Peramalan Minat Pencarian Brand Hijab dan Sarung Terkenal di Indonesia pada Data Google Trends Menggunakan Arimax dan Elman RNN

Permata, Regita Putri (2019) Peramalan Minat Pencarian Brand Hijab dan Sarung Terkenal di Indonesia pada Data Google Trends Menggunakan Arimax dan Elman RNN. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 06211540000024-Undergraduate-Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (6MB) | Request a copy

Abstract

Perkembangan busana muslim menyebabkan minat pencarian terhadap brand sarung dan hijab semakin tinggi. Tujuan dari penelitian ini adalah meramalkan minat pencarian hijab dan sarung berdasarkan data google trend. Brand Hijab yang digunakan meliputi Rabbani, Zoya, Dian Pelangi, Elzatta, dan Shafira, sedangkan brand sarung yang digunakan adalah Gajah Duduk, Wadimor, Atlas, Mangga, dan Sapphire. Metode yang digunakan pada penelitian ini adalah metode peramalan statistika yaitu Naive, Winters Exponential Smoothing, ARIMA, ARIMAX, serta metode peramalan machine learning yaitu FFNN dan ERNN. Pola data yang ditunjukkan cenderung meningkat menjelang hari raya idul fitri sehingga adanya unsur variasi kalender. Hasil analisis menunjukkan bahwa adanya perbedaan model terbaik pada 10 brand. FFNN menjadi metode terbaik dalam meramalkan 4 brand sarung dan 2 brand hijab dari 10 minat pencarian brand. ARIMA baik untuk meramalkan 2 brand, sedangkan ARIMAX dan ERNN masing-masing hanya 1 brand. Hasil peramalan periode 2019 menunjukkan bahwa minat pencarian Sarung Atlas diramalkan paling tinggi dari seluruh brand sarung yang dibandingkan. Namun sebaliknya brand hijab akan terjadi penurunan minat selama periode tersebut.
================================================================================================
The development of moslem fashion caused a search interest of veil and sarong brands is getting higher. The aim of this research is to forecast search interest of veil and sarong brands by google trends data. Monthly data about search interest of The veil brands, i.e. Rabbani, Zoya, Dian Pelangi, Elzatta, and Shafira, while sarong brands, i.e. Gajah Duduk, Wadimor, Atlas, Mangga, and Sapphire. This research focuses on statistical forecasting methods, namely Naive, Winters Exponential Smoothing, ARIMA, ARIMAX, and machine learning forecasting methods namely FFNN and ERNN. The data pattern shown tends to increase ahead of Eid al-Fitr so there is an element of calendar variation. The results of the research showed that there are differences in the best models on 10 brands. FFNN is the best method in forecasting 4 sarong brands and 2 veil brands. ARIMA is good for forecasting 2 brands, while ARIMAX and ERNN are only 1 brand. The forecasting results of the 2019 period showed that the search interest of Atlas Sarong is predicted to be the highest of all branded sarong that are compared. But on the contrary the hijab brand will decrease interest in this period.

Item Type:	Thesis (Undergraduate)
Additional Information:	RSSt 519.53 Per p-1 2019
Uncontrolled Keywords:	ARIMA, ARIMAX, ERNN, FFNN, Peramalan
Subjects:	H Social Sciences > HA Statistics Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA280 Box-Jenkins forecasting
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Regita Putri Permata
Date Deposited:	24 Nov 2021 03:57
Last Modified:	24 Nov 2021 03:57
URI:	http://repository.its.ac.id/id/eprint/61599

Actions (login required)

View Item