We are very happy to announce that Maya Arditi, advised by Eran Toch and Irad Ben Gal, had successfully defended her Master’s thesis, “Privacy-Preserving Synthesis of Human Mobility Location Sequences”. 

People’s location data is continuously tracked from a multitude of devices and sensors, enabling the ongoing analysis of sensitive information that can re-identify individuals or reveal sensitive information.

Maya had analyzed the use of different synthetic data generation models for long location sequences, including long short-term memory networks (LSTMs), Markov Chains, and variable-order Markov models (VMMs).

Examples of location diaries generated by LSTM and other methods

She employed different performance measures, such as data similarity and privacy, and introduce different measurements to quantify each of these measures.  Her experiments, based on the anonymous data of 300 thousand users, show that different models can be used with different data analysis applications, such as traffic prediction or lifestyle analysis.