Loading...
Search for: forecasting
0.256 seconds

    Stock Price Forecasting Using Neural Networks and Fuzzy Logic

    , M.Sc. Thesis Sharif University of Technology Alizadeh, Parisa (Author) ; Shavandi, Hassan (Supervisor)
    Abstract
    This research proposes a novel hybrid method for stock price index forecasting relying on technical analysis, the fundamental analysis of capital market, neural networks technology, and fuzzy logic. The new method shows a good performance comparing complicated and time-consuming forecasting methods. Several factors influence stock price; for example, an important one is the previous trend of stock price. Fortunately, by developing technical analysis and introducing the various indices of this method the maximum use of historical data is made in order to forecast future prices. Another kind of factors is macro-economic variables that their influence on the long-term trends of the stock... 

    Urban Water Demand Forecasting with Dynamic Artificial Neural Networks

    , M.Sc. Thesis Sharif University of Technology Fa'al, Fatemeh (Author) ; Abrishamchi, Ahmad (Supervisor)
    Abstract
    The water demand forecasting is an important activity for successful planning, utilization and operation of urban water supply and distribution systems. The population growth result in water consumption growth, also the restriction of water resources lead to pay more attention to the water demand management. The unexpected droughts, financial crises, over-use of water resources, or inessential infrastructure development are the outcome of poor water demand prediction and inflexible water resource management. This research is addressed the daily short-term (two week ahead), weekly medium-term (six months ahead), and monthly long-term (two years ahead) water demand. The dynamic artificial... 

    Forecasting and Optimization a Portfolio Using Robust Optimization

    , M.Sc. Thesis Sharif University of Technology Badri, Hamid Reza (Author) ; Modarres Yazdi, Mohammad (Supervisor)
    Abstract
    In this Thesis, a multi period portfolio optimization consisting stocks, gold and risk free asset is considered, in which periodical reinvestment and withdrawing is possible. Maximizing the net present value of investor’s cash flow is the objective. Due to the existence of uncertain parameters, two robust counterpart models are developed. In the first model, a conservative robust model is presented to generate feasible solution in all cases. In the second one, the conservative degree of investor is adjustable to control the risk of the model by investor appropriately. For evaluating the proposed models, the data of 5 well known stocks of Tehran market and gold prices are gathered. By using... 

    Forecasting Financial Market Case Study: Tehran Stock Market

    , M.Sc. Thesis Sharif University of Technology Samadi, Mohammad Reza (Author) ; Modarres Yazdi, Mohammad (Supervisor)
    Abstract
    In this thesis, we examine different forecasting methods to predict volatility in financial markets. Tehran Exchange Price Index (TEPIX) is adapted to forecast in short and long term periods. TEPIX is the most important index in Tehran Stock Market which is officially reported daily. Autoregressive Integrated Moveing Average models (ARIMA), Generalaized Autoregressive Heteroskedastic models (GARCH) and Artificial Neural Networks (ANN) are used for forecasting TEPIX. Spectral Analysis is also regarded as a completely new approach in financial mathematics to forecast TEPIX in short and long term periods. We consider different criteria to compare the performance of different methods of... 

    Prediction of Microstructure Evolution of Severely Deformed Pure Aluminum during Annealing

    , M.Sc. Thesis Sharif University of Technology Jafari, Rahim (Author) ; Kazeminezhad, Mohsen (Supervisor)
    Abstract
    Severe Plastic Deformation (SPD) Processes have drawn lots of attention due to their ability to refine grain size and develop some properties of bulk metals and alloys. After deformation, however, ductility and formability of metals are reduced. Annealing has been used as a solution for improvement of these characteristics after deformations even after SPD processes. On the other hand, there is a possibility that during annealing grains could grow, therefore it can neutralize the effect of SPD process. Consequently, predicting behavior and evolution of microstructure during annealing finds an important role. In this research, accordingly, vertex model have been used in order to predict... 

