Abstract:
The unpredictability of markets and the fluctuation of prices is a feature that is commonplace throughout the entire world, but it is more widespread in Bangladesh. As a direct result of this, the costs of the things we use on a daily basis fluctuate in a predictable pattern. It suggests that there will be a significant effect on the component that we consume on a regular basis. In Bangladesh, ginger may be found in nearly all of the foods that we consume on a daily basis. For those who are living below the poverty line, maintaining a record of the price is of the utmost importance, but doing so manually is a laborious and time-consuming endeavor. Machine learning (ML) is the most effective method for performing this activity in a sufficient manner and for developing enormous techniques to forecast the price of commodities in order to deal with market volatility. In the course of our work, we aimed to make an estimate of the price of ginger by utilizing various ML applications. We constructed our dataset using the information that was available from the Ministry of Agriculture in Bangladesh. We used a variety of machine learning techniques, including K-Nearest Neighbor (KNN), Decision Tree, Neural Network (NN), Support Vector Machine (SVM), and Random Forest, to make a prediction about the price of ginger. To make an accurate forecast of ginger's expense, an accomplished algorithm of the highest caliber was used. I make an effort to determine whether the cost of ginger falls into the category of expensive (high), inexpensive (mid), or preferable by utilizing the methods that have been described previously (low).
