The company which provided the dataset is the world leader in manufacturing of construction and mining equipment, diesel and natural gas engines, industrial gas turbines and diesel-electric locomotives. The current revenue of the company is estimated to be on the order of tens of billions and they sell products and parts via a worldwide dealer network. The company sells more than 3 million products and 700,000 parts in more than 20 countries around the world every year. They operate with more than 3,000 suppliers and 3,000 dealerships and their logistics operations alone are worth more than 60 million dollars per year.
The dataset provided is one example of supply chain problem for one product of the company - a medium size excavator. In the current dataset, the number of dealers, production facilities and shipping ports is the same as in the original problem; it is only the demand figures, the production capacities, the transportation times and costs and the sale prices that have been randomly generated. The figures have been generated according to a normal distribution with the same mean and standard deviation as in the original dataset (e.g. the demand figures have the same mean and standard deviation as those found in the original problem).
The dataset has been extended with 9 more years of demand distributions. The additional 9 years have been created with the same random problem generator. The purpose of the dataset is to provide more instances of the problem. The dataset may be interpreted as containing 10 years of demand for one product or the demand figures of 10 similar products. For instance, we adopted this dataset in a machine learning context to have a larger and more comprehensive training set.