Perbandingan Model Regresi Untuk Memprediksi Harga Jual Cabai Rawit Berdasarkan Iklim Harian

Abstract

Chili contributes to inflation of 0.15% in July 2022. Inflation is caused by an increase in selling prices, this increase is caused by fluctuations in selling prices. Several factors, such as climate conditions cause fluctuations in the price of cayenne pepper. Predictions need to be made to estimate the selling price based on daily climate conditions. Regression techniques are generally used to predict the future. The data used in this research is data that doesn’t have a normal distribution and does not have linearity. The XGBoost Regression, KNN Regression, and Random Forest Regression algorithms handle data with these characteristics. Evaluation of the three algorithms resulted in XGBoost Regression being the best model with the smallest MAE=3388, the smallest MAPE=9,96%, which is in the very good category, and the largest R2-Score=0,91. Using the SHAP method, temperature is the variable with the most significant contribution with an average SHAP value of +7003,8 which shows that this variable positively influences selling price predictions.

 Keywords: Cayenne Pepper, Climate, Selling Price, Regression, Prediction, Comparasion