I dabbed a little into land value surfaces estimations using ML/neural nets. The implementation was surprisingly straightforward and results don’t look completely insane. For instance, the surfaces are not as smooth as kriging (good!) but I have no idea how reliable the ML estimates really are. More work is needed, for sure, but it is exciting to already see the spatial and the temporal dynamics.
The Cambridge Endowment for Research in Finance (CERF) has published a blog post on Kahshin Leow’s and my research on predictable REIT returns: https://www.cerf.cam.ac.uk/blog/blog-2024
Spring has arrived both at home and at work.
This Wednesday (March 20) will be busy: First, I’ll head to the University of Reading for a research seminar (12–1 pm). My paper shows how REIT return predictability increases when machine learning methods are allowed to shine. In the evening (6:15—7:15 pm), I will take part in a seminar on generative AI organised by the Society of Property Researchers in London. Pretty excited to share my work and to meet new and old friends.
Spring arrived early this year. The apricot is flowering, to the delight of big bumble bees. Let’s hope there will be no more frosty spells.
