance with the minimum forecast error. In measuring network performance using Root Mean Square Error (RMSE), experimental results significantly show that 3 inputs-10 hiddens-1 output architecture model gives the best prediction result for monthly precipitation in Myanmar.
Abstract: The electric power industry is currently undergoing an unprecedented reform. One of the most exciting and potentially profitable recent developments is increasing usage of artificial intelligence techniques. The intention of this paper is to give an overview of using neural network (NN) techniques in power systems. According to the growth rate of NNs application in some power system subjects, this paper introduce a brief overview in fault diagnosis, security assessment, load forecasting, economic dispatch and harmonic analyzing. Advantages and disadvantages of using NNs in above mentioned subjects and the main challenges in these fields have been explained, too.
Abstract: This study investigates the performance of radial basis function networks (RBFN) in forecasting the monthly CO2 emissions of an electric power utility. We also propose a method for input variable selection. This method is based on identifying the general relationships between groups of input candidates and the output. The effect that each input has on the forecasting error is examined by removing all inputs except the variable to be investigated from its group, calculating the networks parameter and performing the forecast. Finally, the new forecasting error is compared with the reference model. Eight input variables were identified as the most relevant, which is significantly less than our reference model with 30 input variables. The simulation results demonstrate that the model with the 8 inputs selected using the method introduced in this study performs as accurate as the reference model, while also being the most parsimonious.
Abstract: Forecasting the values of the indicators, which
characterize the effectiveness of performance of organizations is of
great importance for their successful development. Such forecasting
is necessary in order to assess the current state and to foresee future
developments, so that measures to improve the organization-s
activity could be undertaken in time. The article presents an
overview of the applied mathematical and statistical methods for
developing forecasts. Special attention is paid to artificial neural
networks as a forecasting tool. Their strengths and weaknesses are
analyzed and a synopsis is made of the application of artificial neural
networks in the field of forecasting of the values of different
education efficiency indicators. A method of evaluation of the
activity of universities using the Balanced Scorecard is proposed and
Key Performance Indicators for assessment of e-learning are
selected. Resulting indicators for the evaluation of efficiency of the
activity are proposed. An artificial neural network is constructed and
applied in the forecasting of the values of indicators for e-learning
efficiency on the basis of the KPI values.
Abstract: The selection for plantation of a particular type of
mustard plant depending on its productivity (pod yield) at the stage
of maturity. The growth of mustard plant dependent on some
parameters of that plant, these are shoot length, number of leaves,
number of roots and roots length etc. As the plant is growing, some
leaves may be fall down and some new leaves may come, so it can
not gives the idea to develop the relationship with the seeds weight at
mature stage of that plant. It is not possible to find the number of
roots and root length of mustard plant at growing stage that will be
harmful of this plant as roots goes deeper to deeper inside the land.
Only the value of shoot length which increases in course of time can
be measured at different time instances. Weather parameters are
maximum and minimum humidity, rain fall, maximum and minimum
temperature may effect the growth of the plant. The parameters of
pollution, water, soil, distance and crop management may be
dominant factors of growth of plant and its productivity. Considering
all parameters, the growth of the plant is very uncertain, fuzzy
environment can be considered for the prediction of shoot length at
maturity of the plant. Fuzzification plays a greater role for
fuzzification of data, which is based on certain membership
functions. Here an effort has been made to fuzzify the original data
based on gaussian function, triangular function, s-function,
Trapezoidal and L –function. After that all fuzzified data are
defuzzified to get normal form. Finally the error analysis
(calculation of forecasting error and average error) indicates the
membership function appropriate for fuzzification of data and use to
predict the shoot length at maturity. The result is also verified using
residual (Absolute Residual, Maximum of Absolute Residual, Mean
Absolute Residual, Mean of Mean Absolute Residual, Median of
Absolute Residual and Standard Deviation) analysis.
Abstract: This paper presents an application of Artificial Neural Network (ANN) to forecast actual cost of a project based on the earned value management system (EVMS). For this purpose, some projects randomly selected based on the standard data set , and it is produced necessary progress data such as actual cost ,actual percent complete , baseline cost and percent complete for five periods of project. Then an ANN with five inputs and five outputs and one hidden layer is trained to produce forecasted actual costs. The comparison between real and forecasted data show better performance based on the Mean Absolute Percentage Error (MAPE) criterion. This approach could be applicable to better forecasting the project cost and result in decreasing the risk of project cost overrun, and therefore it is beneficial for planning preventive actions.
Abstract: In this paper we apply an Adaptive Network-Based
Fuzzy Inference System (ANFIS) with one input, the dependent
variable with one lag, for the forecasting of four macroeconomic
variables of US economy, the Gross Domestic Product, the inflation
rate, six monthly treasury bills interest rates and unemployment rate.
We compare the forecasting performance of ANFIS with those of the
widely used linear autoregressive and nonlinear smoothing transition
autoregressive (STAR) models. The results are greatly in favour of
ANFIS indicating that is an effective tool for macroeconomic
forecasting used in academic research and in research and application
by the governmental and other institutions
Abstract: S-Curves are commonly used in technology forecasting. They show the paths of product performance in relation to time or investment in R&D. It is a useful tool to describe the inflection points and the limit of improvement of a technology. Companies use this information to base their innovation strategies.
However inadequate use and some limitations of this technique lead
to problems in decision making. In this paper first technology
forecasting and its importance for company level strategies will be
discussed. Secondly the S-Curve and its place among other
forecasting techniques will be introduced. Thirdly its use in
technology forecasting will be discussed based on its advantages,
disadvantages and limitations. Finally an application of S-curve on
3D TV technology using patent data will also be presented and the
results will be discussed.
Abstract: In this paper we present a Feed-Foward Neural
Networks Autoregressive (FFNN-AR) model with genetic algorithms
training optimization in order to predict the gross domestic product
growth of six countries. Specifically we propose a kind of weighted
regression, which can be used for econometric purposes, where the
initial inputs are multiplied by the neural networks final optimum
weights from input-hidden layer of the training process. The
forecasts are compared with those of the ordinary autoregressive
model and we conclude that the proposed regression-s forecasting
results outperform significant those of autoregressive model.
Moreover this technique can be used in Autoregressive-Moving
Average models, with and without exogenous inputs, as also the
training process with genetics algorithms optimization can be
replaced by the error back-propagation algorithm.
Abstract: This paper deals with heterogeneous autoregressive
models of realized volatility (HAR-RV models) on high-frequency
data of stock indices in the USA. Its aim is to capture the behavior of
three groups of market participants trading on a daily, weekly and
monthly basis and assess their role in predicting the daily realized
volatility. The benefits of this work lies mainly in the application of
heterogeneous autoregressive models of realized volatility on stock
indices in the USA with a special aim to analyze an impact of the
global financial crisis on applied models forecasting performance.
We use three data sets, the first one from the period before the global
financial crisis occurred in the years 2006-2007, the second one from
the period when the global financial crisis fully hit the U.S. financial
market in 2008-2009 years, and the last period was defined over
2010-2011 years. The model output indicates that estimated realized
volatility in the market is very much determined by daily traders and
in some cases excludes the impact of those market participants who
trade on monthly basis.