Nitya Kaki
From wanting to use AI for social good to IEEE conference acceptance for ML research predicting housing insecurity
Where Nitya Started
Her Background
- • High school student passionate about social justice
- • Interested in using technology to solve real-world problems
- • Wanted to make a tangible impact on vulnerable communities
- • Learning machine learning and data science
Her Goals
- • Apply AI to address social challenges
- • Publish meaningful research with real-world impact
- • Build expertise in machine learning
- • Create tools that help communities
Her Vision
"I wanted to use AI to help solve social problems. Housing insecurity affects millions of families, and I believed machine learning could help identify at-risk individuals before they lose their homes."
— Nitya, before joining YRI
The Research
Working with her YRI mentor, Nitya developed a machine learning model to predict housing insecurity using proxy indicators from socioeconomic data. Her research provides a tool for early intervention that could help prevent homelessness.
Early Prediction of Housing Insecurity Using Machine Learning and Proxy Indicators
Housing insecurity often goes undetected until it's too late for intervention
Random Forest classification on socioeconomic proxy indicators
82.5% accuracy in predicting housing insecurity risk
Tool for social services to identify and help at-risk families
Proxy Indicator Analysis
Nitya identified key socioeconomic indicators that serve as early warning signs of housing insecurity. Her Random Forest model analyzes multiple factors to flag individuals at risk before they become homeless.
Enabling early intervention for at-risk families
The Outcome
Conference Paper Accepted
AI for Social Good
IEEE International Conference on Psychology and Social Policies 2025
My Random Forest model predicts housing insecurity with 82.5% accuracy. YRI mentorship helped me get accepted to IEEE ICPSP 2025.
Wanted to use AI for social good but didn't know where to start
IEEE conference accepted with an 82.5% accurate housing insecurity prediction model
Why This Research Matters
Prediction accuracy for identifying housing insecurity risk
Detection enables intervention before homelessness occurs
Tool for social services to help vulnerable families
Ready to Start Your Research Journey?
Join the YRI Fellowship and work with expert mentors to conduct original research, publish in top journals, and build a profile that stands out.
Apply Now