چكيده به لاتين
Today's world is a world of change and knowing what situation awaits us in the future is an important factor in the preservation and survival of organizations. Every day we face situations and conditions that require predicting the future.
In most manufacturing industries, demand is uncertain and difficult to predict. Calculating the optimal amount and the optimal time to order goods is an important and very strategic issue in every organization. Inventory refers to the storage of any goods or resources that can be used in any organization. An inventory system has a set of rules or policies, which control and support the system's inventory level. It also decides when and to what extent reserves should be recharged. The main concern of every production organization is to minimize total costs and maximize profits. In today's highly competitive market, one mistake is enough to completely destroy the profit of the organization and make the situation of the organization unstable.
In the prediction-based theory, management predicts future events by using a variety of forecasting methods and administrative methods. The purpose of prediction theory is to identify, define and formulate decision-making patterns and facilitate the decision-making process for problem solving. Demand forecasting is one of the main topics of the supply chain. This goal has been to optimize stocks, reduce costs and increase sales, profits and customer loyalty. For this purpose, historical data can be analyzed to improve demand forecasting using various methods such as machine learning techniques, time series analysis, and deep learning models (Salaiz-Firo et al., 2020).
In this research, after reviewing the literature on the subject and reviewing previous research, it was observed that a lot of research has been done in the field of demand forecasting. Also, there is a lot of research in the field of demand forecasting inside and outside the country. However, the review of the literature on car demand forecasting is relatively limited, and so far, the comparison between parametric and non-parametric methods for demand forecasting in this industry has not been considered. Meanwhile, the comparison between two groups of forecasting methods helps to choose a more effective approach. Iran is a developing country and in order to move towards development and be classified as a developed country, the study of vehicle demand forecasting seems to have fruitful results. However, a proper study on personal car demand forecasting is still limited due to the lack of access to statistical data. Therefore, in this thesis, the forecasting of car demand in Kerman Motor Company is discussed, and in order to achieve the goal of the research, different forecasting approaches will be used, and their results will be compared in the group of parametric and non-parametric methods. .
In this regard, the regression method will be selected as a parametric method, and the ant colony algorithm will be selected as a non-parametric method, and the prediction results will be compared with each other.
