The Application of Machine Learning Algorithms in Predicting the Usage of IoT-based Cleaning Dispensers Machine Learning Algorithms in Predicting the Usage if IoT-based Dispensers Tobechi Obinwanne ∗ University of Applied Sciences Upper Austria tobechi.obinwanne@fh-steyr.at Chibuzor Udokwu University of Applied Sciences Upper Austria chibuzor.udokwu@fh-steyr.at Patrick Brandtner University of Applied Sciences Upper Austria patrick.brandtner@fh-steyr.at ABSTRACT Internet of Things (IoT) based liquid cleaning dispensers are being increasingly used in public buildings for personal sanitation pur- poses. However, it is not always easy for facility managers to keep track of, as well as predict product usage. Most devices deployed at facilities still require the facility/building manager or staf at the facility, to check the devices from time to time. In recent years, the need to efectively utilize these devices as well as anticipate usage rates has become necessary because the time lag between reflling the dispensers and their being out of service can pose health risks. This paper thus explores how machine learning (ML) algorithms can be applied to improve the availability of IoT-based liquid clean- ing dispensers. The goal of the paper is to apply machine learning in predicting the daily usage volumes of cleaning solutions, thereby increasing the efciency of the cleaning dispensers. The paper com- pares diferent machine learning algorithms to determine the best algorithm for predicting the usage patterns of IoT-based cleaning dispensers, thereby, develops a predictive model that can be applied to improve the availability of cleaning products in IoT-based dis- pensers. The results of the analysis show that the Random Forest algorithm performed best among the evaluated models using regres- sion performance measures. Hence, ML algorithms can be applied to help building or sanitation managers improve the availability of cleaning products in IoT-based cleaning dispensers, ultimately improving the user experience. CCS CONCEPTS · Applied computing → Enterprise computing; · Information systems → Information systems applications. KEYWORDS Internet of Things, Machine Learning, Data Preprocessing, Regres- sion Models ACM Reference Format: Tobechi Obinwanne, Chibuzor Udokwu, and Patrick Brandtner. 2023. The Application of Machine Learning Algorithms in Predicting the Usage of ∗ Corresponding author. This work is licensed under a Creative Commons Attribution International 4.0 License. ICEEG 2023, April 27–29, 2023, Plymouth, United Kingdom © 2023 Copyright held by the owner/author(s). ACM ISBN 979-8-4007-0839-8/23/04. https://doi.org/10.1145/3599609.3599637 IoT-based Cleaning Dispensers: Machine Learning Algorithms in Predicting the Usage if IoT-based Dispensers. In 2023 7th International Conference on E-Commerce, E-Business and E-Government (ICEEG 2023), April 27–29, 2023, Plymouth, United Kingdom. ACM, New York, NY, USA, 7 pages. https: //doi.org/10.1145/3599609.3599637 1 INTRODUCTION The Internet of Things (IoT) refers to the integration of physical devices with the internet, allowing for remote monitoring of sensor readings, remote control, and automation [1]. COVID-19 caused increased hygiene practices and a surge in IoT-integrated liquid cleaning dispenser usage. [2]. Outbreaks tend to occur in spaces with lower hand hygiene adherence and are associated with rapid improvements in hand hygiene performance [3]. Hand hygiene has always been considered one of the most efective, reproducible, and low-cost weapons to deal with some infections [4]. The good health habits acquired during the COVID-19 pandemic should be maintained even after the virus is eradicated [4]. The use of Internet of Things (IoT) technology has made it possible to improve the accessibility and usage of various devices and systems [5]. IoT in cleaning dispensers improves product availability and accessibility for hygiene [6]. The cleaning dispensers are equipped with IoT technology that allows for remote monitoring and control of their operation [6]. IoT cleaning dispensers face availability and usage challenges, including inconsistent dispenser availability causing user frustration. [6]. IoT-based liquid dispensers also provide valuable data and in- sights that can be used to improve the dispensing process. These dispensers collect liquid dispense data and relevant information for trend analysis, pattern identifcation, and improvement areas. [7]. IoT cleaning dispensers improve cleaning product availability and accessibility in public spaces. [6]. The cleaning dispensers are equipped with IoT technology that allows for remote monitoring and control of their operation [6]. Despite the advancement of IoT technology in cleaning dispensers, they still face some challenges in terms of their availability and usage. One of the major challenges is the inconsistent availability of the dispensers, which leads to frustration for users who are unable to fnd a dispenser when they need it [6]. This is often a result of the need for building or facility managers to conduct manual checks on the dispensers to know when the dispenser’s liquid content is exhausted and manually re- fll the same [2]. Furthermore, IoT dispensers don’t estimate liquid usage to enable managers to order appropriate amounts and make plans. The goal of this paper is to explore how machine learning algo- rithms can be applied to improve the availability of IoT-based liquid 188