Topic: Multitask Learning For Crime Prediction in Edmonton
Partner: Professor Russell Greiner, Department of Computing Science, University of Alberta
Date: Fall 2016
During the Fall 2016 semester at the University of Alberta, Koosha Golmohammadi, the City’s Data Scientist, co-advised a team of U of A students in the course Introduction to Machine Learning. Students worked with datasets from the City’s Open Data Catalogue as well as other sources of data to find solutions to predict crime data.
- Multitask Learning For Crime Prediction in Edmonton
Students: Ji Yang, Kalvin Eng, Hang Zhu, Yang Zhang and Baihong Qi.
In this project, we explore three different machine learning algorithms and measure their performance on predicting the number of crimes using root mean squared error. The datasets are from the City of Edmonton’s Crime and Census data from 2012 to 2016. We apply multitask least square support vector regression, the Curds and Whey algorithm and multitask random forest to our dataset. Our approach outperforms conventional single task learning models by 5 to 8 percent.