University of Twente Student Theses
Efficient Marketing: Economically Integrated Strategies and Short-Term Forecasting
Stok, A.J. (2024) Efficient Marketing: Economically Integrated Strategies and Short-Term Forecasting.
|
PDF
3MB |
| Abstract: | This study at ScanmarQED focusses on developing the AutoForecaster, an automated system for predicting a marketing Key Performance Indicator (KPI) while incorporating relevant economic factors. Once the system is implemented, ScanmarQED aims to use their current Marketing Mix Model (MMM) as a benchmark to compare the results and variables selected by the new forecasting system, seeking to gain new insights automatically. The AutoForecaster selects the best forecasting methods from literature and uses different techniques for economic factors and the marketing KPI, Units Serviced. It applies seven forecasting models for economic factors, four variable selection models to identify important variables influencing the marketing KPI, and eight forecasting techniques to forecast the marketing KPI. The study finds that the Bayesian model outperforms others, balancing complexity and accuracy. The Backward Stepwise Selection method identifies the most influential variables, including the unemployment rate and Vehicle Miles Travelled. Marketing channels like Social, Display, and Video contribute to marketing metrics. The AutoForecaster's integration of financial and marketing models provides actionable insights, optimising marketing strategies with a 30/60/90-day forecast horizon. A PowerBI dashboard ensures real-time data visualisation, enhancing decision-making. Future iterations will incorporate more conditions and constraints to improve predictability and accuracy. |
| Item Type: | Essay (Master) |
| Clients: | ScanmarQED, Houten, The Netherlands |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 31 mathematics, 54 computer science, 83 economics, 85 business administration, organizational science |
| Programme: | Industrial Engineering and Management MSc (60029) |
| Link to this item: | https://purl.utwente.nl/essays/99839 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page