Dynamic pricing for hotel rooms when customers request multiple-day stays
Prominent hotel chains quote a booking price for a particular type of rooms on each day and dynamically update these prices over time. We present a novel Markov decision process (MDP) formulation that determines the optimal booking price for a single type of rooms under this strategy, while consider...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Institutional Knowledge at Singapore Management University
2015
|
| Subjects: | |
| Online Access: | https://ink.library.smu.edu.sg/lkcsb_research/5147 https://ink.library.smu.edu.sg/context/lkcsb_research/article/6146/viewcontent/DynamicPricingHotelRooms_2015_wp.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Singapore Management University |
| Language: | English |
| Summary: | Prominent hotel chains quote a booking price for a particular type of rooms on each day and dynamically update these prices over time. We present a novel Markov decision process (MDP) formulation that determines the optimal booking price for a single type of rooms under this strategy, while considering the availability of rooms throughout the multiple-day stays requested by customers. We analyze special cases of our MDP to highlight the importance of modeling multiple-day stays and provide guidelines to potentially simplify the implementation of pricing policies around peak-demand events such as public holidays and conferences. Since computing an optimal policy to our MDP is intractable in general, we develop heuristics based on a fluid approximation and approximate linear programming (ALP). We numerically benchmark our heuristics against a single-day decomposition approach (SDD) and an adaptation of a fixed-price heuristic. The ALP-based heuristic (i) outperforms the other methods; (ii) generates up to 7% and 6% more revenue than the SDD and the fixed-price heuristic respectively; and (iii) incurs a revenue loss of only less than 1% when using our pricing structure around peak-demand events, which supports the use of this simple pricing profile. Our findings are potentially relevant beyond the hotel domain for applications involving the dynamic pricing of capacitated resources. |
|---|