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
Collecting visitor data has long been important to cultural institutions. But as Cesare Fialà explains, the fast-developing fields of AI and machine learning are making it possible to dramatically improve the way that people flow is monitored and forecasted.
“Using the data gathered from a certain location or area, our AI engine is able to forecast people flow for the upcoming periods by pulling together data from all sorts of sources. Factors such as weather conditions and flights into the city can all be built in to help provide accurate forecasts.
“This data is then fed into our optimisation engine which generates resource recommendations for our clients – those being human resources, material resources and financial resources.”