Analisis Tren Produksi dan Preferensi Penonton Netflix: Pendekatan Big Data untuk Menyusun Strategi Konten Global

Authors

  • Muhamad Thoriq Azmi Universitas Lanlangbuana Bandung
  • Enpri Rifa Azima Universitas Lanlangbuana Bandung
  • Egie Fergiana Universitas Lanlangbuana Bandung
  • Hadi Prasetyo Utomo Universitas Lanlangbuana Bandung

DOI:

https://doi.org/10.57255/intellect.v4i02.1387

Keywords:

netflix, big data analitics, produksi film, preferensi penonton, analisis tren, rating, popularitas

Abstract

The objective of this study is to support strategic decision-making in content investment and diversification on the Netflix platform using a big Data analytics approach. This research utilizes a Dataset obtained from Kaggle, covering the period from 2010 to 2025. The Dataset consists of 21,845 titles and includes attributes such as title name, content type, genre, release year, content ID, rating, vote count, and country of availability. Kaggle is a widely used platform for sharing Datasets and hosting Data analysis competitions in both academic research and industry. The analyzed Data encompass various attributes, including release year, country of origin, genre, duration, and audience response metrics such as ratings, vote counts, and popularity. Exploratory Data analysis (EDA) was employed to identify content production patterns based on genre and to evaluate audience responses through the distribution of ratings and popularity levels. Data analysis was conducted using Python and executed through Google Colab. The results indicate that content with high popularity—reflected by higher vote counts and popularity scores—tends to have relatively higher ratings compared to content with lower exposure. These findings suggest that popularity can serve as a proxy for global audience preferences. However, the relationship between popularity and rating is not entirely linear, as it is influenced by external factors such as promotional strategies and genre-specific characteristics. The study identifies genres and content types that achieve not only high ratings but also high popularity, thereby more accurately reflecting global audience preferences. Based on these findings, a practical recommendation for Netflix is to invest in producing more content within genres that consistently demonstrate high popularity and ratings, such as drama and action, as these genres most strongly represent global viewer preferences. From a social perspective, this strategy may carry the risk of reducing content diversity and cultural narratives if the platform overly prioritizes the most popular genres.

Abstrak

Tujuan penelitian ini adalah untuk pengambilan keputusan strategis dalam investasi dan diversifikasi konten pada aplikasi Netflix menggunakan pendekatan big Data analitik. Studi ini menggunakan Dataset Website Kaggle sejak tahun 2010 hingga 2025 yang diperoleh website Kaggle, Data yang didapat sebanyak 21.845 tayangan dengan atribut Judul Tayangan, Jenis Tayangan, Genre Tayangan, Tahun Rilis, ID Tayangan, Rating, Jumlah Vote dan Daftar Negara, sebuah platform berbagi Dataset dan kompetisi analisis Data yang banyak digunakan dalam penelitian dan industri. Data yang dianalisis mencakup berbagai atribut seperti tahun rilis, negara asal, genre, durasi, hingga metrik respons penonton seperti rating, vote count, dan popularitas. Metode analisis eksploratif digunakan untuk mengidentifikasi pola produksi konten berdasarkan genre serta mengevaluasi tanggapan audiens melalui distribusi rating dan tingkat popularitas. Analisis Data dilakukan menggunakan Phyton yang dijalankan menggunakan Google Collabs. Hasil penelitian menunjukkan konten dengan popularitas tinggi, yang ditunjukkan oleh nilai vote dan popularity, cenderung memiliki rating yang relatif lebih tinggi dibandingkan konten dengan eksposur rendah. Temuan ini mengindikasikan bahwa popularitas dapat merefleksikan preferensi penonton global, meskipun hubungan antara kedua variabel bersifat tidak sepenuhnya linier karena dipengaruhi oleh faktor eksternal seperti strategi promosi dan karakteristik genre. Temuan ini mengidentifikasi genre dan tipe konten yang tidak hanya memiliki rating tinggi, tetapi juga popularitas tinggi, sehingga lebih mencerminkan preferensi penonton global. Berdasarkan temuan tersebut, Rekomendasi praktis yang bisa dilakukan adalah dengan memproduksi lebih banyak konten dari genre yang konsisten memiliki popularitas dan rating tinggi (seperti drama dan action), karena genre ini paling mencerminkan preferensi penonton global. Secara implikasi sosial, ini dapat berpotensi menurunkan keragaman konten dan narasi budaya jika platform terlalu fokus pada genre yang paling populer.

