Recommendation System for Thesis Topics Using Content-based Filtering

Kusuma, Hans Satria; Musdholifah, Aina

doi:10.22146/ijccs.62716

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Inverse Document Frequency is a value to see how often a term appears in a corpus, the more often a term appears, the term will be considered a less important term and the value will be smaller (Kusuma & Musdholifah, 2021). The TF-IDF value of a term in a document is obtained using equation below.…”

Section: ) Text Vector Creation Stagementioning

confidence: 99%

Use of Hybrid Methods in Making E-commerce Product Recommendation Systems to Overcome Cold Start Problems

Santosa

2023

telematika.

View full text Add to dashboard Cite

The large number of users and the items offered in e-commerce make it difficult for buyers to choose the right items and sellers to offer their items to the right buyers. To overcome this problem, a system that can offer and recommend goods automatically, namely a recommendation system is needed. One of the most popular methods used to create a recommendation system is collaborative filtering, the recommendations are created based on similarities in user behavior. Unfortunately, this method has a weakness, namely cold start, where the recommendations will be inaccurate on data that has a lot of new users and items due to minimal historical data regarding user behavior. This problem will be tried to be solved in this study using a hybrid method, where this method combines more than 1 method to create a list of recommendations so that it will cover the shortcomings of each method. This study uses Amazon's e-commerce product and transaction data. The use of the hybrid method in this study can overcome the cold start problem by using switching and mixed methods, by not using the collaborative filtering model on new user recommendations or users who have little interaction. New users will receive recommendations based on the combination of popularity-based and content-based filtering models. This can be seen from the Mean Absolute Error (MAE) value of the model, where the MAE value for the data with a minimum user has at least 3 times rating is 0.566883, for the minimum 7 times, the MAE value is smaller, 0.487553.

show abstract

Section: ) Text Vector Creation Stagementioning

confidence: 99%

Use of Hybrid Methods in Making E-commerce Product Recommendation Systems to Overcome Cold Start Problems

Santosa

2023

telematika.

View full text Add to dashboard Cite

show abstract

“…Andakke (2021) melakukan penelitian untuk menghasilkan sistem informasi bank judul skripsi, adaptasi penelitian dan pengembangan (Reseacrh and Development) dengan model pengembangan ADDIE, diketahui hasil pengujian dengan menggunakan standar ISO 9126 dengan 4 karakteristik, yaitu functionality (100%), reliability (100%) tidak ditemukan error dan dengan menggunakan white-box testing tidak ditemukan kesalahan logika [8]. Kusuma & Musdholifah (2021) mengelompokkan topik skripsi berdasarkan minat dan kemampuan mahasiswa tersebut [16]. Penelitian yang dilakukan dengan mengembangkan suatu sistem rekomendasi dengan menggunakan content-based filtering dimana nantinya mahasiswa diminta untuk memilih mata kuliah yang diminati beserta dengan nilainya.…”

Section: Latar Belakangunclassified

Sistem Rekomendasi Tugas Akhir Mahasiswa pada AMIK Indonesia untuk Mendukung Merdeka Belajar-Kampus Merdeka Menggunakan Metode Collaborative Filtering (CF)

Putra

Darusalam

Sari

2022

jtik

View full text Add to dashboard Cite

The purpose of this study was to develop a model of a student's final project recommendation system by applying the Collaborative Filtering (CF) method. Agile Development Methods (ASD) is used in software development where this method is widely used for software development because it can produce system requirements data that is more descriptive and easy to implement into software. After going through the process of completing this research, the results of this study; 1) In knowing the topic or research theme in the final project, students with an expert system can be seen from the themes and sub-themes and valid calculations are carried out in helping students to find out the research title for the final project quickly, 2) By applying the Collaborative Filtering (CF) method ) in detecting research topics or themes at AMIK Indonesia, it can produce valid calculations that are the same as manual calculations so that the selection process can be carried out quickly and accurately, 3) In designing this application, it consists of the main menu page, a list of research topics, FAQs and about applications with using the programming language PHP, ReachJS and MySQL as data processing in the recommendation of the student's final project, and 4) The test is carried out using Mean Absolute Error (MAE), root-mean-square error (RMSE), Recall Value, and F-Measure. The results of the test evaluation show that the Collaborative Filtering (CF) method is quite accurate with the resulting recommendations.

show abstract

Recommendation System for Thesis Topics Using Content-based Filtering

Cited by 2 publications

References 6 publications

Use of Hybrid Methods in Making E-commerce Product Recommendation Systems to Overcome Cold Start Problems

Use of Hybrid Methods in Making E-commerce Product Recommendation Systems to Overcome Cold Start Problems

Sistem Rekomendasi Tugas Akhir Mahasiswa pada AMIK Indonesia untuk Mendukung Merdeka Belajar-Kampus Merdeka Menggunakan Metode Collaborative Filtering (CF)

Contact Info

Product

Resources

About