Did An AI Buy This Property?
The importance of location in real estate is particularly evident in the saying “location, location, location,” which is often cited as the most important factor in determining the value of a property. The advice to “buy the worst house in the best street” can be a sound strategy in some cases. The idea behind this advice is that a property’s value is influenced not just by its own characteristics, but also by the characteristics of the surrounding neighborhood.
Location can have a significant impact on a person’s life, but the extent to which it predicts a person’s life can vary depending on various factors. For example, where a person lives can influence their access to educational and employment opportunities, the quality of healthcare available, and the safety of their environment. Additionally, the culture, traditions, and social norms of a particular location can also shape a person’s experiences and perspectives.
With location having such a strong influence on real-world outcomes, your AI systems will benefit from the feature engineering of location data. While the most commonly used location features are city and state names, categorical location features such as these are less than optimal due to their high cardinality and the difficulty in grouping similar locations. It is good practice that location signals be in the form of
- Latitude and longitude
- Distance to another location e.g. distance to the nearest hospital or capital city
- Distance traveled in a period of time
- The grouped characteristics of nearby locations e.g. the socio-economic attributes or population density of the state or local region
Experimenting with these features and serving them in production can take a lot of time and energy. We’ve built an open-source feature engineering library that makes it easy to create these location signal types and more! Click here for a free download, with worked examples in Python: https://docs.featurebyte.com/