University of Twente Student Theses
New Product Forecasting with Analogous Products : Applying Random Forest and Quantile Regression Forest to forecasting and inventory management
Steenbergen, R.M. van (2019) New Product Forecasting with Analogous Products : Applying Random Forest and Quantile Regression Forest to forecasting and inventory management.
|
PDF
4MB |
| Abstract: | Due to market developments and innovations, companies face shorter product life cycles, forcing them to forecast demand for newly introduced products. These forecasts allow them to guide operational decisions, such as procurement and inventory control. However, forecasting the demand of new products is challenging compared to existing products, since historical sales data is not available as an indicator of future sales. Moreover, little attention has been paid in literature to quantitative methods for new product forecasting, especially with respect to quantifying the uncertainty in demand. We present a novel forecasting method demandForest, which combines K-means, Random Forest, and Quantile Regression Forest. This machine learning-based approach combines the historical sales data of previously introduced products and product characteristics of existing and new products to make prelaunch forecasts for new products. demandForest clusters and predicts demand patterns, and predicts the quantiles of the total demand in an introduction period. We validate our approach using real-world data sets of five companies. Compared to multiple benchmark methods, demandForest provides the most accurate predictions (Average decrease of 19% in forecast error), more consistent service levels (3 to 9 percentage points improvement), resulting in potential inventory savings around 15% depending on lead times and service levels. |
| Item Type: | Essay (Master) |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 31 mathematics, 50 technical science in general, 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/79848 |
| 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