Improving Demand Forecasting in Steel Industry - A Case Study
No Thumbnail Available
URL
Journal Title
Journal ISSN
Volume Title
Perustieteiden korkeakoulu |
Master's thesis
Authors
Date
2020-10-21
Department
Major/Subject
Strategy and Venturing
Mcode
SCI3050
Degree programme
Master’s Programme in Industrial Engineering and Management
Language
en
Pages
vii + 80
Series
Abstract
Steel industry is very volatile in nature. Global competition, raw material price fluctuations and position at the upstream of global supply chains are only some of the challenges that increase the volatility. The volatile environment causes more challenges. One way to overcome some of these challenges is demand forecasting. Demand forecasting helps the companies to create better plans, optimize resource usage and prepare for changes in the volatile market. Therefore, accurate demand forecasting is important for the companies that operate in the steel industry. However, it has been unclear how to improve demand forecasting in the steel industry and in the Case Company. This thesis answers the following research question: “How to improve the accuracy of demand forecasting in the Case Company?”. The research included interviews, literature review and data analyses for answering the research question. Concrete output of the case study was an improved macro economical leading indicator based demand forecast of the Case Company’s steel coil demand in Europe. This forecast became the most accurate demand forecast of the Case Company when forecasting beyond two months. Improved accuracy of demand forecasting was of course a positive outcome. However, this study found that it may be more important to focus efforts on decreasing the demand variability instead of trying to implement more accurate forecasting solutions. The problem of too bad forecasting accuracy is often overlooked by simply assuming that the best solution is to get better and more accurate forecasting solutions. In fact, the root cause for bad forecast accuracy is demand fluctuation. Therefore, efforts for smoothening the demand fluctuation should be at least equally important as improving the forecasting methods. This case study thesis contributes to demand forecasting research by finding that macro economical leading indicator based demand forecasting can produce accurate results in the steel industry. In addition, this thesis suggests researchers and practitioners to study demand variability root causes and mitigation opportunities before trying to implement more advanced demand forecasting solutions. For example, mitigating demand variability by adjusting customer incentives by adjusting contracts. The reason is that elements that greatly increase the demand fluctuation might be unknowingly embedded into the operations and contracts of a company and its customers. Knowing the root causes of demand variability also helps choosing the optimal forecasting method.Description
Supervisor
Seppälä, TimoThesis advisor
Seppälä, TimoKeywords
demand forecasting, leading indicator forecasting, demand management, demand variability