University of Twente Student Theses

Login

Improving the planning process by developing a forecasting model : predicting future demand based on historical information

Verkerk, Lotte (2022) Improving the planning process by developing a forecasting model : predicting future demand based on historical information.

[img] PDF
1MB
Abstract:This research is conducted at Mainfreight’s Transport Branch in 's-Heerenberg which offers domestic and international transport services. This research focuses on predictive information that contributes to a better and timely estimation of the expected demand of domestic planning which can be used to arrive at a better distribution of the collective vehicle capacity between domestic and international transport. For that purpose, we develop a forecast model which predicts the demand of domestic planning with a time interval of one day and lead times from one day to two weeks ahead. Time series data of the demand for domestic planning, collected at daily intervals, reveals a within-week and within-year seasonal cycles. In addition, the data shows that national holidays also significantly affect the demand on the day itself and surrounding days. Considering these characteristics of the demand, we propose three forecasting models proposed: Exponential smoothing, seasonal ARIMA, and rule-based forecasting. The current forecasting approach is reconstructed so that it can be used as a benchmark in terms of forecasting performance. The results show that rule-based forecasting has the highest performance. Compared to the current forecasting approach, the rule-based forecasting model increases the performance by 44.2% in terms of mean absolute deviation.
Item Type:Essay (Bachelor)
Clients:
Mainfreight Forwarding Netherlands, 's-Heerenberg, Netherlands
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:54 computer science, 58 process technology, 85 business administration, organizational science
Programme:Industrial Engineering and Management BSc (56994)
Link to this item:https://purl.utwente.nl/essays/92990
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page