Strategic Customer Shopping Behaviour Analysis and Sales Optimization using Business Intelligence
Fuente:
Zenodo
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Recurso digital |
| Publicado: |
Zenodo
2026
|
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866901693895016448 |
|---|---|
| author | G, Bhuvaneswar B, Jagadhesan |
| author_facet | G, Bhuvaneswar B, Jagadhesan |
| contents | <p>This study focuses on analyzing customer shopping behaviour and optimizing sales strategies using Business Intelligence (BI) techniques. The project is based on a dataset containing 3,900 customer transactions across multiple product categories. </p> <p>The analysis integrates Python for data preprocessing, SQL for structured querying, and Power BI for interactive data visualization. Key variables examined include customer demographics, purchase behaviour, subscription status, discount usage, and product categories.</p> <p>The findings reveal that clothing generates the highest revenue and sales volume, while accessories also contribute significantly to overall performance. Subscription adoption remains relatively low (27%), yet subscribers demonstrate consistent spending patterns. Discounts play a critical role in influencing purchase decisions, particularly for products such as hats and sneakers. Additionally, demographic analysis shows that young adults and middle-aged customers are the primary contributors to revenue.</p> <p>The study highlights the importance of leveraging Business Intelligence tools to uncover actionable insights. Based on the analysis, strategic recommendations are proposed, including enhancing subscription programs, optimizing discount policies, strengthening customer loyalty initiatives, and implementing targeted marketing strategies.</p> <p>Overall, this project demonstrates how data-driven decision-making can help retail organizations improve customer engagement, increase sales performance, and achieve sustainable business growth.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19159022 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Strategic Customer Shopping Behaviour Analysis and Sales Optimization using Business Intelligence G, Bhuvaneswar B, Jagadhesan <p>This study focuses on analyzing customer shopping behaviour and optimizing sales strategies using Business Intelligence (BI) techniques. The project is based on a dataset containing 3,900 customer transactions across multiple product categories. </p> <p>The analysis integrates Python for data preprocessing, SQL for structured querying, and Power BI for interactive data visualization. Key variables examined include customer demographics, purchase behaviour, subscription status, discount usage, and product categories.</p> <p>The findings reveal that clothing generates the highest revenue and sales volume, while accessories also contribute significantly to overall performance. Subscription adoption remains relatively low (27%), yet subscribers demonstrate consistent spending patterns. Discounts play a critical role in influencing purchase decisions, particularly for products such as hats and sneakers. Additionally, demographic analysis shows that young adults and middle-aged customers are the primary contributors to revenue.</p> <p>The study highlights the importance of leveraging Business Intelligence tools to uncover actionable insights. Based on the analysis, strategic recommendations are proposed, including enhancing subscription programs, optimizing discount policies, strengthening customer loyalty initiatives, and implementing targeted marketing strategies.</p> <p>Overall, this project demonstrates how data-driven decision-making can help retail organizations improve customer engagement, increase sales performance, and achieve sustainable business growth.</p> |
| title | Strategic Customer Shopping Behaviour Analysis and Sales Optimization using Business Intelligence |
| url | https://doi.org/10.5281/zenodo.19159022 |