Paula Branco

Paula Branco

Assistant Professor

EECS - University of Ottawa

About me

I’m an Assistant Professor at the School of Electrical Engineering and Computer Science in the University of Ottawa, Canada.

My main research interests are focused on Artificial Intelligence and Machine Learning with a special focus on imbalanced domains, outlier detection, anomaly detection, cost-sensitive and utility-based learning, fraud detection and cybersecurity.

Interests

  • Artificial Intelligence
  • Machine Learning
  • Imbalanced Domains
  • Outlier Detection
  • Anomaly Detection
  • Cybersecurity

Education

  • PhD in Computer Science, 2018

    MAPi - Joint Doctoral Programme

  • MSc Computer Science - Specialization in Data Mining and Advanced Data Processing, 2014

    FCUP - University of Porto

  • Specialization in the MSc Mathematics for School Teachers, 2013

    FCUP - University of Porto

  • Degree in Mathematics - Educational Branch, 2002

    FCUP - University of Porto

Experience

 
 
 
 
 

Assistant Professor

EECS, University of Ottawa

Jan 2020 – Present Ottawa, Canada
Courses:

  • Winter 2020: Databases 1
  • Fall 2020: (New) Artificial Intelligence for Cybersecurity Applications
 
 
 
 
 

PostDoctoral Fellow

Dalhousie University

Jan 2019 – Dec 2019 Halifax, Canada
Methods for Handling Problems with Domain-specific Utility Preference Biases

News

New paper accepted @ BIBM 2020

IEEE International Conference on Bioinformatics and Biomedicine 2020 (IEEE BIBM 2020)

New paper accepted @ PSBD co-located with IEEE BigData 2020

7th International Workshop on Privacy and Security of Big Data (PSBD 2020) @ IEEE Big Data 2020

LIDTA'20 - Tutorial accepted @ ECML/PKDD 2020

Learning with Imbalanced Domains and Rare Event Detection

New Assistant Professor Position

Started an Assistant Professor Position at School of Electrical Engineering and Computer Science at University of Ottawa, Canada.

New Paper on Discovery Science Conference

New paper published on Discovery Science: “The CURE for Class Imbalance”

Research

My main research interests are Machine Learning, Data Mining and Data Science. I’m interested in predictive analytics with a special focus in cost-sensitive/utility-based predicitive analytics, imbalanced domains learning, anomaly detection, fraud detection and rare extreme values forecasting.

Utility-based Predictive Analytics

    * Utility-based learning problems
    * Cost-sensitive learning problems
    * Performance Evaluation

Imbalanced domains

    * Strategies for dealing with imbalanced domains
    * Imbalanced Regression
    * Imbalanced Time Series
    * Imbalanced Data Streams
    * Performance Evaluation on imbalanced domains

Rare Events Mining

    * Outlier detection
    * Anomaly detection
    * Fraud detection
    * Rare extreme values forecasting

Real-world Applications

The problems that I’ve been addressing in the last years have many important real-world applications. Examples of such applications are:

Cybersecurity

	* Malware detection
	* Intrusion Detection
	* Network Traffic Anomaly Detection
	* Misuse/Signature Detection

Health Care Problems

	* Rare disease detection
	* Cancer Prediction
	* Diabetes Prediction
	* Forecasting/anticipating heart diseases

Spatio-temporal data

	* Fores fires forecasting
	* Monitor distribution and health of aquatic species
	* Recommend locations for exploration of mineral resources

Failure and fraud detection

	* Failure detection in sensors data
	* Anticipating equipments interventions
	* Fraud detection applications such as:
		* credit card transactions
		* insurance claims
		* email phishing

Ecological/Meteorological data

	* prediction of abnormal values in ecological indicators
	* anticipation of critical phenomena related with air or water quality
	* forecasting weather extreme events such as:
		* floods
		* heavy snowfall
		* black ice
		* heat waves

Recent & Upcoming Talks

Rare Events Detection: Methods and Evaluation

“Rare events detection: Methods and Evaluation” September 2020 LIDTA’2020: Tutorial on Learning with Imbalanced Domains and Rare Event Detection at ECML/PKDD 2020 here Tutorial page: LIDTA

Teaching

Current courses:

Code Course University Role link Year Term
CSI 5188 AI for cybersecurity Applications EECS - University of Ottawa Instructor [CSI5188] 2020 Fall
CSI 2132A Databases 1 (section A) EECS - University of Ottawa Instructor CSI2132A 2020 Winter

Past courses

Code Course University Role link Year Term
CSI 2132A Foundations of Data Science using R Faculty of Computer Science - Dalhousie University TA 2019 Fall

Recent Publications

Quickly discover relevant content by filtering publications.
(2019). The CURE for Class Imbalance. Bellinger, Colin, Branco, Paula, Torgo, Luis.

PDF

(2019). Pre-processing approaches for imbalanced distributions in regression. Branco, Paula, Torgo, Luis, Ribeiro, Rita P.

PDF

(2018). Rebagg: Resampled bagging for imbalanced regression. Branco, Paula Oliveira, Torgo, Luís, Ribeiro, Rita Paula.

PDF

(2018). MetaUtil: Meta learning for utility maximization in regression. Branco, Paula Oliveira, Torgo, Luís, Ribeiro, Rita Paula.

PDF

UBL R package

UBL R Package - Utility-Based Learning in R

UBL is an R package developed for Utility-based Learning.

Contact