<p>Penelitian ini bertujuan untuk meramalkan tren penjualan menu pada restoran guna membantu pihak pengelola restoran dalam menentukan dan memberikan rekomendasi pengelolaan stok menu. Peramalan dilakukan dengan mengimplementasikan metode <em>single moving average</em> pada data transaksi penjualan selama periode 15 bulan, yakni bulan Januari-Desember 2018 dan Januari-Maret 2019 untuk menghasilkan ramalan bulanan dan harian. Total sampel data latih yang diolah sebanyak 10.515 record yang merupakan data transaksi penjualan pada bulan Januari-Desember tahun 2018, serta 2.246 record data bulan Januari-Maret 2019 sebagai data uji (untuk menguji akurasi ramalan). Hasil pengujian hasil ramalan bulanan untuk Top-10 menu menghasilkan perhitungan MAPE <em>(Mean Absolut Percentage Error) sebesar </em>4% yang berarti tingkat akurasi sangat baik, yakni sebesar 96%. Sedangkan pengujian hasil ramalan harian menghasilkan MAPE yang cukup tinggi yaitu sebesar 39.2%, mengindikasikan nilai akurasi yang cukup rendah, yakni 60.8%. Meskipun akurasi untuk ramalan harian, masih rendah namun hasil penelitian ini dapat memberikan gambaran kepada pengelola hotel tentang rentang minimum-maksimal stok yang perlu disiapkan untuk menu tertentu pada hari-hari tertentu. Untuk memperoleh akurasi prediksi harian yang lebih akurat, penelitian ini akan dilanjutkan dengan mencoba metode lain serta menambah jumlah data latih.</p><p> </p><p class="Judul2"><strong><em>Abstract</em></strong></p><p class="Judul2"><em>This research aims to forecast sales trend of a restaurant menus to help the restaurant management in determaining and providing recommendations for managing stocks. Forecasting was performed by applying the single moving average towards fifteen months recorded data transaction, namely January to December 2018, and Januari to March 2019 to establish monthly and daily forecast. Total data training was 10.515 recods data transaction obtained from Januari to December 2018, while data testing was 2.246 record data transaction within Januari to March 2019. Result for montly forecast shows, that the average accuracy reached 96% (MAPE 4%) indicating the forecast is almost perfect. While, for daily forecast the average accuracy is only 60.8% (MAPE 39,2%) indicating that the forecast is less accurate. Although, accuracy of the daily forecast is considered less accurate, the result still can be used by the restaurant management to figure-out minimum and maximum amount of stock to be prepared for certain menus in certain days. </em></p>
This research aims to develop trash volume monitoring based on Arduino nano and orange pi. This prototype detected trash volume in the trash can, and send the information through the monitoring server via a cellular network in real-time. So that the trash management, in this case, Dinas Kebersihan, could be efficient. In which the trash can located in various places could be easily monitored through the website. The results show, optimum range for the sensor that installed in the trash can is maximal 25 cm, in which for every trash that detected by sensor must be in range of 0 cm between 4.5 cm, where the position of the sensor does not face to face so that the sensor detects more accurately in determining the volume of free space in the trash.
In the past, statisticians, programmers, and data scientists handled data analytics, rarely interacting with companies directly. However, this "experts only" method of data analysis and display has been altered by more user-friendly data visualization, dashboards, and mashup technologies. With improvements that make it possible for people at all levels of an organization to analyze data in meaningful ways, data analytics is being pushed into business. The reporting and visualization tools that statisticians formerly used are now being improved by manufacturers of enterprise-grade analytics. This study describes how dashboards help businesses optimize their operations. And how business dashboards are developed using real-time data and people's innate capacity for visual thought.
The utilization of Internet of Things (IoT) technology, especially in remote areas, is still relatively low, even though the technology is required to implement smart farming or smart villages, which aims to improve the quality of life of people in rural areas. The high investment cost for IoT networks that still use cellular networks or Wi-Fi is one of the causes of the slow implementation of this technology. Our previous research has developed an alternative network for IoT devices in remote areas with the concept of a Tandem Multihop Wireless Network focusing on developing simple message scheduling. This research focuses on implementing ad-hoc routing protocols in tandem with multi-hop wireless to analyze the advantages and disadvantages of the protocol. Each sensor periodically sends data to the monitoring server via IoT devices on each tower. The scenario was implemented using MININET-WIFI. Evaluations were carried out to determine delivery probability, latency average, and jitter. In general, the two Ad-Hoc protocols tested, namely OLSR and BATMAN, had the same performance when the data sent was 1 MB, but when the data size was increased to 2 MB, the OLSR routing protocol on several nodes had better performance than BATMAN.
In the past, statisticians, programmers, and data scientists handled data analytics, rarely interacting with companies directly. However, this "experts only" method of data analysis and display has been altered by more user-friendly data visualization, dashboards, and mashup technologies. With improvements that make it possible for people at all levels of an organization to analyze data in meaningful ways, data analytics is being pushed into business. The reporting and visualization tools that statisticians formerly used are now being improved by manufacturers of enterprise-grade analytics. This study describes how dashboards help businesses optimize their operations. And how business dashboards are developed using real-time data and people's innate capacity for visual thought.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.