Perbaikan Kinerja Digital Marketing Melalui Prediksi Engagement Instagram Brand Produk Berbasis Machine Learning
Improving Digital Marketing Performance Through Machine Learning-Based Instagram Engagement Prediction for Product Brands
Abstract
Persaingan ketat antar brand kecantikan lokal di Indonesia menuntut perbaikan kinerja pemasaran digital melalui prediksi engagement di Instagram. Penelitian ini bertujuan membangun model prediksi tingkat keterlibatan (engagement rate) dan mengidentifikasi faktor unggahan yang paling berpengaruh menggunakan pendekatan machine learning. Metode kuantitatif prediktif diterapkan dengan menganalisis 1.922 unggahan dari 10 brand kecantikan terkemuka. Dua algoritma regresi, Random Forest Regression (RFR) dan Support Vector Regression (SVR), dibangun dan dievaluasi. Hasil menunjukkan model SVR lebih unggul dalam memprediksi engagement rate dengan nilai R² 0,0404, MAE 0,5505%, dan RMSE 4,9911%. Meskipun kemampuan model dalam menjelaskan variasi engagement terbatas, nilai MAE yang rendah mengindikasikan akurasi yang memadai untuk estimasi praktis. Analisis interpretasi model SVR mengidentifikasi tiga faktor paling dominan: jumlah pengikut, segmen pengikut mid-tier (100 ribu-1 juta), dan jumlah penyebutan akun lain (mention). Temuan ini menegaskan bahwa fondasi audiens berkualitas dan strategi kolaborasi adalah prioritas utama untuk meningkatkan kinerja pemasaran digital. Model SVR dapat direkomendasikan sebagai alat bantu pengambilan keputusan berbasis data untuk merancang strategi konten yang lebih efektif
Downloads
References
Abu-Dalbouh, M. H., Freihat, M. M., Jawarneh, R. I., Abdalwahab, M., Salim, M., & Alateyah, S. A. (2025). Analyzing Consumer Decision-Making in Digital Environments Using Random Forest Algorithm and Statistical Methods. International Journal of Advanced Computer Science and Applications (IJACSA), 16(3).
Ajala, S., Jalajamony, H., Nair, M., Marimuthu, P., & Fernandez, R. (2022). Comparing Machine Learning and Deep Learning Regression Frameworks for Accurate Prediction of Dielectrophoretic Force. Scientific Reports, 12(1). https://doi.org/10.1038/s41598-022-16114-5
Al-Ali, R., Mekimah, S., Zighed, R., Shishakly, R., Almaiah, M., Shehab, R., & Aldhyani, T. H. (2024). Evolution and gaps in data mining research: Identifying the bibliometric landscape of data mining in management. Decision Science Letters, 435–448. https://doi.org/10.5267/j.dsl.2024.12.011
Basalamah, R. A., Umayah, A., & Wismiarsi, T. (2025). Effect of Social Media Engagement and Beauty Influencers on Purchase Intentions of Indonesian Beauty Products. JEMSI (Jurnal Ekonomi, Manajemen, Dan Akuntansi), 11(1), 619–629.
Borrero, J., & Mariscal, J. (2023). Elevating Univariate Time Series Forecasting: Innovative SVR-Empowered Nonlinear Autoregressive Neural Networks. Algorithms, 16, 1–15. https://doi.org/10.3390/a16090423
Celuch, K. (2021). Hashtag usage and user engagement on Instagram: The case of #foodfestivals. Journal of Physical Education and Sport, 21(2), 966–973. https://doi.org/10.7752/jpes.2021.s2120
Chakrabarti, P., & Malvi, E. (2023). Hashtag recommendation for enhancing the popularity of social media posts. Social Network Analysis and Mining, 13(21).
Dinisari, M. C. (2024). ICE (Indonesia Cosmetic Exhibition) prediksi industri kecantikan di Indonesia tahun 2025 akan terus tumbuh. https://entrepreneur.bisnis.com/read/20241209/263/1822669/ice-prediksi-industri-kecantikan-di-indonesia-tahun-2025-akan-terus-tumbuh
Ginting, M., & Haloho, E. (2021). Pengaruh keterlibatan pelanggan dan pemasaran sosial media terhadap loyalitas pelanggan di Lim’s Café Kisaran. Jurnal TEKENSOS, 3(2), 183–192.
