Abstract
Bu projede bir perakende mağazasının geçmiş yıllardaki Black Friday satışları analiz edilmiş ve bu verilerden hareketle gelecek yıllara ait satışları tahmin edilmiştir.
Proje kapsamında analiz edilen veriler, müşterilerin bazı demografik bilgilerini ve sepet tutarlarını içermektedir. Proje kapsamında analiz edilen veriler ile koreasyonlar ortaya çıkarıldı. Müşterilerin demografik bilgileri ve satın alma alışkanlıkları arasında bulunan korelasyonların analizi ile black friday dönemi mağazaların satış stratejileri belirlenebilir ve daha çok satış yapmak için bu bilgiler kullanılabilir.
Aynı veriler kullanılarak proje kapsamında geliştirilen yapay zeka destekli tahmin modeli eğitilmiş ve gelecek yıllara ilişkin satış beklentileri hesaplanmıştır. Daha önceki satış verileri ve demografik verilerle eğitilen sisteme aynı perakende mağazanın mevcut olan ve eğitimde kullanılmayan satış verileri sorularak sistemin tutarlılık oranı test edilmiştir.
References
- BlackFriday.com. (2020). Black Friday history and statistics. https://blackfriday.com/news/black-friday-history
- Eberhard, E. (2018, December). Dashing to the stores: Last-minute holiday trends to watch. Think with Google. https://www.thinkwithgoogle.com/consumer-insights/consumer-trends/last-minute-holiday-shopping-trends/
- Hand, R. (2024, February 24). What is demand forecasting? Importance and benefits of forecasting customer demand. ShipBob. https://www.shipbob.com/blog/demand-forecasting/
- Kaplan, M. (2018, November 28). Sales report: 2018 Thanksgiving, Black Friday, Cyber Monday. Practical Ecommerce. https://www.practicalecommerce.com/sales-report-2018-thanksgiving-black-friday-cyber-monday
- Kayapınar Kaya, S., & Yıldırım, Ö. (2020). Prediction model for automobile sales in Turkey using deep neural networks. Journal of Industrial Engineering, 57-74.
- LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 436–444.
- Liu, J., Liu, C., Xu, Y., & Zhang, L. (2020). Research on sales information prediction system of e‐commerce enterprises based on time series model. Information Systems and e-Business Management, 823–836.
- Murray, P. N. (2014, June 11). Why we really shop. Psychology Today. https://www.psychologytoday.com/us/blog/inside-the-consumer-mind/201406/why-we-really-shop
Abstract
In this project, a retail store's Black Friday sales from prior years were examined, and sales projections for the next years were made using this information.
A few demographic details and consumer basket amounts are among the data examined for this research. Correlations were found using the data that was examined for the study. Stores can identify their Black Friday sales strategy and use this knowledge to increase sales by evaluating the relationships between demographic data about their clients and their shopping behaviors.
The artificial intelligence-supported forecasting model created as part of the research was trained using the same data, and sales projections for the upcoming years were computed. The consistency rate of the system was evaluated by comparing the sales data of the same retail store to the system that was trained using past sales data.
References
- BlackFriday.com. (2020). Black Friday history and statistics. https://blackfriday.com/news/black-friday-history
- Eberhard, E. (2018, December). Dashing to the stores: Last-minute holiday trends to watch. Think with Google. https://www.thinkwithgoogle.com/consumer-insights/consumer-trends/last-minute-holiday-shopping-trends/
- Hand, R. (2024, February 24). What is demand forecasting? Importance and benefits of forecasting customer demand. ShipBob. https://www.shipbob.com/blog/demand-forecasting/
- Kaplan, M. (2018, November 28). Sales report: 2018 Thanksgiving, Black Friday, Cyber Monday. Practical Ecommerce. https://www.practicalecommerce.com/sales-report-2018-thanksgiving-black-friday-cyber-monday
- Kayapınar Kaya, S., & Yıldırım, Ö. (2020). Prediction model for automobile sales in Turkey using deep neural networks. Journal of Industrial Engineering, 57-74.
- LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 436–444.
- Liu, J., Liu, C., Xu, Y., & Zhang, L. (2020). Research on sales information prediction system of e‐commerce enterprises based on time series model. Information Systems and e-Business Management, 823–836.
- Murray, P. N. (2014, June 11). Why we really shop. Psychology Today. https://www.psychologytoday.com/us/blog/inside-the-consumer-mind/201406/why-we-really-shop
Details
| Primary Language | English |
|---|---|
| Subjects | E-Trade |
| Journal Section | Research Articles |
| Authors | |
| Publication Date | August 31, 2024 |
| Submission Date | July 1, 2024 |
| Acceptance Date | August 3, 2024 |
| Published in Issue | Year 2024 Volume: 15 Issue: 3 |
