Article Per Year (5 Year)
p-Index From 2019 - 2024
0.61
P-Index
This Author published in this journals
All Journal Jurnal Sains dan Teknologi INFOKUM
Arif Hamied Nababan
Universitas Prima Indonesia
Computer Science & IT Economics, Econometrics & Finance Mathematics Physics Social Sciences

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Prediction of Hotel Booking Cancellation Using K-Nearest Neighbors (K-NN) Algorithm and Synthetic Minority Over-Sampling Technique (SMOTE) Adli Abdillah Nababan; Miftahul Jannah; Arif Hamied Nababan
INFOKUM Vol. 10 No. 03 (2022): August, Data Mining, Image Processing, and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (306.281 KB)

Abstract

Cancellation of bookings puts considerable pressure on management decisions, in this case from the hospitality industry. Cancellation of bookings limits the correct prediction and is, therefore, a very important tool for revenue management performance. However, in recent times, thanks to the availability of considerable computing power through machine learning approaches, it has become possible to create more accurate models for predicting booking cancellations compared to using more traditional methods. Previous research has used several machine learning approaches, such as Decision Tree, Support Vector Machine, Deep Neural Network, Logistic Regression, and Random Forest to predict hotel cancellations. However, they have not addressed the class imbalance problem that exists in predicting hotel cancellations. In this study, we have provided a solution by introducing an oversampling technique to solve the class imbalance problem, together with the k-nearest neighbors algorithm to predict hotel booking cancellations better. The results of this study show that an increase in the performance of the method's accuracy increased by 3.88%, precision increased by 9.00%, recall increased by 10.00%, and F1-Score increased by 10.00% in the hotel booking dataset. It can be concluded that the SMOTE method with KNN has a better performance than only using the KNN method in predicting the cancellation of hotel reservations.
SMART APPLICATION FOR AUTISM DIAGNOSIS IN TODDLERS USING THE NAIVE BAYES METHOD IN LANGKAT REGENCY Ryan Dhika Priyatna; Arif Hamied Nababan; Adli Abdillah Nababan; Miftahul Jannah; Harry Pratama Figna
INFOKUM Vol. 10 No. 5 (2022): December, Computer and Communication
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58471/infokum.v10i5.1199

Abstract

All parents expect to have healthy, proud, and perfect children, however, sometimes things don't go the way they want. Some parents get the child they want and some don't. Some of them have children with special needs, such as autism. In Indonesia, each year, children with autism continue to increase. In 2015, it is estimated that there are approximately 12,800 children with autism and 134,000 children with the Autism spectrum in Indonesia. In addition to the lack of information and knowledge, preconceived notions also make parents reluctant to hand over their children for treatment. This research is motivated by the lack of solutions offered to existing problems by utilizing the development of information technology. The rapid development of technology in Indonesia has contributed a lot to the problems experienced by society with the birth of various kinds of smart systems. The development of a smart system based on an expert system can be a solution to the diagnosis of autism that appears in toddlers. The expert system that is offered is a system that can diagnose autism in toddlers in the Langkat district by implementing a method that can make decisions by providing the best solution. A good method is a method that has a high level of accuracy. The method used in this study is the Naive Bayes method where this method has been proven to be able to solve complex problems by predicting existing probabilities.
Hyperparameter Tuning pada Model Stance Detection Menggunakan GridSearchCV Arif Hamied Nababan; Mia Yovanca Hutagalung
Jurnal Sains dan Teknologi Vol. 5 No. 1 (2023): Jurnal Sains dan Teknologi
Publisher : CV. Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Tujuan dari penelitian ini adalah membangun model stance detection terhadap Undang-Undang Cipta Kerja yang memiliki performa lebih baik daripada model sebelumnya. Performa model stance detection ini penting untuk ditingkatkan agar dapat dilakukan penyerapan aspirasi masyarakat yang lebih baik terhadap Undang-Undang Cipta Kerja yang  terus menjadi kontroversi besar di Indonesia mulai dari tahun 2019 sampai di tahun 2023 ini. Dalam penelitian ini digunakan metode Hyperparamater Tuning yang diimplementasikan menggunakan kerangka kerja CRISP-DM. Hasil yang diperoleh adalah sebuah model stance detection menggunakan algoritma Support Vector Machine  yang memiliki nilai micro f1-score sebesar 78,4%. Hyperparameter model tersebut adalah  C bernilai 10, parameter max_features dari proses ekstraksi fitur menggunakan metode TF-IDF sebesar 10000, dan menggunakan fitur unigram. Disimpulkan bahwa model tersebut memiliki performa lebih baik dengan nilai micro f1-score yang lebih besar 6,6% daripada model stance detection pada penelitian sebelumnya.
Co-Authors Adli Abdillah Nababan Harry Pratama Figna Mia Yovanca Hutagalung Miftahul Jannah Ryan Dhika Priyatna