    Forecasting of Energy Price for Industrial Consumption Using Intelligent Algorithms

    , M.Sc. Thesis Sharif University of Technology Mirsoltani, Mercede (Author) ; Akhavan Niaki, Mohammas Taghi (Supervisor)
    Abstract
    Forecasting of energy price and consumption is essential in making managerial decisions and plans effectively and efficiently. It is a valuable technique in economic and/or engineering decisions. While there are many sophisticated mathematical methods developed so far to forecast prices and consumption, nature-based intelligent algorithms have been developed recently. Generally, high accuracy, quick responding, and ability to solve complicated models that are some desired characteristics of artificial intelligence algorithms help decision-makers to come up with good solutions to their problems. The main objective of this research is short term forecasting the energy price and consumption in... 

    Using Echo State Networks for Modeling and Prediction of Drought Based on Remote Sensing Data

    , M.Sc. Thesis Sharif University of Technology Mohammadinejad, Amir (Author) ; Jalili, Mahdi (Supervisor)
    Abstract
    Iran is regarded as a dry land and has suffered from extreme to severe drought conditions in recent years. Drought – which is mainly caused by shortage in rainfall – affects the normal life in Iran. Development of tools for effectively monitoring and predicting drought intensity might help the policy makers to reduce the vulnerability of the areas affected by drought. In this thesis, we showed that the intensity of drought can be predicted using satellite imagery data and recurrent neural networks. To this end, the standardized precipitation index (SPI) was chosen as an index for drought and normalized deviation of vegetation index (NDVI) as a remote sensing measure extracted from NOAA-AVHRR... 

    Application of a Novel Approach of Artificial Intelligence in Forecasting Global Solar Radiation and Gas Consumption in Iran

    , M.Sc. Thesis Sharif University of Technology Saeidi Ramyani, Sara (Author) ; Shavandi, Hassan (Supervisor)
    Abstract
    Energy is of the essential elements to improve every nation’s economy and society, which is influenced by a variety of parameters. Thus many empirical methods have been represented to assess the said parameters using other parameters by which they are affected. In this research, Linear Genetic Programming method (LGP) has been used for assessment, which has been applied to project the global shining of the sun in two Iranian metropolises (Tehran and Kerman), and also natural gas utilization in both industrial and domestic sectors. In this research, authentic data from the empirical results existing in technical documents has been used to develop the models. Most prevalent effective... 

    Evaluation of GARCH Forecasting Performance Under Different Error Term Distributions

    , M.Sc. Thesis Sharif University of Technology Khajian, Hamideh (Author) ; Zamani, Shiva (Supervisor)
    Abstract
    Volatility is the most important components in numerous finance applications. So, the methods of volatility forecast with reasonable accuracy require a deep attention.In this thesis with considering several distributions for error term, GARCH forecasting performance is evaluated on the intra- day data of "Foolad" stock returns by two loss functions of "MAE" and "HMAE". This evaluation is done in three forecast horizons, 1 day, 5 days and 20 days. Finally, the result of this study is as follows. GARCH (1, 1) forecast model with skewed t- student error distribution has the minimum value in the both loss functions for 1 day and 5 day forecast horizons. Also GARCH (1, 1) forecast model with t-... 

    Probabilistic Model to Forecast Activities Completion Time in Ongoing Mass Housing Projects Case Study: The 10,000-Unit Mass Housing Project Executed by Kayson Company in Venezuela

    , M.Sc. Thesis Sharif University of Technology Baqerin, Mohammad Hassan (Author) ; Shafahi, Yusef (Supervisor) ; Mortaheb, Mohammad Mehdi (Co-Advisor)
    Abstract
    Reliable forecasting is a fundamental element of successful project management. Construction managers regularly control and monitor their project in order to ensure that their project performance is under control and within the acceptable control limits. Conventionally, the earned value method (EVM) is used to monitor project cost performance. However, its application to schedule performance using schedule performance index (SPI) has been widely questioned both by practitioners and researchers particularly due to poor accuracy early in the project. This study presents a novel activity-based framework, namely Weibull Evaluation and Forecasting Method (WEFM), for stochastic evaluation and... 

