Amiladito Adhyatma Wijanarko, Helmi Imaduddin

Implementasi Metode Random Forest Untuk Memprediksi Jumlah Penjualan Gorden Berdasarkan Data Historis

Introduction

Implementasi metode random forest untuk memprediksi jumlah penjualan gorden berdasarkan data historis. Prediksi penjualan gorden Tova Gorden dengan Random Forest berbasis data historis. Optimalkan stok, atasi kendala, capai akurasi tinggi (R² 96.64%) via sistem web Flask.

Abstract

The rapid development of information technology has encouraged companies, including Tova Gorden, a small business engaged in curtain sales, to adopt technology to improve operational efficiency and competitiveness. Tova Gorden often faces obstacles in fulfilling orders, especially when demand suddenly increases, which is exacerbated by limited stock, raw material difficulties (such as smokers), fabric pre-order systems, and time-consuming production processes. Determining stock that is still based on employee estimates often leads to inefficiencies in the form of shortages or excesses of goods. This condition highlights the urgent need for an accurate prediction system to optimize inventory management. This study aims to implement and test the performance of the Random Forest algorithm, which is an ensemble learning method, to predict the number of curtain sales based on historical sales data. The collected data includes historical information related to curtain sales, including sales weeks, curtain motifs, and sales volumes. Unlike previous studies that generally use Linear Regression and focus on products with stable sales patterns, this study applies Random Forest to address more fluctuating curtain demand patterns. This research method includes several stages, namely Data Collection, Exploratory Data Analysis (EDA), Data Preprocessing, Data Splitting (70% training, 15% validation, 15% testing), Modeling with Random Forest, Evaluation, and Deployment. The evaluation results show that the model has excellent performance, with a coefficient of determination (R²) value of 97.83% on training data, 93.72% on validation data, and 96.64% on test data. Furthermore, the model is integrated into a web-based system using the Flask framework. This system is equipped with data upload features, prediction processes and curtain category grouping, and presentation of model evaluation results.

Review

This study presents a highly relevant and practical application of machine learning to address a common pain point for small businesses: inefficient inventory management due to unpredictable demand. The abstract clearly articulates the challenges faced by Tova Gorden, a curtain sales business, including issues with sudden demand surges, limited stock, raw material difficulties, and reliance on subjective employee estimates. The urgent need for an accurate prediction system to optimize stock levels and improve operational efficiency is well-established, providing a strong rationale for the research undertaken. To tackle the identified problem, the research judiciously employs the Random Forest algorithm, an ensemble learning method, to predict curtain sales based on historical data. The choice of Random Forest is particularly pertinent, as the authors note its suitability for handling fluctuating demand patterns, a departure from traditional methods like Linear Regression often applied to more stable sales. The methodology outlined is comprehensive, encompassing data collection, exploratory data analysis, preprocessing, a clear data splitting strategy (70% training, 15% validation, 15% testing), model development, evaluation, and eventual deployment. This structured approach demonstrates a rigorous investigation into the model's performance for this specific business context. The evaluation results are compelling, showcasing excellent performance across all datasets, with R² values of 97.83% for training, 93.72% for validation, and 96.64% for testing data. These high scores strongly indicate the model's accuracy and robustness in predicting curtain sales. Beyond the statistical efficacy, the practical implementation of the model into a user-friendly, web-based system using Flask, complete with features for data upload, prediction, and result visualization, adds significant value. This deployment transforms the theoretical model into a tangible tool that can directly enable Tova Gorden to make more informed decisions, optimize inventory, and ultimately enhance its competitiveness.

Full Text

Comments

You need to be logged in to post a comment.