Marcinkevičius, Virginijus

Recently, customized manufacturing is gaining much momentum. Consumers do not want mass-produced products but are looking for unique and exclusive ones. It is especially evident in the furniture industry. As it is necessary to set an individual price for each individually manufactured product, companies face the need to quickly estimate a preliminary cost and price as soon as an order is received. The task of estimating costs as precise and timely as possible has become critical in customized manufacturing. The cost estimation problem can be solved as a prediction problem using various machine learning (ML) techniques. In order to obtain more accurate price prediction, it is necessary to delve deeper into the data. Data visualization methods are excellent for this purpose. Moreover, it is necessary to consider that the managers who set the price of the product are not ML experts. Thus, data visualization methods should be integrated into the decision support system. On the one hand, these methods should be simple, easily understandable and interpretable. On the other hand, the methods should include more sophisticated approaches that allowed reveal hidden data structure. Here, dimensionality-reduction methods can be employed. In this paper, we propose a data visualization process that can be useful for data analysis in customized furniture manufacturing to get to know the data better, allowing us to develop enhanced price prediction models.

Accurate cost estimation at the early stage of a construction project is a key factor in the success of most projects. Many difficulties arise when estimating the cost during the early design stage in customized furniture manufacturing. It is important to estimate the product cost in the earlier manufacturing phase. The cost estimation is related to the prediction of the cost, which commonly includes calculation of the materials, labor, sales, overhead, and other costs. Historical data of the previously manufactured products can be used in the cost estimation process of the new products. In this paper, we propose an early cost estimation approach, which is based on machine learning techniques. The experimental investigation based on the real customized furniture manufacturing data is performed, results are presented, and insights are given.