    Considering the Bullwhip Effect Regarding the Ordering Policy and Demand of Ultimate Customer and Representing Solutions to Reduce the Mentioned Effect

    , M.Sc. Thesis Sharif University of Technology Safikhani, Alireza (Author) ; Ghasemi, Farhad (Supervisor)
    Abstract
    Today, with advances in technology and communication equipments, supply chain management plays an important role in different industries. Bullwhip effect is the significant factor which can reduce efficiency of supply chain and increases costs and lead time of services and products to the ultimate customer. In this thesis we have investigated on forecasting method and ordering policy in the bullwhip effect. Basic model based on beer game, moving average, Holt and Brown are 4 models which were studied. Also we defined desired stock and desired stock line which the difference between desired and actual stock and also difference between desired and actual stock line in any period, have... 

    Modeling Tsunami Wavesand Designinga Warning Systemfor This Phenomenon by UseofIT (Case Study the Sea of Oman)

    , M.Sc. Thesis Sharif University of Technology Namdar, Khashayar (Author) ; Abbaspour Tehrani, Majid (Supervisor)
    Abstract
    Tsunami, like many other natural disasters leaves people a short time for escape. When talking about Tsunami, the escape time is the period it takes for the wave to start moving from the epicenter, change into a giant wave gradually and reach to a cost. In order to minimize damages of this phenomenon, the escaped time has to be estimated without delay. For this purpose the first needed action is modeling the Tsunami waves. Analytical and numerical models and software that are designed based on them do exist. To have an efficient and rapid Tsunami alarming system all of these options are examined in this project. Then having a reliable model quite a few probable scenarios are propounded. The... 

    Development of Pavement Performance Prediction Models Based on the Assumptions of Availablity and Ubavailabilty of Accurate Data

    , M.Sc. Thesis Sharif University of Technology Ziyadi, Mojtaba (Author) ; Tabatabaei, Nader (Supervisor) ; Shafahi, Yusof (Supervisor)
    Abstract
    Accurate prediction of pavement performance is essential to a pavement infrastructure management system. Selection of the prediction model is based on the extent of available data, assumptions used in performance modeling, ease of use and management purposes. Therefore, two methods were proposed in this thesis based on the assumptions of availability and unavailibility of accurate data. The first method presents a two-stage model to classify and accurately predict the performance of a pavement infrastructure system. Sections with similar characteristics are classified into groups using a support vector classifier (SVC). Then, a recurrent neural network (RNN) is utilized to predict... 

    Real-Time Traffic Flow Forecasting and Travel Time Prediction

    , M.Sc. Thesis Sharif University of Technology Mahini, Mohammad (Author) ; Habibi, Jafar (Supervisor)
    Abstract
    There has been great progress in Intelligent Transportation Systems (ITS) during the past decade. It is often difficult to manage vehicle traffic systems due to high variations and complexity. Intelligent Transportation Systems try to devise more efficient and more reliable solutions for vehicle traffic systems. Many ITS applications rely on short-term predictions of traffic state and it is crucial to provide reliable estimates of the traffic state in near future.Providing an accurate estimate of transportation time in a specific piece of street is a key task in Intelligent Traffic Systems (ITS). This estimate can be either for the moment or a future prediction. A practical ITS must be... 

    Estimation of Reservoir Performance Parameters Using Percolation Approach

    , Ph.D. Dissertation Sharif University of Technology Sadeghnejad Limouei, Saeeid (Author) ; Masihi, Mohsen (Supervisor) ; Shojaei, Ali Akbar (Supervisor) ; Pishvaie, Mahmoud Reza (Co-Advisor) ; Rabert King, Peter (Co-Advisor)
    Abstract
    The conventional approach to investigate the reservoir performance is to build a detailed geological model, upscale it, and finally run flow simulation which is computationally very expensive. In addition, during the early stage of life of a reservoir, due to the lake of certain data, this method is usually based on analogues or rules of thumb and not detailed reservoir modelling. Therefore, there is a great incentive to produce much simpler physically-based methodologies. The main focus of this thesis is to use percolation approach to estimate the uncertainty in the reservoir properties. This method considers a hypothesis that the reservoir can be split into either permeable (i.e.... 

