A Simplistic Machine Learning Approach to Contact Tracing
This work provides an improved method for contact tracing by more accurately estimating phone-to-phone distance, which is important for public health applications.
This paper addresses the problem of estimating the distance between two phones using handcrafted features from phone instrumental data. The developed GBM and MLP models significantly outperform the leading NIST challenge result by HKUST.
This report is based on the modified NIST challenge, Too Close For Too Long, provided by the SFI Centre for Machine Learning (ML-Labs). The modified challenge excludes the time calculation (too long) aspect. By handcrafting features from phone instrumental data we develop two machine learning models, a GBM and an MLP, to estimate distance between two phones. Our method is able to outperform the leading NIST challenge result by the Hong Kong University of Science and Technology (HKUST) by a significant margin.