PENERAPAN ALGORITMA K-NEAREST NEIGHBOR UNTUK REKOMENDASI PROGRAM LATIHAN WORKOUT DI RUMAH BERDASARKAN KARAKTERISTIK PENGGUNA

  • Rico Herdiyanto Universitas Bina Sarana Informatika
  • Agus Junaidi Universitas Bina Sarana Informatika
Keywords: K-Nearest Neighbor, recommendation system, workout, machine learning, Streamlit

Abstract

The development of technology provides opportunities for the use of recommendation systems to assist users in determining workout programs according to their characteristics. This study aims to implement the K-Nearest Neighbor (KNN) algorithm to develop a home workout recommendation system based on user characteristics. This study employed a quantitative approach and machine learning using a dataset consisting of 973 records. The user characteristics used as input attributes included age, Body Mass Index (BMI), workout goals, workout experience, and available workout time. The dataset was divided into 80% training data and 20% testing data, followed by encoding and standardization using StandardScaler. K values ranging from 1 to 20 were tested to determine the optimal parameter. The results showed that K = 2 was the optimal value, achieving an accuracy of 97.44%. Validation using WEKA with the IBk algorithm resulted in an accuracy of 97.4359%, with 190 data correctly classified and 5 data misclassified. The system generated five workout recommendation categories: Full Body, HIIT, Cardio, Split Workout, and Push Pull Legs. These results indicate that the KNN algorithm can provide highly accurate workout recommendation classification and can be implemented in a web-based recommendation system.

References

Hanani, A. D., Samat, S., Rosita, M., & Assapari, M. H. (2024). Profil cedera dan faktor risiko pada pengunjung Gym Numero Uno berdasarkan usia dan pengalaman berlatih. Babul Ilmi Jurnal Ilmiah Multi Science Kesehatan, 16(2). https://doi.org/10.36729/bi.v16i2.1294
Irfan Sazali Nasution, Arini Dwi Rahmadani, Audina, W., Sari, D. P., & Sari, N. D. (2025). Systematic review: Pengaruh gaya hidup dan pengetahuan masyarakat terhadap risiko penyakit jantung koroner. Sehat Rakyat: Jurnal Kesehatan Masyarakat, 4(2). https://doi.org/10.54259/sehatrakyat.v4i2.4337
Kemalasari Siregar, G., Pujianto, & Ridhawati, E. (2025). Sistem pendukung keputusan untuk rekomendasi olahraga berdasarkan kondisi kesehatan menggunakan metode Analytical Hierarchy Process (AHP). Jurnal Ilmiah Sistem Informasi (JISI), 4(1). https://doi.org/10.24127/jisi.v4i1.8561
Maulyanda, M., Deviani, R., Sabrina, F., & Afdhaluzzikri, A. (2025). WorkoutLife: Penerapan algoritma K-Nearest Neighbor (KNN) untuk rekomendasi workout berdasarkan data gaya hidup. J-SIGN (Journal of Informatics, Information System, and Artificial Intelligence), 3(2). https://doi.org/10.24815/j-sign.v3i2.50115
Mubarak, N., Kusumawati, A., & Raharjo, K. (2021). Menggali peran digital fitness influencer terhadap parasocial interaction dan fan citizenship behaviour. Jurnal Studi Komunikasi (Indonesian Journal of Communications Studies), 5(3). https://doi.org/10.25139/jsk.v5i3.3633
Ning, X., Desrosiers, C., & Karypis, G. (2015). A comprehensive survey of neighborhood-based recommendation methods. In Recommender Systems Handbook (2nd ed.). https://doi.org/10.1007/978-1-4899-7637-6_2
Rahmatullah, R., & Adimahendra, W. (2022). Sistem pendukung keputusan latihan gerakan fitness bagi pemula menggunakan metode Weighted Product. Journal of Information System and Computer, 2(2). https://doi.org/10.34001/jister.v2i2.420
Rijal, A., Adhikari, T. B., Dhakal, S., Maagaard, M., Piri, R., Nielsen, E. E., Neupane, D., Jakobsen, J. C., & Olsen, M. H. (2024). Effect of exercise on functional capacity and body weight for people with hypertension, type 2 diabetes, or cardiovascular disease: A systematic review with meta-analysis and trial sequential analysis. BMC Sports Science, Medicine and Rehabilitation, 16(1), Article 38. https://doi.org/10.1186/s13102-024-00829-1
Roy, D., & Dutta, M. (2022). A systematic review and research perspective on recommender systems. Journal of Big Data, 9(1). https://doi.org/10.1186/s40537-022-00592-5
Valakhorasani, V. (n.d.). Gym members exercise dataset [Data set]. Kaggle. Kaggle
Wibowo, A., & Erawati, W. (2025). Pembuatan model rekomendasi gerakan olahraga berbasis content-based filtering dengan integrasi clustering dan klasifikasi. Jurnal Infortech, 7(2). https://doi.org/10.31294/infortech.v7i2.11384
Published
2026-09-30
How to Cite
Rico Herdiyanto, & Agus Junaidi. (2026). PENERAPAN ALGORITMA K-NEAREST NEIGHBOR UNTUK REKOMENDASI PROGRAM LATIHAN WORKOUT DI RUMAH BERDASARKAN KARAKTERISTIK PENGGUNA. EDU RESEARCH, 7(3), 1757-1770. https://doi.org/10.47827/jer.v7i3.3821
Section
Articles