Prediksi Kunjungan Halaman Website Dengan N-Gram Model

Sri Wahyuni, Elok (2015) Prediksi Kunjungan Halaman Website Dengan N-Gram Model. Masters thesis, Institut Teknologi Sepuluh Nopember.

[img]
Preview
Text
2213206714-Master Thesis.pdf - Published Version

Download (1MB) | Preview

Abstract

Prediksi dan pemodelan pola kunjungan pengguna website dapat diukur kinerjanya dengan beberapa parameter. Parameter pengukuran yang sering digunakan yaitu kompleksitas model, kemampuan model dalam membuat prediksi (aplicability) dan akurasi prediksi. Dalam penelitian ini kami mencoba mengeksplorasi teknik pemodelan prediksi kunjungan halaman website yang mampu mengurangi kompleksitas model namun tetap bisa mempertahankan aplicability model dan akurasi prediksi. Kami menunjukkan dibandingkan dengan model n-gram, model n-gram+ yang dilengkapi dengan skema support pruning dapat mengurangi ukuran model hingga 75% dan mampu mempertahankan aplicability model dan akurasi prediksinya. =============================================================================================== Prediction and modeling patterns of user visits a website can be measured its performance with some parameters. Measurement parameters that are often used are the complexity of the model, the ability of the model to make predictions (aplicability) and the prediction accuracy. In this study we tried to explore the predictive modeling techniques visit the website pages that can reduce the complexity of the model, but retaining the aplicability models and prediction accuracy. We show compared with n-gram models, models of n-gram + is equipped with a support scheme pruning can reduce the size of the model up to 75 % and is able to maintain the accuracy aplicability models and predictions.

Item Type: Thesis (Masters)
Additional Information: RTE 006.312 Wah p
Uncontrolled Keywords: Web Mining, n-gram, Markov Chain, Prediksi
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105 Data Transmission Systems
Divisions: Faculty of Industrial Technology > Electrical Engineering > (S2) Master Theses
Depositing User: Mr. Tondo Indra Nyata
Date Deposited: 11 Aug 2017 07:29
Last Modified: 11 Aug 2017 07:29
URI: http://repository.its.ac.id/id/eprint/48453

Actions (login required)

View Item View Item