You are now in the main content area

Major Research Project Library

The student is required to conduct an applied advanced research project. The project will be carried out under the guidance of a supervisor. On completion of the project, the results are submitted in a technical report format to an examining committee and the student will make an oral presentation of the report to the committee for assessment and grading of the report. The student is expected to provide evidence of competence in the carrying out of a technical project and present a sound understanding of the material associated with the research project.

The major research paper is presented to the university in partial fulfillment of the requirements for the degree of Master of Science in the program of Data Science and Analytics.  

The MRPs listed below are from the most recent graduates from 2023.

The catalogue of all MRP abstracts from 2017 to 2023.  

  • Al-Falahy, Raed – Predicting Patient Readmissions in Hospitals: A Machine Learning Approach 
  • Anand, Gurjyot Singh – Credir Card Fraud Detection Using Machine Learning 
  • Awan, Hina – Comparing Several Machine Learning and Deep Learning Models to Detect Health Care Providers’ Fraud in Insurance Claims 
  • Chanana, Gazal – Automobile Insurance Fraud Analysis and Detection Automobile Insurance Fraud Analysis and Detection 
  • Choudhry, Soheer – Predicting US Wireless Carrier Operator Performance Using Social Media Data and Google Trends 
  • Cobbinah, Maame – A Deep Learning Approach to Forecast the Canadian Consumer Price Index (CPI) Using Encoder-Decoder Attention Mechanisms with Teacher Forcing Techniques
  • Da Silva, Brian Jones – Enhancing Time Series Forecasting Accuracy With Ensemble Methods for Multiple Seasonality in Sales and Retail
  • Ekundayo, Matthias – Predicting House Prices Using Advanced Regression Techniques 
  • Elahi, Muzammil – Household Temporal Space Heating Demand Prediction Using Machine Learning Modelling 
  • Farrukh, Fatima Faiza – Improving Access to Hospital Beds Through Time Series Forecasting and Mathematical Optimization 
  • Go, Carlos – Synthrad2023 – Synthesizing Computed Tomography for Radiotherapy 
  • Gong, Li – Combining Graph Convolutional Networks and Generative Adversarial Networks for Robust Recommendation Systems 
  • Gupta, Snigdha – StreetSmart – A Legal Traffic-Bot Using Generative Language Models 
  • Hossain, Nusrat – Analysis of the Effectiveness of MRI Image Data Vs. Tabular Data When Training Classifiers for Dementia Diagnosis
  • Kaski, Alicia – Transfer Learning Computer Vision Techniques for Early Dementia Diagnosis Using Brain MRI 
  • Li, Ang – Adaptive Learning Management Systems Through Deep Learning 
  • Li, Shijie – Comparing Supervised Learning and Reinforcement Learning Algorithms for Real-Time Inventory Management
  • Marcogliese, James – Culinary Puzzle Pieces: Higher-Order Ingredient Pairings in World Cuisines 
  • Naupada, Lakshmi – Wealthbot: Development of Chatbot for Investment Management 
  • Nguyen, Gia Viet Huy – Machine Learning Approach on Ethereum Transaction Classification 
  • Noor, Faiza Sabiha – Time Series Forecasting Methods of Toronto’s Housing Market 
  • Raj, Ritik – Predicting Impact of Marketing Channels and Digital Marketing KPIs with Machine Learning 
  • Rutkowska, Agnieszka – Deep Reinforcement Learning for Disaster Recovery Orchestration in Data Centers 
  • Sanford, Griffin – Analysis of Explainable AI Techniques on House Market Prices 
  • Singh, Bhupinder – Predicting Drought Susceptibility in the US Using Meteorological Data
  • Singh, Rashmi – An Ensemble Approach to Loan Default Prediction
  • Patel, Smit – Improving Customer Churn Prediction Through Segmentation 
  • So, Brandon – Attentional Bidirectional LSTM for Instrumental Music Synthesis 
  • Sun, Zeyuan - Enhancing Medical Transcription Information Extraction using Transformer Models and Doccano Annotation 
  • Wu, Yu Heng – Sentiment Analysis of Online Reviews From YELP Open Dataset 
  • Zmytrakov, Yurii – Exploring Deep Learning and Machine Learning Techniques to Prevent Payment Frauds with the Help of Ensemble Learning