From $250M to $2B: Driving Transformation with AI-Powered Revenue Optimization for a global real estate company

How our full-house engineering agency partnered with a leading global real estate company to unlock exponential growth by combining data science, machine learning, and commercial strategy.

Key Highlights

Main achievements and outcomes

Location Recommendation Engine

Built a location recommendation engine guiding global expansion into high-yield cities and micro-markets.

Workspace Design Optimization

Optimized workspace design through predictive analytics to maximize utilization and member satisfaction.

Enterprise Pivot

Pivoted pricing model from SMB/consumer focus to enterprise clients, which grew to 40% of total revenue.

Dynamic Pricing & Discounting

Rolled out dynamic pricing & discounting engine using behavioral signals, contract duration, and demand patterns.

Account Growth Scoring

Designed an account growth scoring model to segment customers, predict demand, and calculate lifetime value.

Project Overview & Results

Comprehensive project details, challenges, solutions, and outcomes

Domain

Real Estate, Shared Workspaces, B2B SaaS Pricing & Revenue Optimization

Tech Stack/Tools

Backend: Java, Spring Boot, Spring Security
Auth & Identity: Keycloak, MyID, biometric face verification APIs
Data: PostgreSQL, AWS Redshift, Redis, MongoDB
Messaging/Eventing: SQS, RabbitMQ
DevOps: AWS EC2, Kubernetes, Docker,
Frontend: ReactJS
Other: SageMaker, Airflow

Problem Statement

Company was scaling quickly but faced structural challenges:
Expansion Risk: Location selection was often opportunistic, with inconsistent ROI.
Revenue Model Strain: Heavy reliance on freelancers and small businesses created churn and limited stability.
Static Pricing: Flat desk pricing ignored demand signals and contract length.
Customer Blind Spots: No systematic framework to identify expansion-ready accounts or project lifetime value.

Solution

Expansion & Space Optimization: Location Recommendation Engine: ML models on geospatial, demographic, and competitive datasets. Space Optimization: IoT sensor + booking data → predictive models for desk mix (hot desk vs. private office) → design changes tied to demand lift.
Pricing Transformation: Enterprise Pivot: Data dashboards showed enterprise clients had higher lifetime value and lower churn → partnered with GTM team to reframe offering. Dynamic Pricing Engine: Deployed ML models adjusting desk pricing by demand, contract duration, and behavior patterns.
Customer Intelligence & Retention: Account Growth Scoring Model: Tracked funding rounds, hiring signals, and utilization to predict expansion likelihood. CLV Framework: Guided retention strategy and upsell campaigns.

Outcomes

8x Revenue Growth: From $250M to $2B in two years, with ML-driven revenue optimization central to scaling.
Expansion ROI: +30% improvement on new site performance.
Enterprise Success: Enterprise clients contributed 40% of total revenue by 2019.
Yield Optimization: Dynamic pricing added 18% lift in revenue per desk.
Customer Intelligence: CLV analytics drove 25% higher upsell conversions.