For a travel agency we developed a machine learning model that predicts the preferred holiday type for unregistered website visitors based on their unique interactions with the site.
First time visitors of the site are exposed to holiday content aimed at a broad audience. The model allows the content to be tailored to the (returning) visitor, such that visitors are more likely to find and buy the vacation that best matches their needs. The machine learning model is based on features derived from clickstream data captured by Google Analytics.
To train the model we combine several data sources on an Oracle Big Data Appliance running a Cloudera Hadoop cluster, including Google Analytics data and transaction data from an Oracle database. Similar machine learning models can be used to personalize the content of other types of webshops from visitor clickstream data.
More information?
Do you want more information about our machine learning models or other Data Science solutions? Fill in the form below and we'll contact you. You can also contact us via 070-3195000.