Application of Random Forest Machine Learning Algorithm in Retail Forecasting.
- Author
- Mudoti Revelation
- Title
- Application of Random Forest Machine Learning Algorithm in Retail Forecasting.
- Abstract
-
Abstract
This research project investigates the application of the Random Forest machine learning algorithm to improve demand forecasting for small-scale grocery retailers in Zimbabwe. Small-scale retailers face significant challenges in accurately predicting product demand, often leading to stock-outs, excess inventory, and operational inefficiencies. Traditional forecasting methods, such as statistical models or expert judgment, often fail to capture the complex and dynamic nature of demand in developing country contexts. This study explores the potential of the Random Forest algorithm to address these challenges. A machine learning model was developed and trained using historical sales data from a sample of small-scale retailers. The performance of the model was rigorously evaluated using various metrics, including Mean Absolute Error, Root Mean Squared Error, and R-squared. The results demonstrate the effectiveness of the Random Forest model in predicting future demand with greater accuracy than traditional methods. This research highlights the potential of machine learning to empower small-scale retailers in Zimbabwe by providing them with more informed decision-making tools for inventory management, pricing strategies, and overall supply chain optimization. The study concludes with recommendations for the adoption and further development of machine learning-based forecasting solutions for the retail sector in Zimbabwe.
- Date
- JUNE 2024
- Publisher
- BUSE
- Keywords
- Random Forest machine learning algorithm, predicting product demand, including Mean Absolute Error, Root Mean Squared Error, and R-squared.
- Supervisor
- Mr Chaitezvi
- Item sets
- Department of Computer Science
- Media
-
Mudoti Revelation
Part of Application of Random Forest Machine Learning Algorithm in Retail Forecasting.