Customer Behaviour Analysis Through Clustering and Classification for Segmentation and Forecasting in Marketing Campaigns - Figure 1
Fuente:
Zenodo
Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Published: |
Zenodo
2025
|
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866902295710531584 |
|---|---|
| author | Alexandar Danailov |
| author_facet | Alexandar Danailov |
| contents | <p>Box plots are used for primary analysis of the distribution of key characteristics (Fig. 1). They allow visualisation of medians, interquartile ranges and outliers, helping to identify potential anomalies and differences between groups.<br>• Age: The distribution is concentrated - 50% of customers are between 42 and 61 years old, with no extreme values. This facilitates categorisation by age range when building models.<br>• Income: The main group has an income between 35,000 and 67,000 MUR. Several customers with very high incomes are observed, indicating the need for normalisation and the possibility of using income as a discriminating characteristic in segmentation.<br>• Amount of purchases: The data shows strong asymmetry, with several customers spending significantly more than the others. This draws attention to the existence of a VIP segment that should be taken into account when clustering.<br>• Monthly Site Visits: Most customers visit the site between 3 and 7 times per month, but a small number have significantly higher activity. This is an indicator of strong digital engagement and can be used as a predictive feature.<br>• Purchase Frequency: Half of the customers make between 6 and 18 purchases over 2 years, with no significant outliers. This is a robust indicator for inclusion in behavioural activity patterns.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17205542 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Customer Behaviour Analysis Through Clustering and Classification for Segmentation and Forecasting in Marketing Campaigns - Figure 1 Alexandar Danailov <p>Box plots are used for primary analysis of the distribution of key characteristics (Fig. 1). They allow visualisation of medians, interquartile ranges and outliers, helping to identify potential anomalies and differences between groups.<br>• Age: The distribution is concentrated - 50% of customers are between 42 and 61 years old, with no extreme values. This facilitates categorisation by age range when building models.<br>• Income: The main group has an income between 35,000 and 67,000 MUR. Several customers with very high incomes are observed, indicating the need for normalisation and the possibility of using income as a discriminating characteristic in segmentation.<br>• Amount of purchases: The data shows strong asymmetry, with several customers spending significantly more than the others. This draws attention to the existence of a VIP segment that should be taken into account when clustering.<br>• Monthly Site Visits: Most customers visit the site between 3 and 7 times per month, but a small number have significantly higher activity. This is an indicator of strong digital engagement and can be used as a predictive feature.<br>• Purchase Frequency: Half of the customers make between 6 and 18 purchases over 2 years, with no significant outliers. This is a robust indicator for inclusion in behavioural activity patterns.</p> |
| title | Customer Behaviour Analysis Through Clustering and Classification for Segmentation and Forecasting in Marketing Campaigns - Figure 1 |
| url | https://doi.org/10.5281/zenodo.17205542 |