Sharif Digital Repository

Generally, nowadays, machine learning methods are used in many different areas for their superiority over other methods of prediction. Although being a tough task, stock market prediction with machine learning approaches is being spread due to satisfying results published ever yday. Machine learning methods usually use varied kinds of data ,including structured data such as market data, technical indicators and some fundamental data as well as unstructured one entailing text and graph data in order to enhance their predictability capacity. In this thesis we aimed to find out more about the importance and the contribution of structured data in prediction and we tried to attain a framework... 

Fulfilling the demands of customers, used to be the main purpose of Supply Chain Network Designers. Soon after that, the environmental concerns created the concept of Reverse Logistic in order to prevent goods from being scattered in the environment after their disposal. Governmental regulations and people's concerns, forced the factories to gather the created pollutions of the environment. They gradualy confessed the positive impacts of these ruturns on their financials. The flow of forward and reverse logistics establishes a Closed-Loop in which the returning economical circumstances were transferd into original factories. Later, Open-Loops were created. In open-loops the returns have to... 

Nowadays best using of fossil fuels sources of the country (and) importance of comparison against lack of capacity in petrol production make determined the programmers and the directors to foresee and design expanded programs of the goals, to use natural gas for car fuels. To reach fulfillment of these programs, the confirmed needs of the natural gas cylinders are improved and make it essential to invest on producing compressive natural gas cylinders. In this way economical and technical change researches has been done in order to construct on department to produce 200,000 compressive natural gas cylinders in a year during two sets.(shifts) According to the results of technical researches... 

Queuing systems and their optimization have always been an important concern of every society. It has been a long time that people understand that with quantifying the queues they are standing on, they can save great amount of money and time. Because of that fact, they have been studying these systems, and reached to the interesting conclusions. These researches have shown that there exist a couple of equilibriums in every queuing system, such as: speed-price and speed-quality equilibriums.Knowing these equilibriums along with modeling them will help us optimize queues. The importance of this optimization is its incredible effect on cost reduction in economical and social queues. In many... 

Price and warranty are two powerful marketing tool that can stimulate consumers’ purchase willingness. Therefore, producers must choose the appropriate price and warranty that can stimulate customers to purchase the quantity that will achieve the maximum profit. This study investigates optimal strategies for price and warranty length of a new product to maximize profit of a producer during lifecycle of the product. We consider both durable products and non-durable ones. Customers buy non-durable products many times but if we consider the planning horizon relatively short, each customer buys one product during the period. So, the market for non-durable products is static and for durable ones... 

When demand for a product is price sensitive, pricing and lot sizing decisions are interdependent. Similarly, when a product is highly perishable, the demand may need to be backlogged to avoid costs due to deterioration, i.e., perishability and backlogging are complementary conditions.In this thesis we stablish two economic production quantity models for deteriorating items under conditions of finite production, exponential decay and partial backordering and lost sale. Two joint pricing inventory control models are developed for the problem by employing different modeling approaches over an infinite planning horizon. In two models, customer is viewed to be impatient and the fraction of the... 

Today, many organizations and companies are confronted with enormous competition and uncertainty as a result of factors such as political issues, demand fluctuations, technological change, and financial instability As well as increasing business competitiveness, organizations focus on their core activities and lead to the use of outsourcing strategies, These factors are the cause of the formation of the supply chain And the lack of planning and identifying the factors that cause instability in the supply chain leads to its inaccurate performance. World-class organizations today have found that unintegrated production and distribution processes and poor communication with suppliers and... 

The thesis has considered a two-echelon supply chain which consists of one central warehouse and multiple retailers. Assume all retailers and the warehouse follow a continuous review inventory model. The costumer’s demand comes to retailers in a Poisson process. The retailers replenish their stocks from the warehouse in an (S-1, S) inventory control policy and the warehouse replenishes its stocks in an (r, Q) inventory control policy from an external supplier with an infinite capacity. It may be more representative to model stockouts as lost sales when the retailers are in a competitive market or in monopoly markets all demand will be backorder. Therefore, if the market situation goes... 

Pistachio trade in Iran is of great importance in non-oil exports, and this country has been the main producer of this product for many years. In recent years, unfortunately, pistachio products have fallen sharply in the country, and on the other hand, the United States has been able to take a large share of the global market. The researchers have presented numerous reviews about the causes of this problem, most notably drought and water scarcity, inefficient agriculture, and the lack of comprehensive and efficient management of the pistachio supply chain. In this research, to address these problems, attention has been paid to sustainable supply chain management that addresses three... 

Risk management is one of the important phases of a project life cycle. There are several quantitative and qualitative methods to determine and plan the proper reaction risks in a project. These methods aim to prevent additional and unnecessary costs. Project managers, stake holders and beneficiaries always believe that risk management of project engineering as one of the importance parts. Although there are multiple methods that can evaluate risk, but there is still research problems especially for risk qualitative and quantitative prediction. This gets more serious after evaluating and minimizing risks effects considering the other risks’ damaging effects which have not been considered. In... 

