Forecasting Annual Expenditure in E-Commerce

Abhijeet Yadav, Himani Deshpande, Vinayak Shukla, Dilip Woad, Romil Raina

2024

Abstract

With the rapid penetration of E-commerce in modern society, there is a need to have a holistic analysis of annual expenditure forecasting in e-commerce, underscoring its importance to modern consumer behaviour and economic growth. To achieve the same, this study explores seven machine learning based methodologies namely linear regression, random forest, decision trees, K-Nearest Neighbors (KNN), AdaBoost, Support Vector Regression (SVR), and XGBoost. Through an extensive examination of the effectiveness of each model, this research aims to provide useful information on the effectiveness of used techniques towards predicting yearly expenditures in a dynamic environment like e-commerce. These findings are important for the stakeholders seeking to improve their management strategies in the e-commerce sector, where it is necessary to understand consumers for sustainable development. Two different datasets namely Open Mart and E-Mart are used, which provides expenditure data of various companies found within different regions operating on e-commerce platforms. Among the used methodologies, the Linear Regression is found to be the most efficient one on both datasets, with 97% and 89% prediction accuracy on the Open Mart dataset and the E-Mart dataset, respectively. In contrast, Support Vector Regression (SVR) performs the worst on both the datasets. In depth analysis of the datasets reveals a strong relationship between the increasing use of apps, membership orders, and consumer expenditure overall. Thus, this study suggests that e-commerce companies may increase revenue and consumer engagement by optimizing app usage and promoting membership programs with the help of this insight.

Paper Citation

in Harvard Style

Yadav A., Deshpande H., Shukla V., Woad D. and Raina R. (2024). Forecasting Annual Expenditure in E-Commerce. In Proceedings of the 1st International Conference on Cognitive & Cloud Computing - Volume 1: IC3Com; ISBN 978-989-758-739-9, SciTePress, pages 186-195. DOI: 10.5220/0013305100004646

in Bibtex Style

@conference{ic3com24,
author={Abhijeet Yadav and Himani Deshpande and Vinayak Shukla and Dilip Woad and Romil Raina},
title={Forecasting Annual Expenditure in E-Commerce},
booktitle={Proceedings of the 1st International Conference on Cognitive & Cloud Computing - Volume 1: IC3Com},
year={2024},
pages={186-195},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013305100004646},
isbn={978-989-758-739-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Cognitive & Cloud Computing - Volume 1: IC3Com
TI - Forecasting Annual Expenditure in E-Commerce
SN - 978-989-758-739-9
AU - Yadav A.
AU - Deshpande H.
AU - Shukla V.
AU - Woad D.
AU - Raina R.
PY - 2024
SP - 186
EP - 195
DO - 10.5220/0013305100004646
PB - SciTePress