A Tool for Sales Forecasting based on the Neural Network
- Resource Type
- Conference
- Authors
- Basahel, Sarah; Sen, Adnan Ahmed Abi
- Source
- 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom) Computing for Sustainable Global Development (INDIACom), 2023 10th International Conference on. :607-611 Mar, 2023
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
Fields, Waves and Electromagnetics
General Topics for Engineers
Geoscience
Nuclear Engineering
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Training
Web services
Neural networks
Time series analysis
Production
Companies
Predictive models
Prediction Tools
Business Intelligence
Neural Network
Productivity
Sales
- Language
Time series is a well-known way of successively predicting the behavior of a variable by considering its preceding behavior. It is well known that predicting future sales of large companies is a critical and sensitive issue because it is linked to the production quantity. Accuracy of predictions can save a significant amount of money by reducing the amount of waste due to excessive production. Several other methods are used for prediction. This paper provided a comparison between three methods of predicting based on time series, namely regression, moving averages, and neural networks. Also, the paper provided a tool to facilitate working with neural networks for non-specialists (normal users). The results on real data for a Saudi company have proved that the neural networks model outperformed other models with an accuracy rate or more than 96%. The tool of this paper will be useful for building more complex models by introducing additional factors into the sales forecasting process and publishing it as a web service for ease of use and access.