Predicting oil prices, especially in exporting countries, will help governments in the policy-making process by obtaining a reliable estimate of oil revenues. The existence of a complex mechanism governing the process of oil price formation has reduced the efficiency of linear models in forecasting and led researchers to use nonlinear intelligent systems to predict oil prices. In this study, after a detailed study of the structure of artificial neural network, two models of neural network GMDH and MLP and ARIMA method have been used to predict oil price. There are important factors in the prediction process with neural networks, and if all these factors are selected correctly; One can expect... 

There are several types of uncertainty in supply chains that cause some difficulties in the planning of a supply chain. Uncertainty on the supply side can cause interruptions in the quality, quantity, or delivery time of orders. To avoid such interruptions, retailers usually contract with two different suppliers for a common good. In this setting, one of the suppliers has higher reliability and higher price, while the other supplier offers a lower price but has a lower level of reliability. In other words, to ensure a lower level of uncertainty, retailers have to pay more. This is one of the main tradeoffs in the dual sourcing strategy. In this thesis, we consider a two-echelon supply chain... 

The use of drones in various fields is increasing. One of the applications that can be mentioned for drones is humanitarian areas can include drug supply chains, blood supply chains, relief chains, and the like. The use of these unmanned vehicles in humanitarian areas poses legal challenges compared to other areas. This study aimed to investigate drones following a disaster, the essential role of UAVs, and a vehicle to carry out relief operations. Following a disaster, infrastructure can be severely damaged, and the destruction of infrastructure can reduce the efficiency of land vehicles. In this research, “drone and vehicle routing problem” have been done to provide relief and minimize the... 

Despite the significant progress of machine learning models in the health domain, current advanced methods usually produce non-transparent and black-box models, and for this reason, they are not widely used in medical decision-making. To address the issue of non-transparency in black-box models, interpretable machine learning models have been developed. In the health domain, counterfactual scenarios can provide personalized explanations for predictions and suggest necessary changes to transition from an undesirable outcome class to a desirable one for physicians. The aim of this study is to present an interpretable machine learning framework in the health domain that, in addition to having... 

Although inventory control under discrete demand in dynamic quantities and time intervals are very common in reality, existing literature has largely ignored them. In this thesis, we investigate the inventory control decisions in a two echelon supply chain. The vendor supplies a product to several retailers, buying discrete quantities in pre-determined time intervals. The order quantity and order cycles for each retailer can be different from others. We have developed a new efficient algorithm to find the optimal ordering policy involves the scheduling and the order quantity of vendor to his supplier to minimize his cost function in infinite time horizon. Moreover, we have designed a revenue... 

Although, planning and control systems improved, but most of projects have some Problems such as long time and high cost. In project oriented organizations which Perform several projects have more problems. An important reason of these Problems is lack of skill and competency of executive factors and project managers In planning and control. These persons are chosen base on organization Relationship, not systematically. One way to become successful in projects is Chose and assessment of project managers and executes in right way. "System of Competency and assessment of project manager" is offered to solve this problem. According to this system, at first projects are defined and grouped base... 

In this Thesis pricing has been used in Job-shop scheduling problem in detailed scheduling point of view. Also, in this study, due date is price-dependent variable in wich the manufacturer has the ability to choose one item from some pairs of prices and due dates for every jobs in order to maximize the total profit, i.e. revenue less scheduling cost. In this problem, total weighted tardiness has been choosen for scheduling cost. In this research, pairs of prices and due dates has been studied. According to the complexity of this problem, a Genetic algorithm has been proposed to solving the problem. As a managerial insight, it shown that joint optimization of pricing and scheduling decisions... 

The research has tried to identify obstacles before and during project implementation within the supply chain in electronic markets, using fuzzy model complex relationships among the obstacles to be checked in order to determine the degree of importance of each of these methods actually weights of each of these obstacles will it was, visibility and better understanding of the existing situation to be considered and implemented solutions to overcome them. In this study, the identification of appropriate criteria for supplier selection in electronic markets and prioritizing them are addressed. After filling the questionnaire by staff in the process of the results and obtain a final decision of... 

Today, the major part of the capital of each country, especially developing countries, is devoted to its construction and construction projects. On the other hand, one of the growth and economic factors of any society is the success of its development projects. In fact, one of the activities of developing countries to build economic infrastructure is the implementation of infrastructure development projects that account for the bulk of the country's budget annually, and therefore the principled planning of these projects is from the requirements and it is necessary to achieve the lowest cost-to-productivity ratio. In Iran, which is considered as a developing country, a significant amount is...