2020/01/01 by Jannis Walk, Robin Hirt, Walk, Jannis +5 · 1 citation
Agricultural and Biological Sciences · Decision Sciences · Energy · #Applications (stat.AP) #Energy Efficiency and Management #Energy, Environment, and Transportation Policies #FOS: Computer and information sciences #Food Waste Reduction and Sustainability #Forecasting Techniques and Applications #Machine Learning (cs.LG) #Machine Learning (stat.ML)
paper · pdf · doi:10.48550/arxiv.2003.13304
openalex publication_date 2020/03/30 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Reverse Vending Machines (RVMs) are a proven instrument for facilitating\nclosed-loop plastic packaging recycling. A good customer experience at the RVM\nis crucial for a further proliferation of this technology. Bin full events are\nthe major reason for Reverse Vending Machine (RVM) downtime at the world leader\nin the RVM market. The paper at hand develops and evaluates an approach based\non machine learning and statistical approximation to foresee bin full events\nand, thus increase uptime of RVMs. Our approach relies on forecasting the\nhourly time series of returned beverage containers at a given RVM. We\ncontribute by developing and evaluating an approach for hourly forecasts in a\nretail setting - this combination of application domain and forecast\ngranularity is novel. A trace-driven simulation confirms that the\nforecasting-based approach leads to less downtime and costs than naive emptying\nstrategies.\n