Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Clean Energy and Smart Technology

PRODUCT SALES PREDICTION SYSTEM AT REX COMPUTER STORE USING WEBSITE-BASED SINGLE EXPONENTIAL SMOOTHING METHOD Rizqi Kafa Muntaqa; Sibyan, Hidayatus; Dimas Prasetyo Utomo
Clean Energy and Smart Technology Vol. 3 No. 2 (2025): April
Publisher : Nacreva Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58641/cest.v3i2.136

Abstract

Estimating or predicting the amount of sales is one of the factors that determines whether a company's business is running well or not. The problem faced by Rex Computer is that it cannot predict product sales in the future with current sales data, so customers may run out of stock when they want to buy the items they want. This study aims to create a system that is able to predict sales and determine the level of accuracy of the system. This study will implement the single exponential smoothing method, which is one of the prediction algorithms. The method used is an interview with Rex Computer employees regarding product sales and sales data is obtained. As well as conducting a literature study to find data from various literatures about predictions using the single exponential smoothing method. This study produces a website-based prediction system that can predict with results for product sales in the USB Wifi category with an alpha value of 0.1, namely the prediction results of 6-7 products, MAD = 2.11, MSE = 8.16, RMSE = 2.85560831906761, MAPE = 18.52, and accuracy = 81%,
GOLD PRICE PREDICTION SYSTEM USING THE RANDOM FOREST METHOD Kurnia Agung Prastyo; Sibyan, Hidayatus; Nur Hasanah
Clean Energy and Smart Technology Vol. 4 No. 1 (2025): October
Publisher : Nacreva Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Gold is one of the most important commodities, serving as an investment instrument and a hedge against inflation. The high volatility of gold prices demands accurate predictions to support investment decision-making. This study aims to develop a gold price prediction system using the Random Forest method based on machine learning. The dataset used consists of daily gold prices from Yahoo Finance covering the period from 2020 to 2024. The research stages include data collection, preprocessing, model training, evaluation, and implementation into an interactive website. Evaluation results show a MAE of 329.31, MSE of 148,599.40, RMSE of 385.49, and a negative R² value (-1.97), indicating the model is not yet accurate. However, the system can provide a general overview of gold price trends and can be further improved to enhance prediction accuracy.
IMPLEMENTASI CHATBOT SEBAGAI VIRTUAL ASSISTANT PADA PELAYANAN PUBLIK DAN BANTUAN DI DINAS SOSIAL KABUPATEN WONOSOBO DENGAN METODE TF-IDF Sagita Efendi; Sibyan, Hidayatus; Nur Hasanah
Clean Energy and Smart Technology Vol. 3 No. 1 (2024): October
Publisher : Nacreva Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58641/cest.v3i1.103

Abstract

Information needs are important in public service to give users an initial understanding of the services, the lack of information can make the public service doesn’t work like its function. Based on that reason, a study has been done to create a system that can provides information and assistance on Dinas Sosial PMD at Wonosobo Regency. The study creates chatbot named HADIR bot as a virtual assistant on public services and assistance in Dinas Sosial PMD at Wonosobo regency with TF-IDF method. The goals of this chatbot are to support public service and also virtual assistant that can run 24 hours a day based on the users request or question in chatbot, this chatbot also provides initial description and frequently asked question that often asked to the employees, and provides basic information and document template about list of the assistance. The design of the chatbot uses UML (Unified Modelling Language) like Use Case, Activity Diagram, and Sequence Diagram. This Chatbot created with telegrams features named BotFather, with the function made by Python and text editor uses Visual Studio Code, the chatbot runs in Telegram with TF-IDF method in term weighting and cosine similarity method to evaluate the similarities between document.