Penerapan Business Intelligence untuk Optimasi Kinerja Aplikasi Perusahaan

Setiawan, Herfian (2018) Penerapan Business Intelligence untuk Optimasi Kinerja Aplikasi Perusahaan. Masters thesis, Institut Teknologi Sepuluh Nopember.

[img]
Preview
Text
05211450010021-Master_Thesis.pdf - Accepted Version

Download (1MB) | Preview

Abstract

Aplikasi atau software sangat diperlukan dalam menjalankan suatu bisnis perusahaan. Semakin maju suatu perusahaan semakin banyak aplikasi yang digunakan dan semakin besar pula data yang tersimpan dalam database perusahaan. Oleh karena itu, aplikasi yang digunakan perusahaan harus diperiksa dan dianalisis setiap tahun guna menghindari menumpuknya aplikasi atau memberikan informasi tentang masih kurangnya aplikasi yang ada. Penerapan Business Intelligence sebagai teknik untuk mengekstrak data dari berbagai database perusahaan dapat membantu perusahaan lebih mudah mendapatkan data yang relevan sehingga menjadi informasi yang berguna dan mudah dipahami dimana kemudian dilanjutkan dengan analisis statisitik dalam Data Mining. Metode Data Mining telah banyak diterapkan dalam perusahaan terutama untuk menangani kasus data yang berukuran besar. Dalam masalah klasifikasi, metode Data Mining bekerja dengan sangat baik. Algoritma yang diusulkan untuk mengklasifikasi dan memprediksi kinerja aplikasi perusahaan yaitu Naive Bayes, Decision Tree, Random Forest dan k-Nearest Neighbour. Dari hasil penelitian diperoleh bahwa metode Decision Tree dengan algoritma J48 adalah metode terbaik dengan nilai akurasi tertinggi dan juga memiliki waktu tercepat dibandingkan dengan metode lainnya yaitu secara berturut-turut 99.92% dan 0.71 detik. ========================================================================================================= Application or software is necessary in running a business company. The more advanced a company more and more applications are used and the greater the data stored in the company database. Therefore, the applications that companies use should be checked and analyzed every year to avoid stacking applications or providing information about the lack of existing applications. Implementation of Business Intelligence as a technique to extract data from various company's databases can help companies more easily to obtain relevant data so that it becomes useful information and easy to understand which then proceed with statistical analysis in Data Mining. Data Mining methods have been widely applied in companies, especially to handle large data cases. On the classification problem, the Data Mining methods work very well. The proposed algorithms to classify and to predict the performance of enterprise applications are Naive Bayes, Decision Tree, Random Forest and k-Nearest Neighbors. From the our results, it is found that Decision Tree method with J48 algorithm is the best method with the highest accuracy value and also has the fastest time compared to other methods that is 99.92% and 0.71 seconds respectively.

Item Type: Thesis (Masters)
Additional Information: RTSI 006.312 Set p-1 3100018075456
Uncontrolled Keywords: Data Mining, Business Intelligence, Kinerja Aplikasi, Naive Bayes, Decision Tree, Random Forest, dan k-Nearest Neighbour, Data Mining, Business Intelligence, Application Performance, Naive Bayes, Decision Tree, Random Forest, and k-Nearest Neighbors
Subjects: H Social Sciences > HD Industries. Land use. Labor > HD1393.25 Business enterprises
H Social Sciences > HD Industries. Land use. Labor > HD38.7 Business intelligence. Trade secrets
Q Science > QA Mathematics > QA76.76.A65 Application software. Enterprise application integration (Computer systems)
Q Science > QA Mathematics > QA76.9.D343 Data mining
Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases
Divisions: Faculty of Information and Communication Technology > Information Systems > 59101-(S2) Master Thesis
Depositing User: Herfian Setiawan
Date Deposited: 16 Aug 2018 07:10
Last Modified: 13 Oct 2020 08:11
URI: http://repository.its.ac.id/id/eprint/52432

Actions (login required)

View Item View Item