Aplikasi pembelajaran mesin random forest dan extreme gradient boosting (xgboost) pada perilaku konsumen online dalam wilayah Jabodetabek = Application of random forest and extreme gradient boosting (xgboost) machine learning on online consumer behavior in the Jabodetabek area

Effendi, Kezia Natalia (2024) Aplikasi pembelajaran mesin random forest dan extreme gradient boosting (xgboost) pada perilaku konsumen online dalam wilayah Jabodetabek = Application of random forest and extreme gradient boosting (xgboost) machine learning on online consumer behavior in the Jabodetabek area. Bachelor thesis, Universitas Pelita Harapan.

Preview	Text (Title) Title.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (124kB) | Preview
Preview	Text (Abstract) Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (583kB) | Preview
Preview	Text (ToC) ToC.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (587kB) | Preview
Preview	Text (Chapter 1) Chapter 1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (574kB) | Preview
	Text (Chapter 2) Chapter 2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (631kB)
	Text (Chapter 3) Chapter 3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter 4) Chapter 4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (4MB)
	Text (Chapter 5) Chapter 5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (565kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (563kB) | Preview
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (23MB)

Abstract

Berkembangnya penggunaan internet dan media sosial di Indonesia telah menjadi peluang bagi para pemasar untuk memanfaatkan media sosial sebagai sarana mengembangkan penjualan secara online. Peningkatan penetrasi internet di Indonesia serta popularitas media sosial juga menjadi sarana utama bagi para konsumen untuk menjelajahi, membandingkan, dan membeli produk secara online. Purchase intention sebagai indikator kecenderungan seseorang untuk melakukan pembelian serta perilaku konsumen online menjadi fokus penting dalam pemasaran. Penelitian ini akan mengadopsi pembelajaran mesin random forest dan extreme gradient boosting (XGBoost) untuk memodelkan dan menganalisis purchase intention serta perilaku konsumen online dalam wilayah Jakarta, Bogor, Depok, Tangerang, dan Bekasi di mana data yang didapatkan berasal dari kuesioner online. Variabel target purchase intention akan diprediksi berdasarkan perilaku konsumen yang menjadi variabel prediktor seperti intensitas konsumen menggunakan media sosial, dan perilaku lainnya. Penelitian ini juga melibatkan metode ensemble yang menggabungkan model prediksi random forest dan XGBoost untuk mendapatkan nilai akurasi yang lebih tinggi. Hasil penelitian menunjukkan bahwa model prediksi random forest memberikan akurasi yang lebih tinggi dibandingkan XGBoost yaitu dengan nilai akurasi random forest sebesar 82,98% pada model prediksi pertama dan 81,91% pada model prediksi kedua. Sedangkan model prediksi XGBoost mendapatkan nilai akurasi sebesar 81,91% pada model prediksi pertama dan 78,72% pada model prediksi kedua. / The use of the internet and social media in Indonesia has been growing and become an opportunity for marketers to leverage social media as a means to develop online sales. The increasing internet penetration in Indonesia and the popularity of social media have also become the primary means for consumers to explore, compare, and purchase products online. Purchase intention, as an indicator of an individual’s tendency to make a purchase, and online consumer behavior are crucial focuses in marketing. This research will adopt the random forest and extreme gradient boosting (XGBoost) machine learning methods to model and analyze purchase intention and online consumer behavior in the Jakarta, Bogor, Depok, Tangerang, and Bekasi areas based on online questionnaire. The target variable purchase intention will be predicted based on consumer behavior which is the predictor variable such as the intensity of consumer use of social media and other behavior. The study also involves an ensemble method that combines the random forest and XGBoost prediction models to achieve higher accuracy. The results indicate that the random forest prediction model outperforms XGBoost, with an accuracy of 82.98% in the first prediction model and 81.91% in the second prediction model. Meanwhile, the XGBoost prediction model achieves an accuracy of 81.91% in the first model and 78.72% in the second model.

Actions (login required)

View Item