We want to carry out cleaning where it is needed most, instead of focusing on frequency. Cleaning areas that do not need cleaning does not create value and is a waste of resources. Conversely, not cleaning extremely dirty premises leads to unnecessary wear and tear.
We know that the use and thus the dirtying of premises varies over time. Some days are rainy and entrances get extra dirty. Other days there are a lot of visitors and the guest toilets are used more than other days. These examples highlight the value of a flexible delivery model if we can identify where and when cleaning needs to be prioritised. We call this type of delivery model data-driven cleaning.
Different types of information are needed to facilitate data-driven cleaning. We may need sensors that continuously provide our cleaners with information on how many people are in the customer’s premises and what the air quality is like in each room. Information that helps the cleaners prioritise where to clean.
We might also need to look at seasonal variations at the customer’s premises. Perhaps we can see patterns over time linked to how the premises are used and adapt the cleaning to them, or use historical data and weather forecasts. The more sources we can integrate, the smarter the solutions we can offer. By collecting relevant data, we can optimise our resources and deliver a cleaner experience that better preserves our customers’ properties.