Toothpaste Brand Prediction Based on Analysis of Teeth Condition and Price Preferences Using the Random Forest Algorithm

Afiyati, Afiyati
Ningrum, Rahma Farah
Naima, Faaza

Journal Collabits
Vol 1, No 1 (2024)

This study aimed to predict toothpaste brands based on an analysis of dental conditions and price preferences using the Random Forest algorithm and the CRISP-DM approach. The research results indicated that the variables of tooth color range and frequency of toothache had the highest influence, suggesting that consumers were more likely to choose a brand based on tooth color and sensitivity. Evaluation using the Confusion Matrix and Classification Report models demonstrated good performance with an accuracy of 91.3%. Based on the result, the model could serve as a robust foundation for developing a GUI-based Toothpaste Brand Prediction Application using the tkinter library, assisting users in making more informed decisions.