Claim Missing Document
Check
Articles

Found 2 Documents
Search

Optimasi Pengelolaan Data Pencarian Fasilitas Ekspedisi Berbasis Otomasi dengan Pendekatan Framework Waterfall Yulyanti, Eva; Shindy Yuliyatini; Imelda, Imelda
Jurnal Informatika & Teknologi Cerdas Vol 1 No 1 (2025): Jurnal Informatika dan Teknologi Cerdas (JITC)
Publisher : Program Studi Teknik Informatika Universitas Paramadina

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51353/9gcnrp75

Abstract

Information technology (IT) has become an integral part of everyday life and plays an important role in various aspects of modern society. With the rapid development of technology, IT has changed the way individuals and organizations communicate, work, and interact. PT XYZ, as a company engaged in logistics, faces a challenge in managing expedition facility search data. This study aims to automate the management of expedition facility search data using the Waterfall framework. The stages in Waterfall include stages such as needs analysis, design, implementation, testing and maintenance. The waterfall method is helpful because it provides a structured, clear, and organized process for project completion.
KNNDT Analisis Perbandingan Kinerja Model K-Nearest Neighbors dan Decision Tree untuk Prediksi Pengeluaran Nasabah Shindy Yuliyatini; Olga Pangaribuan, Via; Nuur Bachtiar, Adnan
Jurnal Informatika & Teknologi Cerdas Vol 1 No 2 (2025): Jurnal Informatika & Teknologi Cerdas (JITC)
Publisher : Program Studi Teknik Informatika Universitas Paramadina

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51353/sy3myf10

Abstract

Customer expenditure prediction is a crucial aspect of financial data analysis, helping banking institutions better understand consumer behavior. This study compares the performance of two machine learning algorithms, K-Nearest Neighbors (KNN) and Decision Tree, in predicting customer expenditures. The dataset used consists of 2,567 transaction records from a single customer at Bank BCA. The performance of both models is evaluated using three key metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The results show that the KNN algorithm outperforms the Decision Tree by producing lower prediction errors across all evaluation metrics, making it more effective for this predictive task.