Machine Learning Modeling for Autism Spectrum Disorder Handling and Treatment

The project is about developing a decision support tool to provide a personalized handling and treatment for Autistic Syndrome Disorder patients. This decision support tool will integrate machine learning modeling that will be used to suggest optimal and personalized guidelines for a very large spectrum of ASD patients, not available so far. Theses guidelines will be used by concerned parents, teachers and therapist that are in charge of these patients. The partner is a company that offer accompanying and training services to ASD patients’ parents and therapists.

Developing an Intelligent Conversational Agent Architecture related to the Banking Domain

This research project aims at creating a robust, efficient and reliable conversational agent for the banking domain that will offer a high level of performance in both key areas of conversational agent architecture: Natural Language Understanding and Response Generation. Natural language understanding approaches, retrieval-based models, as well as deep learning will be used to develop the architecture of the conversational agent in this specialized domain.

Québec__Université du Québec à Montréal

No additional funding contribution is required from the academic supervisor or university.
Fellowships will be awarded competitively.

Uplift models extension for smart marketing

Insurance companies heavily fund marketing campaigns such as, for instance, customer retention or cross-sell initiatives. Uplift modeling aims at predicting the causal effect of an action such as medical treatment or a marketing campaign on a particular individual by taking into consideration the response to an action. Typically, the result of an uplift model is used to call customers for marketing some products based on important attributes of a customer.

Quantifying the value added by the first large ensemble of high-resolution climate-change simulations over Québec

Regional Climate Models (RCMs) allow generating climate-change projections into the future over a limited region of the globe at high spatial resolution. The production of large ensembles of simulations from a same RCM is an emerging field of research allowing to explore in detail the interaction between climate change, natural climate variability and extreme events, at the local scale where climate impacts occur.

Combining Internet of Things (IoT) technologies to understand product and consumer behavior in retail environments

The project is about developing a «smart store» system that will allow understanding customer and product behavior. This system will be based on Internet of Things (IoT) technologies allowing any object (product or person) to communicate automatically with its environment. Hence, our system will be used for tracking items and monitor consumer behavior in real time. In a retail environment, we will be able to answer questions such as (i) How many times an item has been picked up or tried by a customer? (ii) How long the item stayed off the shelve?

Linguistic Data Science for the Development of a Business Corpus

This project is dedicated to the development of a new business corpus as a novel data for the company’s business intelligence. It focuses on linguistic pre-processing for the business domain using two types of collected corpora: text and speech. An automatic annotation of the pre-processed business corpus will be completed using labels related to sentiment analysis and emotion mining technologies. Specific rules will be used to strengthen these labels. Last, a cognitive social analysis on human behaviors and team dynamics will be completed within a business meeting.

Understanding atmospheric peril risk across re/insurance portfolios

Natural disasters that are associated to the atmosphere (known as atmospheric perils) such as hurricanes, tornadoes and hail, flooding, drought, and wildfire, caused over $100 billion in damage throughout the world in 2015. Insurance companies often cannot afford to be responsible when such catastrophes occur, and so they purchase insurance to protect themselves (called reinsurance) from these large risks.

Information extraction from real-world business documents

This research project aims at creating a robust, efficient and reliable tool for Information Extraction (IE) from vast amounts of textual data related to the financial domain. Named entities recognition, a subtask of information extraction, seeks to locate and classify elements in text into pre-defined categories such as the names of persons, organizations, locations, expressions of times, quantities, monetary values, percentages, etc.

Development of novel biochemical and biophysical assays for the identification of inhibitors of Hypoxia Inducible Factor-2

Cancer cells are known for their unique capacity to survive and grow in a low oxygen tension environment in the middle of a poorly vascularized solid tumor. This adaptation, which is central to the tumorigenesis process, is mediated by precise cellular mechanisms allowing the regulation of gene expression. Thus, the development of small molecules to modulate the activity of transcription factors is of great therapeutic interest. In order to develop such molecules, we plan to finance, with the help of IntelliSyn Pharma and Mitacs, one M.Sc. student.

Pages