Parcl Labs Price Feed White Paper - UK (London)

Executive Summary

• The Parcl Labs Price Feed (PLPF) for London is an indicator that tracks daily price changes in residential real estate in London, using a simple metric: price per square meter in British Pounds. The London PLPF is 2.5 months faster than existing state.
• Existing data sources suffer from incomplete information and are lagged in the timeliness of their data and, as such, present an out-of-sync view of the real estate market. The UK House Price Index, the official metric that tracks real estate prices, has a two-and-a-half-month lag and does not include information about surface of residences, thus making comparisons difficult.
• To overcome these limitations, we constructed a data warehouse using multiple data sources such as historical records and more timely sources like listings. We then use our enterprise-level ETL process to ingest, clean, and transform millions of individual data points, leveraging spatial data science to generate price estimates for London. We have used this approach to build price feeds for multiple cities in the USA and France.
• To further enhance the accuracy and relevance of our price feed, we employ a range of smoothing time series techniques. These techniques consider historical government data sources and more up-to-date information, ensuring alignment with the gold standard defined in our Parcl Labs Price Feed White Paper.
• Our data provides a daily snapshot of real estate activity in London that is representative of overall market tendencies. We backtested our daily indicator with the UK House Price Index for London and found a correlation coefficient of 0.96 showing that daily data accurately reports what will happen in 2.5 months via the UK House Price Index
• The PLPF for London empowers users to make better-informed real estate and investment decisions. Contact our team today if you want to access London and other global market price feeds.

Introduction

Real estate in London is characterized by a data ecosystem that is lagged, incomplete, and siloed. The HM Land Registry, a non-ministerial government department in charge of maintaining records of transactions and land ownership details, publishes information about real estate transactions with a lag of 2 and a half months in the best of cases and several months in some instances. This official release of the Price Paid Dataset contains information about transactions of real estate in the UK, and even though it provides information about the type of property sold and the price paid, additional characteristics about the residences sold, such as total surface area and other home characteristics (bedrooms, bathrooms) are not provided. Further, this release does not include the exact location of a property to the latitude and longitude level.

The other primary source of information on real estate prices for London is the UK  House Price Index, a hedonic index that tracks movements of residential real estate in the UK for multiple levels of geographies and residence types. This data source also suffers from lags and does not mention what additional fields are used to construct the index.

Today, we are proud to announce that Parcl Labs continues its mission of providing high-quality information to our customers by introducing the Parcl Labs Price Feeds for the Greater London Region, commonly known as London. Our price feeds are the first of their kind, offering real-time indicators that track the evolution of real estate prices using the widely recognized metric of price per square meter.

Data

The segmentation and incompleteness of data pose significant challenges in creating reliable price feeds in the UK. To address these challenges, we rely on historical data alongside more timely information from real estate property listings. We focus on residential properties, including flats (condos), terraced homes, and detached and semidetached homes, allowing us to combine historical trends with more up-to-date data.

Like other Parcl Labs Price Feeds, we employ a rigorous process to create a top-notch data warehouse to develop our London Price Feed. This process involves:

• cleaning, deduplicating, and standardizing information to ensure the highest quality records for each property. This means we only utilize transactions with complete information and compare them across different sources to guarantee an appropriate representation of residential real estate.
• In the case of historical sales, we validate the accuracy of addresses using a third-party source to prevent duplicate data entries and ensure data integrity.
• Once the data is cleaned, standardized, and processed, we leverage state-of-the-art geographic information systems technology to assign properties to multiple types of markets. This enables us to select specific information for desired markets and facilitates tailored analysis at various geographical levels, such as boroughs.

Once the data standardization process is completed, we funnel standardized data into a unique, state-of-the-art database to build scalable and timely price feeds for any desired level of geography. And while we are launching just in the Greater London region, we have the capability to replicate this process for other cities, boroughs, parishes, etc.

Methodology

We took our data and filtered outliers and anomalous operations as we did with the Parcl Labs Price Feed white paper. To address the sparsity of real estate transactions, we followed the same approach as our original price feeds and constructed a dynamic back-propagation window based on the volatility of transactions. This simply looks at how many transactions in a given period of time are available in each market before deciding how far back in time we are going to look to create a sample space. The window selected changes by market, to reflect local idiosyncrasies and capture the relevant data volume.

Given the sparsity of the data, we conducted several experiments to understand the optimal configuration of percentiles to be used in our sample space. Our experimentation indicated that we get a good representation by using observations that fall between the 20th and 80th percentile of the price distribution. This ensures the representativeness and robustness of our approach, considering that real estate data distributions tend to be heavily skewed, requiring the filtering of outliers.

After this initial estimate is conducted for both timely sources as well as historical data, we use a weighted average with a set of geometric weights for the periods where there is overlap between both series such that the impact of mixing different data sources is gradual and does not produce anomalies in the time series. This allows us to obtain a more representative sample of the real estate market and incorporate longer-term trends into our timely information. The last step is to perform a final smoothing process using a moving average that is tailored to each market to filter out the impact of anomalies on price fluctuations.

To guarantee the consistency and reliability of our data, we conduct tailored testing for each one of the markets available in our API before publishing a data update. This testing considers abnormal behavior in the different data sources that compose our database, the local market idiosyncrasies that explain volatility in volume and prices, and geographic factors that further adjust the volatility of our series. This results in a time series that rigorously tests for any sudden movements in the price per square meter.

As an additional quality control metric, we also calculated the Pearson correlation coefficient for the Parcl Labs Price Feed series and the UK Price Home Index for the Greater London Region from January 2010 to June 2023 using the median price on a given month of our price feed. Our analysis found a correlation of 0.9, a very strong correlation between official figures and our daily price feed. This serves as proof that daily data that is robust and easily accessible is possible.

Conclusion

The fragmentation and lack of transparency in real estate data in the London market have prevented users and consumers from making informed decisions regarding residential real estate. Incomplete and siloed information has been the norm for a long time.

Today the Parcl Labs Price Feed (PLPF) for London revolutionizes how we access real estate data in the UK market. By meticulously tracking daily price changes in residential properties across the Greater London region, the PLPF empowers users with timely and comprehensive information like never before.

With our user-friendly API, the Parcl Labs Price Feed for London puts the power of informed decision-making directly into the hands of our users. Get ready to make confident real estate choices like never before!

‍