GHIFFARI, MUHAMMAD FARHAN ATSAR (2024) PENERAPAN ALGORITMA KNN DENGAN METODE COLLABORATIVE FILTERING DALAM MENCARI PRODUK REKOMENDASI ASURANSI. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (572kB) | Preview |
|
|
Text (ABSTRAK)
02 ABSTRAK.pdf Download (177kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
03 BAB 1.pdf Restricted to Registered users only Download (241kB) |
|
|
Text (BAB II)
04 BAB 2.pdf Restricted to Registered users only Download (437kB) |
|
|
Text (BAB III)
05 BAB 3.pdf Restricted to Registered users only Download (262kB) |
|
|
Text (BAB IV)
06 BAB 4.pdf Restricted to Registered users only Download (628kB) |
|
|
Text (BAB V)
07 BAB 5.pdf Restricted to Registered users only Download (105kB) |
|
|
Text (DAFTAR PUSTAKA)
08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (259kB) |
|
|
Text (LAMPIRAN)
09 LAMPIRAN.pdf Restricted to Registered users only Download (609kB) |
Abstract
With medical inflation on the rise in Indonesia, insurance has become very important to provide protection and financial security for individuals and families. Despite the growing awareness of the importance of health in Indonesian society, many people still have mixed views on insurance. This often leads to confusion in choosing the type of insurance that suits their needs. This research aims to develop an insurance recommendation system that utilizes IndoBERT model, Word2Vec, and Collaborative Filtering method. The data used in this research is taken from opinions expressed on Twitter social media. The variables used include opinion text, product_id, user_id, and rating. By using this technology, it is expected to provide more personalized and accurate recommendations for users. The results showed that this recommendation system was able to achieve a Mean Absolute Error (MAE) of 0.6370 and Root Mean Square Error (RMSE) of 0.8688 at k=17, as well as text classification accuracy of 43%. This system is designed to be web-based, so that users can directly see the results of insurance recommendations that suit their needs. With this recommendation system, it is hoped that it can help the Indonesian people in choosing the right insurance. This is very important considering the increasing medical costs, so that the appropriate insurance can provide optimal protection. The use of advanced technologies such as IndoBERT and KNN shows great potential in improving the accuracy of opinion-based recommendations, providing more personalized and appropriate solutions for users. This system not only simplifies the insurance selection process, but also increases public satisfaction and trust in insurance products in the market. Keyword: Collaborative Filltering, KNN, System Recommendation, SVM, Word2vec Semakin meningkatnya inflasi medis di Indonesia, asuransi telah menjadi sangat penting untuk memberikan perlindungan dan keamanan finansial bagi individu dan keluarga. Meskipun kesadaran akan pentingnya kesehatan semakin tinggi di masyarakat Indonesia, banyak orang masih memiliki pandangan yang beragam terhadap asuransi. Hal ini seringkali menyebabkan kebingungan dalam memilih jenis asuransi yang sesuai dengan kebutuhan mereka. Penelitian ini bertujuan untuk mengembangkan sistem rekomendasi asuransi yang memanfaatkan model IndoBERT, Word2Vec, dan metode Collaborative Filtering. Data yang digunakan dalam penelitian ini diambil dari opini yang diungkapkan di media sosial Twitter. Variabel yang digunakan meliputi teks opini, produk_id, user_id, dan rating. Dengan menggunakan teknologi ini, diharapkan dapat memberikan rekomendasi yang lebih personal dan akurat bagi pengguna. Hasil penelitian menunjukkan bahwa sistem rekomendasi ini mampu mencapai Mean Absolute Error (MAE) sebesar 0.6370 dan Root Mean Square Error (RMSE) sebesar 0.8688 pada k=17, serta akurasi klasifikasi teks sebesar 43%. Sistem ini dirancang berbasis website, sehingga pengguna dapat langsung melihat hasil rekomendasi asuransi yang sesuai dengan kebutuhan mereka. Dengan adanya sistem rekomendasi ini, dapat membantu masyarakat Indonesia dalam memilih asuransi yang tepat. Hal ini sangat penting mengingat biaya medis yang terus meningkat, sehingga asuransi yang sesuai dapat memberikan perlindungan optimal. Kata Kunci : Collaborative Filltering, KNN, Sistem Rekomendasi, SVM, Word2vec.
Actions (login required)
 |
View Item |
