- Title
- An analysis of Blessed Friday sale at a retail store using classification models
- Creator
- Shaukat, Kamran; Luo, Suhuai; Abbas, Nadir; Mahboob Alam, Talha; Ehtesham Tahir, Muhammad; Hameed, Ibrahim A.
- Relation
- 2021 The 4th International Conference on Software Engineering and Information Management (ICSIM 2021). The Proceedings of 2021 The 4th International Conference on Software Engineering and Information Management (ICSIM 2021) (Yokohama, Japan 16-18 January, 2021) p. 193-198
- Publisher Link
- http://dx.doi.org/10.1145/3451471.3451502
- Publisher
- Association for Computing Machinery (ACM)
- Resource Type
- conference paper
- Date
- 2021
- Description
- Today decision-making and business planning are fundamental challenges, especially for retailers. Vendors are paying more attention to find out the age group of customers most affected by and interested in special offers on events such as Blessed Friday (falsely known as Black Friday). Besides, they want to know which strategy or marketing plan should be adopted to grasp more customers. Therefore, to assess customers' needs or figure out the group more interested in different Blessed Friday deals is challenging. Many solutions to this problem, like analysis of Blessed Friday consumer behaviour, classification of retail stores, etc., have been proposed. Still, such solutions do not consider the age group of customers. In this research, a comparison of techniques for predicting the age group of shoppers on a Blessed Friday is proposed based on machine learning. This work is done on a dataset obtained from a repository published online. During pre-processing of the dataset, missing values are replaced. Algorithms such as Decision Tree, K-Nearest Neighbor, Naïve Bayes, and Neural Network are applied to determine the most suitable algorithm. This study provides a good understanding of classification, targets the age group more interested in Blessed Friday, and provides primary research ground for further analysis in this domain.
- Subject
- Black Friday; retail store; customer behaviour; RapidMiner; supervised learning; classification
- Identifier
- http://hdl.handle.net/1959.13/1437076
- Identifier
- uon:40229
- Identifier
- ISBN:9781450388955
- Language
- eng
- Reviewed
- Hits: 1638
- Visitors: 1633
- Downloads: 0
| Thumbnail | File | Description | Size | Format |
|---|