We were lucky to have Drew Conway, Head of Data Science at Two Sigma Real Estate’s private investment platform, as our keynote speaker for VTS Accelerate 2024.
Conway shared his insights into the integration of data science and machine learning within the real estate sector. His talk focused on Two Sigma’s approach to leveraging technology for data-supported investment decisions. Check out our recap below to learn his main points.
Integrating data science with real estate expertise
The core of Conway's presentation revolved around Two Sigma Real Estate's approach to integrating data science and machine learning with traditional commercial real estate expertise.The goal is not just to collect data but to develop proprietary metrics and models that provide accurate, actionable insights.
Two Sigma Real Estate uses a variety of data sources, including market trends, economic indicators, and property-specific information. The data science team works closely with real estate investment professionals to make sure their models and metrics are practical (and useful) during various stages in the real estate investment process.
By aggregating and analyzing this data, they can see patterns and trends that might not be obvious through traditional analysis alone.
Ensuring the integrity and quality of data
Data integrity is a very important piece of the puzzle, especially in real estate, which has notoriously messy data. Conway demonstrated an experiment where he compared reported rent growth data across multiple third-party vendors. The results showed quite a lot of variances in their numbers – not ideal when seeking conviction in making investment decisions.
So, Two Sigma Real Estate came up with property-level statistics that let them pinpoint the strengths and weaknesses of different data sets. This approach helped them to provide more accurate and timely insights.
This can help investment teams spot emerging trends and opportunities faster than competitors.
Transparency is also important in building and testing predictive models. "If your investment team doesn’t have a deep understanding of not only the data that went into a model but how that model was fit . . . they're not going to trust it," Conway explained.
A big part of that process is backtesting. When they compare their past prediction models with the actual results, they can see how accurate those models are. This either helps them stand by their data (if accurate) or adjust their models (if not accurate).
Applying their models to real-world investments
With data science-supported insights, the investment team can filter and focus on high-potential opportunities.
Consumer spending data plays a big role here. Conway explained how connections between consumer behavior and rent growth could inform investment strategies.
"[What] was interesting was the amount of rent growth that we could measure directly in markets that were exposed to high degrees of durable consumer goods spending,” he explained.
Two Sigma Real Estate can use that information to target investments in areas with strong consumer spending trends.
Balancing accuracy and stability in their predictions
Another challenge is balancing accuracy and stability. Investment professionals need accurate predictive modeling, but using only one model may mean it changes too much, which can confuse and frustrate investment team members working on a transaction. Conway discussed how ensemble modeling, which combines multiple models to improve stability, addresses this issue. This methodology has helped build trust with investment professionals, as they can seek to rely on the models to provide accurate and reliable predictions.
Putting the tool into practice
As an example, one of Two Sigma Real Estate's internal tools provides comprehensive data and insights, helping investors make quick decisions.
This tool combines various data sources into one platform, offering real-time analytics and visualizations. It helps investors conduct due diligence, spot opportunities, and generate customized reports and predictive models. Users can dive into detailed data like neighborhood-level rent growth or consumer spending patterns.
Its intuitive interface helps data scientists and real estate professionals collaborate and turn technical insights into actionable strategies.
The impact of data science in real estate investing
In conclusion, Conway outlined the value and impact of a data science approach to real estate investing. His four key benefits were:
- Enhanced Tactical and Strategic Decisions: By combining top-down knowledge with bottom-up data insights, you can navigate macro trends with greater precision.
- Conviction to Act with Precision and Confidence: Data science tools can provide increased conviction needed to make informed investment decisions.
- Native Scale for Rapid Opportunity Identification: An engineered system can allow for quick identification of investment opportunities.
- Risk-Adjusted Enhanced Returns: The opportunity to achieve enhanced risk-adjusted returns by using data science and machine learning.
Two Sigma sets a new benchmark for data science in real estate
In the future, real estate investment will likely see even more reliance on data science and machine learning.
Two Sigma Real Estate’s approach provides a good example of how to successfully integrate data science into real estate and offers a roadmap for others to follow.
Investors who embrace these advancements will be better positioned to navigate the market and drive better portfolio outcomes. With continued innovation and collaboration between stakeholders, the potential for data science in real estate investment is limitless.