Goode, A., Rodner, V., & Lawlor, M. (2023). Beyond the Authenticity Bind – Finstagram as an Escape From the Attention Economy. Journal of Marketing Management, 39(11), 1071–1097. https://doi.org/10.1080/0267257X.2023.2255192
Huang, F., Chen, J., Lin, Z., & Kan, P. (2018). Random Forest Exploiting Post-related and User-related Features for Social Media Popularity Prediction. Proceedings of ACM Conference, 1–5. https://doi.org/10.1145/3240508.3266439
Ikayanti, A. P., Setiawan, M. A., & Pratama, A. R. (2021). Pengaruh Influencer dan Iklan di Instagram pada Pemasaran Pariwisata (Studi Kasus Explore Nusa Penida). EXPLORE, 11(1). https://doi.org/10.35200/explore.v11i1.407
Kolhe, A. (2025). Predicting Instagram Post User Engagement With Machine Learning Models. Research Archive of Rising Scholars. https://doi.org/10.58445/rars.2366
Nugraheny, D. E., & Setiawan, S. R. D. (2024). Wamenperin: Pasar kosmetik Indonesia terus tumbuh, harus dimanfaatkan pelaku usaha. https://money.kompas.com/read/2024/10/30/104000126/wamenperin–pasar-kosmetik-indonesia-terus-tumbuh-harus-dimanfaatkan-pelaku?page=all
Ozili, P. K. (2023). The Acceptable R-Square in Empirical Modelling for Social Science Research. In Social Research Methodology and Publishing Results. MPRA (Munich Personal RePEc Archive). https://doi.org/10.4018/978-1-6684-6859-3.ch009
Purba, K. R., Asirvatham, D., & Murugesan, R. K. (2020). Analysis and Prediction of Instagram Users Popularity using Regression Techniques based on Metadata, Media and Hashtags Analysis. Engineering Letters, 28(3), 1–8.
Purba, K. R., Asirvatham, D., & Murugesan, R. K. (2021). Instagram Post Popularity Trend Analysis and Prediction using Hashtag, Image Assessment, and User History Features. The International Arab Journal of Information Technology, 28(1), 85–94.
Santhosh. (2024). A Study of the Impact of Instagram Marketing on the Cosmetic Purchasing Choices of Young Adults. International Journal of Research Publication and Reviews, 5(6), 344–347.
Social Media College. (2023). The Importance Of Call To Actions In Social Media Marketing. https://www.socialmediacollege.com/blog/call-to-actions-social-media-marketing
Swimbawa, M., & Lemy, D. (2023). Pengaruh social media marketing terhadap brand awareness, brand image dan brand loyalty pesona indonesia. Bulletin of Community Engagement, 3(2), 239. https://doi.org/10.51278/bce.v3i2.968
Syahtiti, D., Yuniar, F. A., & Nurhaliza, P. R. (2024). Sosial Media Engagement Dan Hubungannya Dengan Kinerja Customer Relationship Management. Jurnal Manajemen Dan Bisnis Ekonomi, 2(3), 371–378.
The Global Statistics. (2025). Indonesia social media statistics 2025: Most popular platform. https://www.theglobalstatistics.com/indonesia-social-media-statistics/#google_vignette
Wafda, A. (2024). Integrasi Machine Learning dalam Ritel: Tinjauan Komprehensif tentang Prediksi Harga, Analisis Data Pelanggan, dan Pemanfaatan Media Sosial. Jurnal Artificial, 2(2), 90–106. https://doi.org/10.54065/artificial.2.2.2024.543
Copyright (c) 2025 Indah Kurnia, Saiful Mangngenre
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
An author who publishes in the ARIKA Jurnal agrees to the following terms:
- The author retains the copyright and grants ARIKA journal the right of first publication of the work simultaneously licensed under the Creative Commons Attribution-ShareAlike 4.0 License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- The author is able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book) with the acknowledgment of its initial publication in this journal.
- The author is permitted and encouraged to post his/her work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of the published work (See The Effect of Open Access).
