Customer Profiling Using Internet of Things Based Recommendations
Discovering customer interests through customer profile extraction and integration from various sources of customer shopping data and deploying into an IOT framework
Working with collaborators from University of Carthage, University of Madinah and Ajou University, Ali Tufail from School of Digital Science, Universiti Brunei Darussalam and his team have developed a customer profiling system using IoT-based recommendations. First, the model is trained on existing customer datasets from several online stores for customer profile extraction and store profiling. Next, profile integration is done to combine data derived from multiple sources. This is followed by customer segmentation profiling to determine which group of customers has the biggest interest for a certain product. The model is then applied in a real-world scenario, deployed on a Raspberry Pi and integrated into a IOT system using other sensors such as a camera. The system is evaluated based on the forecast accuracy of the most appropriate products.
This work has been published in the journal MDPI Sustainability titled Customer Profiling Using Internet of Things Based Recommendations. Please read their full paper here.
—
Universiti Brunei Darussalam
Jalan Tungku Link, BE1410
Negara Brunei Darussalam
office.sds@ubd.edu.bn