E-Commerce Inventory Management System Using Machine Learning Approach
- Resource Type
- Conference
- Authors
- R, Pramodhini; Kumar, Sourav; Bhardwaj, Siddharth; Agrahari, Naman; Pandey, Suyash; Harakannanavar, Sunil S.
- Source
- 2023 International Conference on Data Science and Network Security (ICDSNS) Data Science and Network Security (ICDSNS), 2023 International Conference on. :1-7 Jul, 2023
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
Fields, Waves and Electromagnetics
General Topics for Engineers
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Training
Machine learning algorithms
Computational modeling
Supply chains
Demand forecasting
Inventory management
Predictive models
Inventory Management
XGBoost
Liner regression stock
demand forecasting
- Language
Inventory management is a crucial requirement for small and medium-sized enterprises because significant financial and human resources are needed. Small and medium-sized enterprises can use it as a service to increase their sales and forecast demand for different products. Demand forecasting is an essential component of all businesses and raises the issue of how much inventory a firm or business should maintain to satisfy demand. In this paper, an effort is made to develop a robust inventory management model with a suitable machine learning algorithm to achieve demand forecasting. The challenges of building an Inventory system with the design decisions is discussed. Here, the model is trained using 80% of own local dataset which produced an accuracy of 63.6646% for the XGBoost model and an accuracy of 82.324% for the linear regression model. The demand forecasting model will help Small/Medium businesses to maintain inventory and minimize manual labor and hence allowing it to reduce the capital spent on maintaining inventory and simultaneously improves the profitability.