Generative Models for Financial Time-Series Predictions

The intern will work on applying new advances from the field of Machine Learning to models which make predictions about time-series data. The models have the desirable property modeling the distribution of outcomes in a way that we can sample from, allowing us to account for uncertainty in the model’s predictions. By making more accurate predictions with more accurate gauges of uncertainty, Electronica will be able to construct portfolios which give more desirable risk-adjusted returns to investors.

Prediction Improvement on User’s Consumption

The goal of the research is to implement different data mining algorithms in order to improve the prediction on a user’s electricity consumption. The research will be dedicated to improve the existing algorithms or implementing new algorithms for the improvement of the prediction accuracy. Besides application of the prediction algorithms, different data pre-processing methods will be used. Research will include supervised and unsupervised modelling of the dataset by using the R programming language.

End-User Understanding of Web Certificates - Year two

Users must decide which websites to trust and which to avoid. How can users know if a website is truly what it claims to be? This is a pivotal issue. When attackers can convince users to trust their sites, though phishing or other strategies, user security and privacy are easily compromised, malware can be downloaded, and infrastructure undermined.
Our plan is to conduct user studies to explore the understanding of browser-presented certificate information.

NLP Techniques for Automated Entity Recognition

The primary goal of this project is to explore a variety of new and existing Natural Language Processing (NLP) techniques to improve the performance, and further the automation of, Knote’s text analysis software – specifically with entity recognition. Entity recognition is the process of identifying all groupings of words in a collection of documents that fall within that entity’s purview, such as proper names or chemical compounds.

Image Style Classification and Its Application on User Engagement

In this project, we will apply machine learning to perform image style classification. We will build a system that uses image style classification to increase user engagement in an eCommerce platform setting. We will study the effects of user preferences for particular image styles on their engagement with the platform.
Image style classification is the task of categorizing an image based on attributes such as composition style (e.g., minimal, geometric, etc.), atmosphere (hazy, sunny), or colour (pastel, bright).

Construction of a Genetic Variant Store

This project proposes to explore and implement a method of storing and retrieving data relating to genetic variation across a population of individuals. Due to the large amount of genetic information each person possesses, such a database requires special attention to minimize the amount of data stored and to create efficient methods of accessing the data. This work will research and test different strategies to build a compact data store that will return results quickly. This data store will be incorporated into the PhenoTips software provided by Gene42 Inc.

Interactive preference elicitation application for book recommendations

Kobo is an online e-book retailer that provides recommendations for future purchases to its user base. One difficulty that recommendation systems face is what is known as the “cold-user” problem. In this scenario, when we know so little of a user’s preferences (for example, if they are new to the platform), we do not have any basis for recommendations. The goal of this project is to develop an interactive application that can elicit such preferences from users about whom we have little information, and that can help improve recommendations for power users.

Machine Learning methods for Nova Scotia property value prediction

This project will develop and apply machine learning techniques to predict the valuation of the properties in Nova Scotia. The techniques will help Property Valuation Services Corporation (PVSC) assessors with more efficiently and accurately valuing properties. The ultimate goal is to help PVSC reduce the number of annual appeals – which is a costly undertaking. It will also reduce the need to send assessors directly to the property locations, instead they will use machine learning techniques to more accurately predict property values.

Learning representations through stochastic gradient descent by minimizing the cross-validation error

Representations are fundamental to Artificial Intelligence. Typically, the performance of a learning system depends on its data representation. These data representations are usually hand-engineered based on some prior domain knowledge regarding the task. More recently, the trend is to learn these representations through deep neural networks as these can produce significant performance improvements over hand-engineered data representations. Learning representations reduces the human labour involved in any system design, and this allows in scaling of a learning system for difficult problems.

Learning tools to predict treatment responses for schizophrenia from neuroimaging data

Schizophrenia is a chronic mental disorder associated with a significant health, social and financial burden, not only for patients but also for their families, and society. However, the current treatment methods have been only partially successful, mainly due to the inter-individual differences between patients, which means that a treatment that is successful for one patient, might not work for another.

Pages