Sistem Rekomendasi Pencarian Indekos di Surabaya Menggunakan Random Forest

Abstract

Looking for a boarding house is common for college students as a temporary place to live when they are studying outside their area of residence. Obtaining information regarding boarding prices that meet the criteria desired by students is quite difficult. In this paper, we proposed a recommendation system for finding boarding houses according to the criteria desired by students using the random forest method. This system can help students get boarding prices that match the boarding criteria they want, especially in the Surabaya area. The research method starts with data collection, preprocessing, and model training using the random forest. Based on the experimental results using the Decision Tree and Support Vector Machine (SVM) comparison method, the proposed method has the highest accuracy rate with a value of 78.55% and an error rate of 305887.80⁰. This recommendation system for predicting boarding houses can help and make it easier for students to find boarding houses that match the criteria they want.