A data-driven optimization method for bundle pricing
In practice, many retailers use bundle pricing strategy in their businesses. The retailer decides not only the prices of each individual products, but also the bundle prices to maximise his expected revenue. However, the pricing decision gets complicated when the number of products involved increase...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156867 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | In practice, many retailers use bundle pricing strategy in their businesses. The retailer decides not only the prices of each individual products, but also the bundle prices to maximise his expected revenue. However, the pricing decision gets complicated when the number of products involved increases. This paper aims to explore a data-driven approach to solve bundle pricing problem. We first apply a decision tree to model the consumer’s sequential choice behaviour in purchasing products. Based on the sequential choice model, we have constructed a bundle pricing optimisation model with an additional set of bundle pricing constraints. We further estimate the parameter values for the sequential choice model from sales data using maximum likelihood estimation (MLE) model. With the estimated parameter values, the optimal price can be obtained by solving a mixed integer linear program. Finally, numerical experiment using synthetic data demonstrates the accuracy of our estimation model and case study is conducted to determine the optimal price and profit using our approach. |
|---|