Pricing problems with Thompson sampling
In 1933, William R. Thompson proposed an algorithm known as Thompson sampling in order to maximise culmulative payo in a multi-armed bandit (MAB) problem. MAB problems have been fre- quently used to model real-life decision making scenarios. This pa- per explores the extension of Thompson sampl...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/77144 |
| _version_ | 1811679510706257920 |
|---|---|
| author | Lee, Samuel Wai Leong |
| author2 | Yan Zhenzhen |
| author_facet | Yan Zhenzhen Lee, Samuel Wai Leong |
| author_sort | Lee, Samuel Wai Leong |
| collection | NTU |
| description | In 1933, William R. Thompson proposed an algorithm known as
Thompson sampling in order to maximise culmulative payo in a
multi-armed bandit (MAB) problem. MAB problems have been fre-
quently used to model real-life decision making scenarios. This pa-
per explores the extension of Thompson sampling to other problems
beyond the MAB setting. More speci cally, Thompson sampling is
applied to product sales using data from a real dataset in a dynamic
pricing setting as part of the multi-product pricing problem. |
| first_indexed | 2024-10-01T03:10:18Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/77144 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:10:18Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | ntu-10356/771442023-02-28T23:12:11Z Pricing problems with Thompson sampling Lee, Samuel Wai Leong Yan Zhenzhen School of Physical and Mathematical Sciences DRNTU::Science::Mathematics::Statistics In 1933, William R. Thompson proposed an algorithm known as Thompson sampling in order to maximise culmulative payo in a multi-armed bandit (MAB) problem. MAB problems have been fre- quently used to model real-life decision making scenarios. This pa- per explores the extension of Thompson sampling to other problems beyond the MAB setting. More speci cally, Thompson sampling is applied to product sales using data from a real dataset in a dynamic pricing setting as part of the multi-product pricing problem. Bachelor of Science in Mathematical Sciences 2019-05-13T13:47:13Z 2019-05-13T13:47:13Z 2019 Final Year Project (FYP) http://hdl.handle.net/10356/77144 en 30 p. application/pdf |
| spellingShingle | DRNTU::Science::Mathematics::Statistics Lee, Samuel Wai Leong Pricing problems with Thompson sampling |
| title | Pricing problems with Thompson sampling |
| title_full | Pricing problems with Thompson sampling |
| title_fullStr | Pricing problems with Thompson sampling |
| title_full_unstemmed | Pricing problems with Thompson sampling |
| title_short | Pricing problems with Thompson sampling |
| title_sort | pricing problems with thompson sampling |
| topic | DRNTU::Science::Mathematics::Statistics |
| url | http://hdl.handle.net/10356/77144 |
| work_keys_str_mv | AT leesamuelwaileong pricingproblemswiththompsonsampling |