Parcl Labs Price Feed White Paper UAE (Dubai)

Executive Summary

• The Parcl Labs Price Feed (PLPF) for Dubai is an indicator that tracks daily price changes in residential real estate across Dubai. It utilizes a simple metric: price per square meter in dollars, using the fixed exchange rate of 3.6725 United Arab Emirates Dirhams to 1 USD.
• Existing data sources fail to provide complete, timely, and accessible information. The REIDIN UAE Residential Property Price Indices (RPPIs) is published monthly with a lag of two months, in a unit that makes it hard to assess price movements. Other sources, like the Residential Sales Price Index by the Dubai Land Department (DLD), have not been updated since 2023.
• To overcome these limitations, we have implemented an enterprise-level ETL process. This process involves ingesting, cleaning, and transforming millions of individual data points, leveraging spatial data science to generate price estimates for different geographic levels.
• Our methodology examines representative market segments and filters outliers and other irregularities to create smooth time series that are tested daily to maintain the quality of our indicator. To further enhance the accuracy and relevance of our price feed, we employ a range of time series smoothing techniques. These methods leverage both historical data sources and more timely information, aligning with the gold standard established in our Parcl Labs Price Feed White Paper.
• The PLPF for Dubai empowers users to make better-informed decisions and can be accessed through our user-friendly API.

Introduction

Dubai is one of the cities in the world that has experienced a surge in interest to invest in and buy real estate, frequently being labeled as one of the top markets for residential real estate. Despite its popularity, the available tools to make informed decisions are incomplete, lagged, and hard to access. The Dubai Residential Sales Price Index (DRSPI), created by the Dubai Land Department (DLD), offers information on price changes measured both as a price and index movement on a monthly, quarterly, and yearly basis. While the index does provide information that can be interpreted directly its estimates are smoothed with a 12-month moving average, thus underestimating rapidly changing conditions such as those observed during the COVID-19 pandemic. Additionally, the index, as of June 2024, was last updated in October 2023.

Other sources, like Dubai’s residential property price index (RPPI) produced by Reidin, have a lag of 2 months. They do not make the historical data easily accessible and present the price variation using an index, making it hard to translate into a commonly used metric without access to the original data used to build the indicator.

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 Feed for Dubai. 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 measured in dollars using the a fixed exchange rate of 3.6725 dinars per dollar. To arrive to this exchange rate we utilize The Central Bank of the United Arab Emirates official rate of 3.672 UAE Dirhams for buying USD and 3.673 for selling USD and divided them by 2. This allows for an easier comparison with our existing USA Price Feeds.

Data

The segmentation, inaccessibility, and incompleteness of data pose significant challenges in creating reliable price feeds in the UAE. To address these challenges, we rely on historical sales data alongside more timely information from real estate property listings. We focus on residential properties such as villas, apartments, penthouses, etc., allowing us to combine historical trends with more up-to-date data. The use of real-time sources such as listings allows us to better represent existing market conditions faced by everyday consumers.

Like other Parcl Labs Price Feeds, we employ a rigorous process to create a top-notch data warehouse to develop our Dubai 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.
• 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. While we are initially launching in Dubai, we have the capability to replicate this process for other parts of the UAE at any geographical level desired.

Data Integration, Standardization, and Processing

Just as we do for our Parcl Labs Price Feed, our data is processed through our ETL process described here. Once we have ingested the data points, it undergoes a validation, integration, standardization, and enrichment procedure:

• Cleaning, Deduplicating, and Standardizing: We clean, deduplicate, and standardize information to ensure the data for each rental unit is up-to-date and accurate. This step is crucial when collecting information from multiple data sources as it eliminates redundant information.
• Data Reconciliation for Historical Records: We reconcile data to ensure consistency over time for each property record, addressing the unique idiosyncrasies and time lags of each data source.
• Geospatial Mapping: We leverage geographic information systems technology to classify properties into various market types using government-provided legal boundary definitions. This allows us to assign properties to multiple levels of geography, ensuring our price feeds are scalable and accurate.

Once the data standardization process is completed we have a unique  state-of-the-art database to build scalable and timely PLPF for any desired level of geography, a necessary step before we can build the most timely residential real estate rental data.

Price Feed Methodology

We follow the same steps outlined in our original Parcl Labs Price Feed White Paper to guarantee inputs into our price feed that address outliers, anomalous operations, and data sparsity by constructing a back-propagation window based on the volatility of transaction volume. This method examines how many transactions are available in each market during a given period before deciding how far back in time to look to create a sample space. The selected window varies by type of information to reflect local idiosyncrasies and capture the relevant data volume. We also conduct additional data cleaning processes to ensure that only relevant observations are included in the price feed calculations, as Dubai and the UAE have multiple different ways of recording real estate transactions.

Given the skewed nature of real estate transactions and the existence of outliers in a market with many luxury deals, 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 15th and 80th percentile of the price distribution. This ensures the representativeness and robustness of our approach, considering that the real estate distribution tends to be heavily skewed, requiring the filtering of outliers.

Figure 3. Distribution of Sales Prices in Dubai in 2023

With the sample space defined and outliers filtered, we use a weighted average, as described in our Price Feed White Paper, intertwining historical sales with timely sources such as listings. This allows us to obtain a more representative sample of the real estate market and incorporate longer-term trends into our timely information. Finally, we employ a 21-day smoothing process to further minimize the impact of market fluctuations.

We arrived at this configuration of parameters after running thousands of simulations to understand the trade-offs between different parameters and to ensure the most balanced and timely data.

Figure 4. PLPF Experiments to Find Optimal Time Series for Dubai

As an additional quality control metric, we also calculated the Pearson correlation coefficient for the Parcl Labs Price Feed series from March 2011 to November 2022, the last available point for download, using the median price for a given month of our price feed. Our analysis found a correlation of 0.8, indicating a very strong positive correlation between official figures and our daily price feed. This serves as proof that robust and easily accessible daily data is possible.

Conclusion

The fragmentation and lack of transparency in real estate data in the Dubai 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 Dubai revolutionizes how we access real estate data in the UAE, one of the most sought-after markets in the world. By meticulously tracking daily price changes in residential properties across Dubai, the PLPF empowers users with timely and comprehensive information like never before in a unit that is easy to compare across markets.

At Parcl Labs, we continue to work on products to accurately reflect the real estate market.

With our user-friendly API, the Parcl Labs Price Feed for Dubai empowers users to make confident, informed real estate decisions. Sign up today and unlock the potential of advanced real estate analytics.

‍