Machine Learning in Real Estate


I recently had an honor to speak about automation for real estate at the IMN’s COO/CFO Forum in New York (awesome crowd!) This post is partly a reflection on what we heard and ideas we shared at the conference. Capital Brain has been around for about 3 years now and we see that the excitement around ML/AI keeps growing. It’s not hard to understand: robots work 10x faster than humans, 24/7, they don’t take vacations and don’t call in sick.

At Capital Brain we automate internal processes in real estate companies by applying data mining and machine learning. The core of Capital Brain technology is the ability to read structured and unstructured data: macro economic factors, CRE industry activity and active players. Then we search for patterns and push insights directly into internal systems via an API.

Such approach allows to automate plenty of mechanical tasks: professionals can receive macro economic numbers directly into their budgeting and underwriting models, they can use data science to identify the next hot market for acquisitions, or even receive real-time competitive intelligence for benchmarking.

Areas in real estate ripe for automation

If you are looking to move away from excel and start applying smart process automation, you need to know that there are two categories of tools available to you:

  • Robotic process automation involves automation of mechanical tasks traditionally done by humans. Typical examples are investor reporting or accounting tasks and the main value proposition here is cost cutting. E.g. private equity clients would be able to substantially drop the asset management fee by automating their investment strategies. All those savings they will be able to pass down to their institutional LPs.


  • The second tool involves judgement-based approach when ML is used to write rules-based software that’s able to make decisions for a human. The value proposition here could be top line optimization. For example, if you are tracking hyper-local submarket activity around your property and you know the correlation between certain types of events (like a conference or a new development announcement) and your asking rent, you can write a ML code that would optimize the rent whenever the same type of event occurs next time.

Implementation approach

You have to have a plan. Period. You have to understand where the smart processing will help you the most. Where the biggest effect on the bottom line would be. This initiative should come from the top. The executive team must realize that automation is not a tactical opportunity, it’s a strategy. Once implemented, it’ll change the operational models and perpetually change how the work is distributed among people and systems. 

It’s no doubt, smart processing requires disciplined execution, time and some grit. You have to think about how automation will affect the composition of your talent pool and the org chart. It’s clear that after implementation the size of your team will change and you have to keep an open communication about it. But in the end, the team will benefit greatly: they’ll be performing less mechanical tasks, will spend more time applying judgement, and will acquire new skills to accommodate higher value work.

Smart process automation will do more than make a few processes better. With the right approach it’ll will make you challenge the established thinking, will bring substantial decrease in costs and a huge competitive advantage.


Looking to automate manual processes and cut costs? Contact Us