What is it about?
This paper presents a methodology for analyzing and predicting key performance indicators (KPIs) in online food delivery services. The study uses data from online food delivery platforms and applies various classification and regression algorithms. The results show that Random Forest consistently performs well in predicting KPIs. The methodology can be adapted to similar problems and helps identify operational issues and their root causes. The paper aims to make online food delivery analytics more accessible to a broader audience, including industry professionals and newcomers to the field.
Featured Image
Photo by Grab on Unsplash
Why is it important?
The research is important because it addresses the growing demand for online food delivery services. The study develops a systematic methodology using classification and regression algorithms to analyze and predict key performance indicators (KPIs) in online food delivery. The unique aspect of this work lies in its application of data analytics techniques to improve operational efficiency and identify potential problems in the delivery process. This research can benefit both researchers and practitioners by providing insights into optimizing online food delivery services and enhancing the customer experience.
Perspectives
The presented research opens up fresh perspectives and new doors for further research studies. It motivates researchers to explore and develop advanced data analytics techniques specifically tailored for online food delivery services. This includes investigating novel algorithms, refining predictive models, and exploring additional factors that impact key performance indicators (KPIs) in online food delivery. The publication encourages researchers to delve deeper into the optimization of operational efficiency, customer satisfaction, and overall service quality in the context of online food delivery.
Gurdal Ertek
Read the Original
This page is a summary of: A Predictive Data Analytics Methodology for Online Food Delivery, November 2022, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/snams58071.2022.10062613.
You can read the full text:
Contributors
The following have contributed to this page
