Level: Intermediate
TCM Section(s)
11.3. Information Management
7.3. Cost Estimating and Budgeting
Venue: 2024 AACE International Conference & Expo
Abstract: The acquisition of industrial goods is essential to ensuring the functionality of equipment, factories, and operational plants in different companies. Unlike simpler or consumer goods, industrial goods do not have their prices published and, generally, are not part of standardized catalogs. Therefore, an accurate forecast of industrial goods prices is essential for achieving favorable outcomes for companies, whether it be through accurate cost estimates or improving the quality of commercial negotiations.
This project involves the application of data mining and machine learning techniques in typical databases of industrial goods. Examples of techniques used include classification algorithms, regression, and neural networks.
In the present work, the techniques were applied to three distinct typical databases: database 1 - items with simple technical characteristics like common materials from the supplier market without manufacturing complexity; database 2 - operational items with specific and standardized technical characteristics; and database 3 - items with complex technical characteristics, normally associated with large equipment.
The work conclusion aims to determine the most efficient machine learning models for each database and develop a guide for estimating the cost of different industrial goods.
TCM Section(s)
11.3. Information Management
7.3. Cost Estimating and Budgeting
Venue: 2024 AACE International Conference & Expo
Abstract: The acquisition of industrial goods is essential to ensuring the functionality of equipment, factories, and operational plants in different companies. Unlike simpler or consumer goods, industrial goods do not have their prices published and, generally, are not part of standardized catalogs. Therefore, an accurate forecast of industrial goods prices is essential for achieving favorable outcomes for companies, whether it be through accurate cost estimates or improving the quality of commercial negotiations.
This project involves the application of data mining and machine learning techniques in typical databases of industrial goods. Examples of techniques used include classification algorithms, regression, and neural networks.
In the present work, the techniques were applied to three distinct typical databases: database 1 - items with simple technical characteristics like common materials from the supplier market without manufacturing complexity; database 2 - operational items with specific and standardized technical characteristics; and database 3 - items with complex technical characteristics, normally associated with large equipment.
The work conclusion aims to determine the most efficient machine learning models for each database and develop a guide for estimating the cost of different industrial goods.