Enhancing Real Estate Asset Management through Predictive and Prescriptive Analytics

The proposed innovation project addresses a critical research problem in the real estate industry, aiming to fundamentally reshape traditional asset management practices through advanced data science techniques. The research problem revolves around the industry’s historical reliance on conventional decision-making, hindered by data interpretation barriers. This project’s significance lies in its potential to unlock the power of data-driven solutions, particularly in optimizing resource allocation, such as marketing budgets, to drive cost savings and enhance efficiency. The primary objectives of this project are to create a decision-making framework that utilizes predictive and prescriptive analytics and to uncover trends within historical and seasonal real estate data. By doing so, it aims to challenge existing practices and offer innovative, data-driven solutions. The project’s methodology involves leveraging deterministic modeling, large language models (LLMs), deep learning, and neural networks, alongside advanced analytics tools like Looker and machine learning technologies, to analyze complex real estate datasets. In essence, this project represents a significant advancement in the real estate industry, offering a transformative approach to asset management. It promises to empower stakeholders with actionable insights, breaking down long-standing data interpretation barriers and providing a roadmap for efficient resource allocation.

Faculty Supervisor:

Rasha Kashef

Student:

Partner:

RealSage

Discipline:

Computer science

Sector:

Real estate and rental and leasing

University:

Toronto Metropolitan University

Program: