Abstract:

Price plays a crucial role in financial activities, and unexpected price fluctuations often indicate market instability. Machine learning techniques have emerged as powerful tools for predicting product prices and mitigating such instability. This paper explores the application of machine learning approaches to forecast the price of onions. The predictions are based on data obtained from the Ministry of Agriculture, Bangladesh. Several machine learning algorithms, including K-Nearest Neighbor (KNN), Naïve Bayes, Decision Tree, Neural Network (NN), and Support Vector Machine (SVM), were used to make the forecasts. We then evaluated and compared the performance of these algorithms to determine which one delivers the highest accuracy. The results show that all the techniques yield similar performance. Using these methods, we aim to classify onion prices into three categories: preferable (low), economical (mid), and expensive (high).

Description:

.