Parcl Labs Price Feed White Paper - UK (London) V2

January 24, 2024
5
min read
Parcl Labs Price Feed White Paper - UK (London) V2

Executive Summary

  • In September 2023, we released the first version of the Parcl Labs Price Feed (PLPF) for London, an indicator that tracks daily price changes in residential real estate in the London area. The metric is price per square meter in British Pounds.
  • After a few months of evaluation, we are releasing an improved version that better reflects the live conditions of residential real estate in London. Our new London price feed uses an enhanced weighting schema where official historical sales and more timely data have a more balanced weight on how the final prices are calculated.
  • We improved our data pipeline to ingest, clean, and transform millions of individual data points across multiple sources, leveraging spatial data science to generate precise price estimates for London. We have used this approach to build price feeds for multiple cities in the USA and France.
  • We ran thousands of experiments to further enhance the accuracy and relevance of our price feed and to determine the optimal parameters for our smoothing time series techniques. These techniques are a continuation of the gold standard defined in our Parcl Labs Price Feed White Paper.
  • 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.

Figure 1. Parcl Labs London Pricefeed V2

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.

The challenge of obtaining timely information is exacerbated by the incomplete nature of more timely sources like property listings, which often lack vital details such as the exact location of a residence. Additionally, there is no straightforward method for discerning duplicative information, rendering these sources insufficient on their own for deriving meaningful insights.

Today, we are excited to announce an updated version of our Parcl Labs Price Feed for the Greater London Region, commonly known as London. This release builds upon our previous London Price Feed, offering optimizations to better reflect the current market conditions of residential real estate in London.

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 semi-detached 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.

Figure 2. Map displaying data points used to calculate the Parcl Labs London Price Feed

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.

In version 2 of the price feed we added additional filters in how we select properties and the deduplication process, to form a better representation of the market.

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 sparse nature of the data, we conducted several experiments to determine the optimal configuration of percentiles for our sample space. In version 1 of our price feed, we utilized observations falling between the 20th and 80th percentiles of the price distribution. After running thousands of simulations with varying percentiles, we concluded that the new version will incorporate observations between the 20th and 90th percentiles. This approach allows us to better reflect the distinct dualities within the London real estate market, particularly the significant real estate transactions in the higher echelons of the sector.

Figure 3. Distribution of Sales in London in 2022-2023 as Measured in Price per Square Meters in British Pounds

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. In V2 of the pricefeed we also modified the parameters in the final smoothing process, with a shorter window for our moving average.

We also conducted tailored testing for the London pricefeed using the previous pricefeed as well as the official index published by the UK government. Our analysis shows that the fundamental relationship with the previous version as well as the government data remains unchanged. This results in a time series that rigorously tests for any sudden movements in the price per square meter. The Pearson Correlation Coefficient for the Parcl Labs Price Feed London V2 series and the UK Price Home Index for the Greater London Region from January 2010 to November of 2023 using the median price on a given month of our price feed found a correlation of 0.97, 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.

Figure 4. Correlation Between Parcl Labs Price Feed London V2 and House Price Index for the London Region

Conclusion

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

Today we are updating the only available daily price indicator of residential real estate available for London. Our new price feed improves the timeliness of our data, and better captures the bifurcated nature of the London market while maintaining the gold standard of our first price feed.

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!

Table of Contents
There are no table of contents for this article.