cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Rizki Hesananda
Contact Email
hessananda@gmail.com
Phone
-
Journal Mail Official
innotech@cyber-univ.ac.id
Editorial Address
Jl. TB Simatupang No.6, RT.7/RW.5, Tj. Bar., Kec. Jagakarsa, Kota Jakarta Selatan, Daerah Khusus Ibukota Jakarta 12530
Location
Kota adm. jakarta selatan,
Dki jakarta
INDONESIA
Innotech
Published by Universitas Siber Indonesia
ISSN : -     EISSN : 30311640     DOI : -
Core Subject : Science,
Computer Science & IT
Innotech: Jurnal Ilmu Komputer, Sistem Informasi dan Teknologi Informasi adalah sebuah jurnal blind peer-review yang disediakan untuk publikasi hasil penelitian yang berkualitas di bidang Ilmu Komputer, Sistem Informasi dan Teknologi Informasi namun tak terbatas secara implisit. Semua publikasi di jurnal Innotech bersifat akses terbuka yang memungkinkan artikel tersedia secara bebas online tanpa berlangganan apapun. Innotech: Jurnal Ilmu Komputer, Sistem Informasi dan Teknologi Informasi adalah jurnal nasional serta bebas biaya dalam Proses Submisi.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 2 Documents
 1 
Search results for , issue "Vol 3 No 1 (2026): Innotech Issue Januari 2026" : 2 Documents clear
PERBANDINGAN ALGORITMA K-NEAREST NEIGHBOUR DAN NAÏVE BAYES DALAM ANALISIS SENTIMEN PRODUK INFINIX NOTE 40 Aji Pradana, Arya; fitria
Innotech: Jurnal Ilmu Komputer, Sistem Informasi dan Teknologi Informasi Vol 3 No 1 (2026): Innotech Issue Januari 2026
Publisher : Universitas Siber Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Abstract: Infinix Note 40 is a popular product with high specifications yet affordable, complemented by an attractive purchase package. This product has gained attention on social media and review platforms, including the Gadgetin YouTube channel. This study aims to compare two data mining algorithms, K-Nearest Neighbour (KNN) and Naïve Bayes, in sentiment analysis. From 8,323 comment data on videos from the GadgetIn channel, the results show that Naïve Bayes outperforms KNN with an accuracy of 69% compared to KNN's accuracy of 59%. The detailed metrics for Naïve Bayes are as follows: Precision of 68.9%, Recall of 69%, and F1-Score of 68.5%. This finding highlights the superiority of Naïve Bayes in analyzing sentiment towards Infinix Note 40 from reviews on the Gadgetin YouTube channel, with the interpretation leaning towards the negative, where the model classified 39% of sentiments as negative, 26% as neutral, and 34% as positive. Keywords: Data Mining, Text Classification, Sentiment Analysis, K-Nearest Neighbor, Naïve Bayes, YouTube.
Identifikasi Perbandingan Prediksi Harga Saham pada PT XYZ Menggunakan Teknik Algoritma FB Prophet dan Random Forest pada Metode CRISP-DM Astuti, Rika; Chandra Bagaskoro Setyoko, Dwi
Innotech: Jurnal Ilmu Komputer, Sistem Informasi dan Teknologi Informasi Vol 3 No 1 (2026): Innotech Issue Januari 2026
Publisher : Universitas Siber Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research aims to compare the effectiveness of two stock price prediction algorithms, namely FB Prophet and Random Forest, using the CRISP-DM method. The main focus of the study is on the stocks of PT XYZ, with data taken from the period of March 1, 2019, to March 1, 2024. Stock price prediction is a significant topic in the field of finance as it can help investors make better decisions. Both algorithms are evaluated based on error rates measured using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). This study demonstrates that both FB Prophet and Random Forest algorithms have their respective advantages in predicting stock prices. This research is also expected to contribute to the scientific literature in the fields of data mining and stock price prediction analysis.

Page 1 of 1 | Total Record : 2

 1 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol 3 No 1 (2026): Innotech Issue Januari 2026 Vol 2 No 2 (2025): Innotech Issue Juli 2025 Vol 2 No 1 (2025): Innotech Issue Januari 2025 Vol 1 No 2 (2024): Innotech Issue Juli 2024 Vol 1 No 1 (2024): Innotech Issue Januari 2024