| dc.description.abstract | Waste management is a critical issue worldwide. One of the major challenges in waste management is the efficient collection and transportation of waste from the source to the disposal facility. Research shows that systematic adoption of data-driven technologies (e.g. Machine Learning and Internet-of-Things) can assist public utilities (Kommune) by a) improving the waste collection management process, and b) minimizing the total incurred cost (Misra et al., 2018; Komninos, 2007). Thus, in this work, we show that systematic adoption of data-driven techniques can significantly improve the waste collection process and minimize the incurred cost to public utilities. In order to perform experiments, we generated a synthetic dataset motivated by a real-life urban environment. Also, we aimed to present different approaches to cost-benefit analysis in the targeted scenario. Our study shows that the systematic use of Internet-of-Things-based smart garbage bins, smart transportation algorithms, and Machine Learning can significantly reduce the total incurred cost of public utilities operating in this space. | |
