I'm a software engineer with more than 10 years of industry experience mainly in the GIS field. I hold the position of Lead engineer at HERE technologies where I head a development team in charge of the creation and maintenance of location based services belonging to the HERE technologies platform. My focus is on leveraging the most recent techniques in machine learning and data analysis to improve the quality of our products.
Speeches di Marco Catalano
Global Heat map and learning to rank
Reverse geocoding is one of HERE Technologies most heavily used services and a huge amount of data is produced by its access logs. From this data geocodes can be extracted and then counted with respect to some cellulation of the earth creating a sparse heat map. For our Place & Address Search products we use such a heat map to define a notion of relative place importance useful to index and rank addresses and places. However, the large data size, sparsity, and variations in traffic from which different heat maps may be derived, makes faithful visualization and comparison a challenge.
In this talk I will focus on describe how we are able to collect, visualize and compare this information and how we make use of it, together with machine learning techniques, to improve our address autocompletion service.