    Long-Term Water Demand Forecasting for the Tehran City under Uncertainties

    , M.Sc. Thesis Sharif University of Technology Miraki, Ghasem (Author) ; Abrishamchi, Ahmad (Supervisor)
    Abstract
    Forecasting model of water consumption amounts could be used in order to manage water resources for future condition of city. In this thesis, a model for forecasting water demand for Tehran has been presented by evaluating regression models and intelligent models. In this study, uncertainties which are connected to climate and population changes are taken into account. The considered variables include minimum, maximum and medium temperature, precipitation and solar radiation. Considering objectives of this thesis and various forecasting methods and their advantages and regional conditions of Tehran, in addition to regression analysis, perceptron neural network, probabilistic neural network... 

    Meteorological Drought Forecasting Using Conjunctive Model Of Adaptive Neuro Fuzzy Inference System And Wavelet Transforms (Case Study: Urmia Lake Watershed

    , M.Sc. Thesis Sharif University of Technology Soleimani, Arash (Author) ; Abrishamchi, Ahmad (Supervisor)
    Abstract
    Drought is a common phenomena which has a lot of unwanted conse-quences on human being life and environment. Drought forecasting plays a significant role in water resources and environmental systems. Considering IRAN inappropriate location which is on the arid and semi-arid area of the earth and Widespread damages which are related to drought during recent years in iran; importance of developing an accurate model by using new technologies becomes quite inevitable. In the last decay Neural Networks have appeared very useful in non-Stationary and non-linear time Series forecasting and modeling.
    This study is about to use conjunctive model of adaptive neuro fuzzy inference system and... 

    Lifetime-Aware Resource Allocation in Cloud Computing for Energy Optimization

    , M.Sc. Thesis Sharif University of Technology Moghadam, Marziyeh (Author) ; Goudarzi, Maziar (Supervisor)
    Abstract
    Cloud computing is a way to increase capacity or add capabilities dynamically without investing in new infrastructure. The purpose of this project is the use of specialized algorithms for efficient energy management for cloud computing environments.One of the issues that is very important with respect to cloud computing is considering lifetime of servers or physical machines. Servers are some of the most important and critical elements of cloud computing. Server costseffect on the costs of the entire cloud computing system and the interference of serverseffects on entire system. Lifetime of each sever is dependent on a few factors, the most important of which is the number of switching... 

    Forecasting Crude Oil Prices: A Comparison between Artificial Neural Networks and Vector Autoregressive Models

    , M.Sc. Thesis Sharif University of Technology Ramyar, Sepehr (Author) ; Kianfar, Farhad (Supervisor)
    Abstract
    Crude oil is a key element in world economy and the most widely traded form of energy. Therefore, a clear and effective understanding of crude oil price behavior is of great importance for businesses, governments and policy makers. Taking into account the exhaustible nature of crude oil and impact of monetary policy along with other major drivers of crude oil prices, this paper investigates predictability of oil prices using artificial neural networks. A Multilayer Perceptron (MLP) neural network is developed and trained with historical data from 1980 to 2014 and using mean square error (MSE) for testing data, optimal number of hidden layer neurons is determined. Meanwhile, an economic model... 

    Improved Supply Chain Management Performance by Applying Hybrid Forecast Method

    , M.Sc. Thesis Sharif University of Technology Shiri, Davood (Author) ; Hajji, Alireza (Supervisor)
    Abstract
    In today’s competitive world, using an efficient forecast method is necessity for companies. To now, many forecast methods have been developed, but many of them have not an expected efficiency. In this research, we develop a new hybrid forecast method with application of forecasting retails demand. The hybrid method is the combination of ARIMA method and neural networks. To test the efficiency of the method we use the 96 weeks data of plastic containers demand. We also comprise the hybrid method with other forecast methods including naïve method, ARIMA method and neural network method by applying root mean square error and mean absolute percentage error indexes. In the case of plastic...