Data analytics for commercial realty

Data analytics is emerging as a key differentiator for asset managers in commercial real estate (CRE). It is helping them strengthen decision-making capabilities, streamline operations, and align portfolios with ever-changing tenant demands and regulatory expectations.

This blog explores how advanced data analytics is redefining how Commercial Real Estate (CRE) firms manage assets and shape investment strategies. It covers the growing adoption of geospatial analytics for precise site evaluation, machine learning (ML) models that enhance price predictions, and real-time anomaly detection that strengthens risk monitoring. The discussion also includes predictive analytics for forecasting lease expirations and tenant renewals, and the use of digital twins—virtual models of assets—for performance simulation and maintenance optimization. Finally, it highlights how ESG and sustainability analytics are embedding environmental and governance metrics into investment decision-making.

Key tools and trends: Geospatial analytics for neighbourhood-level investment insights, ML models (e.g., Random Forests, Gradient Boosting) for price prediction:

Geospatial analytics for neighbourhood-level investment insights

What it is

Geospatial analytics uses AI to interpret satellite imagery, demographic data, zoning patterns, traffic flow and other such datasets. Instead of relying solely on ZIP-code or metro-level comparisons, investors can now evaluate assets block by block.

Use case

A major real estate investment trust (REIT) used geospatial overlays—juxtaposing coastal inundation models of the National Oceanic and Atmospheric Administration with property locations—to identify $87 million worth of assets at risk. By executing divestments and securing the at-risk sites, the REIT reduced its climate risk exposure by 62%.

ML for price prediction

What it is

AI models such as Random Forests, Gradient Boosting Machines (GBMs) and neural networks can model CRE prices using variables such as macroeconomic indicators, lease structures, tenant health, foot traffic, and amenities.

Traditional regression models fail to capture how non-linear relationships and outliers can affect datasets. ML models, however, adapt over time and provide confidence intervals around predictions, enabling better buy/sell decisions.

Use case

Organisation: A leading real estate AI analytics firm

Application: The platform analysed public records and economic datasets across New York to identify $2.1 billion worth of commercial properties that would be undervalued by 2025. Its predictive models identified surging demand in Harlem’s creative corridor, flagging office-to-condo conversions as an opportunity to earn an attractive 12% return on investment.

Real-time anomaly detection for risk monitoring

What it is

AI monitors building-level internet of things (IoT) data (energy usage, HVAC load, occupancy sensors, etc.), leasing activity, and even tenant sentiments to flag unusual patterns before they become critical risks.

Use case

Organisation: A global facilities management firm

Application: The firm’s smart building solution integrates AI and sensor-driven data streams to proactively detect equipment faults. Deployed across more than 20,000 sites and covering over 1 billion square feet, this system significantly reduces equipment downtime, reactive operations and maintenance costs.

Predictive analytics in forecasting lease expirations and renewal rates

What it is

ML can be used to forecast when tenants are likely to renew their leases and recommend optimal pricing and timing strategies.

Use case

Organisation: A real estate technology provider specialising in lease analytics

Application: The firm developed a ML algorithm that analyses historical lease expiration data, tenant payment behaviour and broader market conditions to predict the likelihood of lease renewal and optimise pricing dynamics.

The platform also has automated dashboards and actionable insights to help property managers prioritise upcoming lease expirations. It enables alignment of renewal pricing with the tenant’s profile and optimised timing of offers for maximum impact.

This approach has led to improved tenant retention through personalised and timely renewal offers, increased revenue by competitively pricing units, and more proactive tenant engagement. Additionally, it has enhanced operational efficiency through automated reporting and built-in collaboration tools for cross-functional teams.

Digital twins: The virtual blueprint of real estate

What it is

Digital twin technology creates virtual models of physical assets that sync in real time with operational data. For asset managers, this means real-time simulation of building performance, environmental control and predictive maintenance—all from a centralised platform.

By combining spatial data, building systems and predictive modelling, digital twins allow for:

• Scenario planning and simulation
• Energy optimisation
• Fault detection and diagnostics
• Enhanced lifecycle management

Strategic benefits: Remote facility management, scenario testing for renovation or expansion plans, enhanced leasing strategy through space visualisation

Use case

Organisation: A global real estate investment firm, in partnership with a digital twin technology provider

Application: The firm implemented digital twin technology across its North American and European offices and retail portfolios, covering over 100 million square feet. By adopting a real estate ontology-driven digital twin platform, the organisation saved approximately $1 million annually in operational and energy costs. These savings stemmed from real-time building automation and integration of IoT-based fault detection systems across its buildings.

ESG and sustainability analytics: Aligning with investor values

Environmental, social and governance (ESG) data is now a strategic asset. Leading firms integrate ESG metrics into daily reporting and financial modelling to evaluate a building’s carbon footprint, energy usage and tenant health factors.

ESG analytics has moved from ‘nice to have’ to a strategic necessity for CRE asset managers. As global capital increasingly flows into sustainable investments, firms that integrate ESG analytics are landing premium tenants, getting access to better financing options, and able to ensure long-term asset resilience.

By embedding ESG key performance indicators (KPIs) into day-to-day operations and financial modelling, asset managers can actively track:

• Carbon footprint
• Energy and water consumption
• Indoor environmental quality
• Diversity, equity and inclusion (DEI) practices
• Regulatory alignment with the European Union (EU) Taxonomy, the Sustainable Finance Disclosure Regulation (SFDR), the Securities and Exchange Commission (SEC) climate disclosure rules, etc.

Use case of ESG analytics

Organisation: A commercial real estate firm leveraging ESG software analytics

Application: With the application of an ESG data platform, a major property investment firm met its 2020 carbon reduction goals two years ahead of schedule. The firm is now targeting more ambitious goals for 2025, including substantial reductions in energy consumption and greenhouse gas emissions. It has already achieved a 6% reduction in water usage and a 20% increase in waste diversion compared with 2008 levels.

To resonate with today’s asset managers, data analytics platforms must go beyond visual dashboards. They must deliver:

• AI-enabled rent forecasting for proactive market positioning
• IoT-based operational insights to drive tenant satisfaction and cost savings
• Digital twins for virtual asset management and leasing support
• Real-time ESG dashboards to meet investor and regulatory requirements
• Robust cybersecurity frameworks to secure sensitive property data

By embracing these innovations, CRE firms can unlock the full potential of their data, transforming it from a passive repository into a strategic tool that drives value across the portfolio lifecycle.