Skripsi

PENERAPAN METODE NAÏVE BAYES UNTUK KLASIFIKASI PENGGUNAAN LAYANAN ANJUNGAN TUNAI MANDIRI OLEH MAHASISWA UNIVERSITAS SRIWIJAYA

---

This study aims to classify the level of Automated Teller Machine (ATM) usage among students of Sriwijaya University using the Naïve Bayes method in a data mining approach. The level of ATM usage is divided into three categories, namely passive (0–2 times), moderate (3–5 times), and active (>5 times) per month. The data used is primary data collected from 120 respondents with variables including gender, bank type, transaction type, withdrawal amount, transaction time, ATM location, and disruption experience. The dataset is divided into 96 training data (80%) and 24 testing data (20%). The classification process is carried out by calculating prior probability, conditional probability, and posterior probability with the application of Laplace smoothing to handle zero probability values. The results show that the Naïve Bayes method is able to classify ATM usage based on the highest probability values, with a dominant pattern found in female respondents, state-owned banks, cash withdrawal transactions, withdrawal amounts below IDR 250,000, afternoon transaction times, campus-area ATM locations, and 0–2 disruption experiences. The posterior probability results for each class indicate that the Moderate category has the highest probability value, suggesting that the model tends to classify ATM usage most strongly into the Moderate category compared to the Passive and Active categories. The model evaluation yields an accuracy of 58.33%, indicating that the classification performance is not yet optimal. The precision, recall, and F1-score values for each class show that the best performance is achieved in the Active class, while the Passive and Moderate classes remain relatively low. Keywords: data mining, Naïve Bayes, classification, ATM, students

---

Availability

Detail Information

Series Title

-

Call Number

T1978752026

Publisher

Indralaya : Prodi Ilmu Matematika, Fakultas Matematika Dan Ilmu Pengetahuan Alam Universitas Sriwijaya., 2026

Collation

xvi, 63 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Ilmu Matematika
Algoritma Naive Bayes

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment