Intelligent tenant screening: automated risk assessment with explainable AI (XAI) - ON-1174

Project type: Innovation
Desired discipline(s): Computer science, Mathematical Sciences, Operations research
Company: CMAI
Project Length: 4 to 6 months
Preferred start date: 03/02/2026
Language requirement: English
Location(s): Toronto, ON, Canada
No. of positions: 1
Desired education level: Master'sPhDPostdoctoral fellow
Open to applicants registered at an institution outside of Canada: No

About the company: 

CMAI is an advanced Artificual Intelligence (AI) technology company focused on transforming property management operations through artificial intelligence driven operation management and workflow automation. The firm not only unifies the entire end-to-end property managment workflows, but also leverages properties’ data, maintaince records and regulations to build a predictive serivce model to significantly drive property management efficiency, energy and reserouce saving, environment and social sustainbility, driving asset value growth.

Describe the project.: 

The traditional tenant screening process is currently plagued by two opposing challenges: operational inefficiency and inherent human bias. Property managers spend excessive hours manually verifying income, credit, and references, a process prone to error and fraud.
The main goal of this research project is to develop an Intelligent Tenant Screening & Risk Assessment System. Unlike standard background check tools, this system utilizes Natural Language Processing (NLP) and Machine Learning (ML) to automate the verification of heterogeneous applicant data (employment letters, bank statements, credit reports) while simultaneously detecting document fraud.
Crucially, the project aims to solve the "black box" problem in AI decision-making. We will integrate Explainable AI (XAI) frameworks to ensure transparency. The system will not simply output a "pass/fail" recommendation; it will provide auditable, logic-based reasons for every assessment. This allows for rigorous algorithmic auditing, ensuring the model complies with regulations. Furthermore, the research will explore alternative risk metrics to support vulnerable groups (e.g., newcomers to Canada with "thin" credit files, fresh graducated student with limited income statement), thereby expanding the pool of eligible tenants while reducing landlord risk.
Ultimately, this project aims to deliver a compliance-first engine that reduces tenancy disputes by 30% and establishes a new industry standard for ethical, automated leasing.

Required expertise/skills: 

• NLP Specialization: Experience with Natural Language Processing techniques (NER, Text Classification) to process unstructured documents like employment letters or landlord references. Knowledge of transformers (BERT, GPT models) is an asset.
• Explainable AI (XAI): Familiarity with libraries like SHAP (SHapley Additive exPlanations) or LIME. The student know how to make a model "explain" its decision is a plus
• Fraud Detection: Experience with anomaly detection algorithms to identify forged documents or inconsistent data points.
• API Integration: Ability to connect with third-party APIs (Credit bureaus like Equifax/TransUnion, open banking APIs).