Downloads

Download data is not yet available.

References

Z. Hidayat, “DAMPAK TEKNOLOGI DIGITAL TERHADAP PERUBAHAN KONSUMSI,” vol. 13, no. September, 2016.

R. Salam, “Manajemen Bisnis di Era Digital,” 2020.

T. Tahir, K. Qasim Maqbool, S. Zafar, M. Zulkifl Hasan, M. Zunnurain Hussain, and M. Atif Yaqub, “Dialogue Social Science Review (DSSR) A Global Analysis of Netflix Content Production Unveiling Dominant Countries and Industry Trends,” vol. 2, no. 3, pp. 519–534, 2024, [Online]. Available: www.thedssr.com

A. Ali, A. Raza, M. M. M. Sayed, B. A. Qureshi, and Y. M. Memon, “Data-driven Insights Machine Learning Approaches for Netflix Content Analysis and Visualization,” J. Eng. Res. Reports, vol. 27, no. 4, pp. 278–290, 2025, doi: 10.9734/jerr/2025/v27i41471.

N. Lee, J. Lim, M. Choi, and H.-C. Jeong, “Global Streams, Local Currents: A Data Analysis on Global VOD Content Consumption,” pp. 1–21, 2025, [Online]. Available: http://arxiv.org/abs/2502.19043

Dian Sudiantini, Dwi Nurambarwati, Faizah Dwi Julianti, Farhan Febriansyah Putra, Gaida Putri Naraya, and Gea Verina Nazara, “Inovasi Dalam Manajemen Pemasaran Dan Menjaga Relevan Bisnis Di Era Digital,” J. Ris. dan Inov. Manaj., vol. 1, no. 2, pp. 129–138, 2023, doi: 10.59581/jrim-widyakarya.v1i2.378.

M. Saraee, S. White, and J. Eccleston, “A Data mining approach to analysis and prediction of movie ratings,” Manag. Inf. Syst., vol. 10, pp. 343–352, 2004.

G. Mejías, Netflix Nations: The Geography of Digital Distribution, vol. 19, no. 1. 2021. doi: 10.7195/ri14.v19i1.1565.

S.-H. Chen, Y.-J. Chen, and W.-C. Leung, “Analyzing differences in customer satisfaction on the video streaming platform Netflix,” Ann. Manag. Organ. Res., vol. 4, no. 3, pp. 193–209, 2023, doi: 10.35912/amor.v4i3.1554.

W. Ni and C. Coupé, “Time-synchronic comments on video streaming website reveal core structures of audience engagement in movie viewing,” Front. Psychol., vol. 13, no. January, 2023, doi: 10.3389/fpsyg.2022.1040755.

L. Mikos, “Digital media platforms and the use of TV content: Binge watching and video-on-demand in germany,” Media Commun., vol. 4, no. 3A, pp. 154–161, 2016, doi: 10.17645/mac.v4i3.542.

Q. Zhang, Y. Zhu, X. Zhang, and M. G. Terwilliger, “Predicting popularity: Machine learning insights into movie team patterns and online ratings,” Issues Inf. Syst., vol. 25, no. 3, pp. 386–398, 2024, doi: 10.48009/3_iis_2024_129.

D. Gavilan, S. Fernández-Lores, and G. Martinez-Navarro, “The influence of online ratings on film choice: decision making and perceived risk,” Commun. Soc., vol. 32, no. 2, pp. 45–59, 2019, doi: 10.15581/003.32.2.45-59.

Referensi tentang kelelahan media : Webster, J. G. (2014) “The Marketplace of Attention: How Audiences Take Shape in a Digital Age.

MIT Press”

Referensi Teori Konsumsi Media : Uses and Gratifications Theory Katz, E., Blumler, J. G., & Gurevitch, M. (1974). “Uses and Gratifications Research.”

Downloads

Submitted

2025-07-19

Accepted

2026-02-16

Published

2025-12-31

How to Cite

Azmi, M. T., Azima, E. R. ., Fergiana, E. ., & Utomo, H. P. (2025). Analisis Tren Produksi dan Preferensi Penonton Netflix: Pendekatan Big Data untuk Menyusun Strategi Konten Global. Intellect : Indonesian Journal of Learning and Technological Innovation, 4(02), 361–373. https://doi.org/10.57255/intellect.v4i02.1387