Building value with data.
A combination of domain expertise and technology
Kania combines fundamental knowledge of real assets investments with technological advances in data analysis and processing.
We focus on quantitative analysis of real estate markets, provide analytics, identify and test predictive characteristics of data and deploy ML processes to large data sets for superior information and insights.
For inquiries please contact info@kaniaadvisors.com
Alternative Data
We identify, test and produce specific data sets that offer improved insights or predictive characteristics.
Nowcasting
Alternative and live data sets to monitor economic activity relevant to real estate markets
Geolocation
Geolocation data and analytics to drive granular insights and assess location specific market and asset dynamics.
Listed Markets
Our listed alternative beta indices have generated consistent, repeatable and significant outperformance to benchmark by focusing on factors relevant to real estate markets, not general equity market factors. ➔
Listed real estate securities
Why listed real estate securities markets are more suitable for systematic alpha with consistent, repeatable processes potentially offering more attractive outcomes.
Rental growth is one of the main focus areas of fundamental managers, but how does it materialise in listed REITs funds portfolios.
What does trading activity in fundamental funds tell us about forward-looking aspects of portfolio construction.
For information about systematic alpha, our indices or our specialist factor data for listed real estate securities markets, please contact info@kaniaadvisors.com
Machine Learning
Processing geolocation data using ML
Machine learning techniques can be used to get accurate real estate market information. In this case we track new supply at a submarket geolocation over a period of time which provides accurate, specific and timely information about new construction activity, number of projects, size of projects, completion timelines and overall available stock supply. This allows us to monitor logistics assets at any location including markets where traditional estimates or coverage might be insufficient or unavailable. Further, machine learning techniques can process large volumes of data and provide valuable insights for investment decisions.
