Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 52880 (01)
- University: Sharif University of Technology
- Department: Industrial Engineering
- Advisor(s): Rafiee, Majid; Kayvanfar, Vahid
- Abstract:
- Demand forecasting has always been a concern for business owners as one of the main activities in supply chain management. Unlike the past that forecasting was carried out by means of limited amount of information, today, forecasting is performed using machine learning algorithms and data-driven methods with the advent of new technologies and data explosion. Patterns and trends of demand, customer information and preferences, comments and suggestions, post-consumption feedbacks are some types of data which are used in these approaches. Considering the all mentioned changes, traditional statistical methods and techniques such as time series analysis have bias in predicting these kind of data and do not have acceptable accuracy. So, machine learning algorithms have been more popular and replaced in recent years in the literature. In this study, K-nearest neighbors (KNNs), decision tree, gradient boosting, extreme learning machine and multi-layer perceptron have been employed as predictor for analyzing customer information and forecasting the customers’ demand. In order to select the best method, the obtained results are compared. By doing so, the obtained results show that the artificial neural network based methods outperform the other employed algorithms
- Keywords:
- Demand Forecasting ; Data Mining ; Machine Learning ; Data-driven Supply Chain ; Big Data Analytics ; Extreme Learning Machine
Digital Object List
-
محتواي کتاب
- view
Bookmark