Rani Puspita
Bina Nusantara University

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

Found 3 Documents
Search

Perbandingan Metode KNN, Decision Tree, dan Naïve Bayes Terhadap Analisis Sentimen Pengguna Layanan BPJS Rani Puspita; Agus Widodo
Jurnal Informatika Universitas Pamulang Vol 5, No 4 (2020): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/informatika.v5i4.7622

Abstract

BPJS is really helpful because one of its goal is to provide good service for the member in terms of healthiness. But, when there’s many people using the service, then it will cause more pros and contras. Therefore, researcher will be doing sentiment analysis in the field of data mining towards bpjs users on social media Twitter as much as 1000 data that later will be filtered to be 903 data because there are some data that has been duplicated. Researchers used the KNN, Decision Tree, and Naïve Bayes methods to compare the accuracy of the three methods. Researchers used the RapidMiner version 9.7.2 tools. The results showed that the sentiment analysis of Twitter data on BPJS services using the KNN method reached an accuracy level of 95.58% with class precision for pred. negative is 45.00%, pred. positive is 0.00%, and pred. neutral is 96.83%. Then the Decision Tree method the accuracy rate reaches 96.13% with the precision class for pred. negative is 55.00%, pred. positive is 0.00%, and pred. neutral is 97.28%. And the last one is the Naïve Bayes method which achieves 89.14% accuracy with precision class for pred. negative is 16.67%, pred. positive was 1.64%, and pred. neutral is 98.40%.
Analisis Sentimen terhadap Layanan Indihome di Twitter dengan Metode Machine Learning Rani Puspita; Agus Widodo
Jurnal Informatika Universitas Pamulang Vol 6, No 4 (2021): JURNAL INFORMATIKA UNIVERSITAS PAMULANG
Publisher : Teknik Informatika Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/informatika.v6i4.13247

Abstract

Indihome is a digital service such as the internet that can be used at home, landlines and interactive TV. However, because it is so extensive, Indihome has received a lot of criticism because the internet connection is rarely stable. Therefore, a sentiment analysis in the field of was carried out data mining on customers Indihomeon Twitter social media which consisted of 1350 data and filtered into 1309 data because a lot of data indicated duplicates. In this study, researchers used the methods Random Forest and Gradient Boosted Trees (GBT). This research was conducted using tools Rapidminer version 9.8. Research shows that sentiment analysis on Indihome services using the method Random Forest achieves an accuracy of 99.54% with class precision for pred. negative is 99.92%, pred positive is 25.00%, and pred. neutral is 60.00%. Then the GBT method has an accuracy rate of 99.31% with a precision class ofn for pred. negative is 99.46%, pred. positive is 0.00%, and pred. neutral is 0.00%. So it can be concluded that the Random Forest method is a better method when compared to GBT.
Hardware sales forecasting using clustering and machine learning approach Rani Puspita; Lili Ayu Wulandhari
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 3: September 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v11.i3.pp1074-1084

Abstract

This research is a case study of an information technology (IT) solution company. There is a problem that is quite crucial in the hardware sales strategy which makes it difficult for the company to predict the number of various items that will be sold and also causes the excess or shortage in hardware stocking. This research focuses on clustering to group various of items and forecast the number of items in each cluster using a machine learning approach. The methods used in clustering are k-means clustering, agglomerative hierarchical clustering (AHC), and gaussian mixture models (GMM), and the methods used in forecasting are autoregressive integrated moving average (ARIMA) and recurrent neural network-long short-term memory (RNN-LSTM). For clustering, k-means uses two attributes, namely "Quantity and Stock" as the best feature in this case study. Using these features the k-means obtain silhouette results of 0.91 and davies bouldin index (DBI) values of 0.34 consisting of 3 clusters. While for forecasting, RNN-LSTM is the best method, where it produces more cost savings than the ARIMA method. The percentage of the difference in saving costs between ARIMA and RNN-LSTM to the actual cost is 83%.