Module: Practical AI for Real Estate

This session offers the essential knowledge of what AI is and how it operates, tailored for real estate professionals eager to incorporate AI into their business practices. It is designed to be accessible to everyone, irrespective of technical background, providing a necessary foundation for all subsequent sessions and future independent work with AI. More specifically, the session covers:

Strategies for minimizing AI output errors, effective prompting techniques, and an overview of the top AI products.

An accessible overview of artificial intelligence, with a particular focus on conversational AI and advanced language models like GPT-4.

The distinction between AI and traditional software, highlighting AI’s ability to derive rules from objectives, in contrast to the predefined rules in conventional software.

The inner workings of neural networks, the AI learning process, and text understanding through techniques such as tokenization, embedding, and self-attention.

Session 2 – Market Research with Generative AI

documents and reports such as:

• prompt engineering
• AI-powered searching
• critical thinking with AI
• insights and recommendations with AI
• limitations of AI in working with text

It delves into AI’s capability in enhancing document analysis, underscoring the significance of context in communication and the development of effective AI prompting strategies.

The session highlights the crucial role of AI in synthesizing vast amounts of market data, drawing objective, context-aware conclusions. It stresses the importance for real estate professionals to not only understand but also effectively utilize these advanced tools for gaining competitive insights.

Session 3 – Analysis, Strategy and Forecasting

The session introduces using generative AI in business analysis, in the real estate sector.

It starts by covering the integration of qualitative information in analysis, outlining the benefits and challenges of using qualitative data and how generative AI can enhance precision and speed in this context.

Then, it delves into the creation of strategies with AI assistance, highlighting steps like setting context, defining problems, specifying tasks, and prompt generation for effective strategy formulation.

It considers two key case studies: using AI as a tool to execute strategy generation and using AI as a consultant to develop a complete strategy for a specific problem.

Next, the session explores the application of AI in mathematical operations, contrasting the capabilities of Excel and large language models (LLMs) in handling mathematical tasks.

Finally, it progresses to practical aspects of strategic real estate analysis, like simple valuation, sensitivity analysis, and Monte Carlo Analysis, demonstrating how these can be approached using gen AI. It concludes with a case study on forecasting and building custom models using AI.

Session 4 – Data Visualisation

This session presents AI capabilities to write and execute code from natural language prompts using the example of creating data visualizations relevant to real estate professionals. In particular, it covers:

• Basic data processing and analysis tasks using real data and how to turn it into an advanced analysis by entering the right prompts.
• Creation, customization, and analysis of diverse chart types, including bar charts, pie charts, and time series plots, all made accessible through natural language commands.
• How to effortlessly generate maps with your own data, regardless of technical skills or background.
• Animated visualizations of graphs and maps, adding an engaging dimension to data presentation.
• Development of interactive visualizations such as dynamic dashboards or even interactive maps.

Key takeaways include the ability to handle diverse data types, the use of AI to interpret code and generate visuals, and techniques for creating compelling, interactive data presentations.

Session 5 – Navigating AI in Real Estate

The session consists of three diverse presentations that delve into advanced aspects of AI and its practical applications in real estate.

First, Monika offers a deeper insight into the philosophical and technical intricacies of AI, discussing future trends, ethical considerations, and the impact of AI on the workforce.

Second, Thomas provides a more hands-on approach, detailing how AI can be pragmatically implemented in business operations, with a focus on efficiency and innovation.

Third, Niko concentrates on the practical aspects of integrating AI into businesses, particularly emphasizing the skills required for successful adoption and the transformation of job roles in an AI-driven corporate landscape.

Together, these lectures provide a comprehensive understanding of AI’s potential, challenges, and the evolving dynamics of its integration into various industries.

Automating Excel Models with VBA

Use Case: Automated Sensitivity Analysis for Property Investment

• Introduction to VBA for financial modelling
• When to use VBA vs. Python vs. Java
• Basics of macros and custom VBA scripts
• Using ChatGPT to generate and improve VBA code
• Building a simple Excel automation tool:
• Automate a sensitivity analysis for IRR and NPV based on different rent levels
• Create a macro button to execute different investment scenarios
• Hands-on exercise:
• Modify and test VBA code with AI assistance

AI-Powered Data Analysis with Python

Use Case: Automating Data Extraction & Analysis

• Why use Python in real estate financial modelling?
• Overcoming Excel limitations
• Using ChatGPT for Python scripting
• Building a Python tool:
• Extract and clean data from an Excel real estate model
• Perform automated analytics (average rent, NOI trends, IRR calculations)
• Output results back into Excel
• Hands-on exercise:
• Adapt the Python script to their own model

Creating a Web-Based IRR Calculator with Java

Use Case: Interactive Investment Analysis

• Introduction to Java for financial applications
• When to use Java over VBA/Python
• Using ChatGPT to generate and optimise Java code
• Building a Java-based IRR calculator:
• User inputs: Purchase price, rent, expenses
• Output: Monthly cash flow, IRR, ROI, cap rate
• Simple interactive interface
• Hands-on exercise:
• Modify the Java tool to include additional financial metrics

AI-Powered Financial Model Automation

• Objective: You will use your acquired knowledge during the day to automate a part of a real estate model using AI-generated code (VBA, Python, or Java)
• Project ideas:
• Automate a financial metric calculator (IRR, NPV, DSCR)
• Create a customised scenario generator for different rent levels
• Build an AI-driven data extraction tool to clean and format property datasets
• Develop a simple chatbot for real estate financial queries
• Hands-on:
• Participants design, build, and test their projects
• AI-assisted troubleshooting and debugging

Project Presentations & Course Wrap-Up

Q&A and next steps

Participants showcase their projects

Explain their AI-assisted automation and improvements

Feedback & discussion

Key takeaways & future AI opportunities