Climate change is one of the greatest challenge society has ever faced, with increasingly severe consequences for humanity. Climate change also creates risks to both the safety and soundness of the individual firms and to the stability of the financial system.
This project’s objective is to create a proprietary digital platform which will allow for a faster, more accurate diagnosis of a building’s indoor environmental quality (IEQ) – at a fraction of the cost of today’s industry testing rates. The project aims to ensure that data being collected can be properly categorized and analyzed, creating a fully automated diagnostic tool. This novel analysis method requires being able to identify deficiencies in a commercial building that can be remedied, as well as proposing an actionable resolution plan for each identified deficiency.
As location is an integral part of both population and individual health, there is an emerging role for geospatial artificial intelligence (GeoAI) technology in health and healthcare. Novel infectious diseases such as COVID-19 are associated with population density, environmental factors, and interactions between humans and wildlife. GeoAI technology can be used to collect and analyze large amounts of spatial data, such as individual-level epidemiological data, social media, human mobility, transportation, mobile phone data, and vulnerable populations.
Freight service is an integral part of any business that supplies or sells physical goods. Even though its importance is often hidden from consumers, the sight of trucks and cargo vans on city streets and highways can make one appreciate the extent to which freight service impacts our lives. In North America, many carriers (i.e. companies that own trucks, vans, etc.) care medium or small sized, consisting of a handful to no more than a hundred trucks in their fleet.
The project objective is to develop a method for measuring public opinion using social media data. Presently the ability to derive externally valid inferences from social media data is impeded by issues such as sample bias and data structure. By applying recent innovations in machine learning to account for such issues, this project aims to develop a robust, reliable and inexpensive means by which to continuously gauge public opinion with respect to a given topic.
This project benefits the partner organization by helping advance its mission of promoting democratic participation.
Leveraging the entirety of point of sale and loyalty data collected across a category, as well as additional socio-economic and other supporting data sources, apply statistical modelling to identify the own-price elasticity of demand and cross-price elasticity of demand at regular and promoted price points across Unilever’s portfolio within that category. Subsequently measuring the promotional cannibalization of Unilever’s temporary price reduction activities across the market to assess the promotional events with the highest return on investment and revenue optimization potential.
Poor mental health and stress are an expected outcome of the COVID-19 pandemic. Social distancing is taking another toll on the mental health of individuals. With most of the medical consultations being held online there is an urgent need to enable continuous monitoring of mental health by identifying risk factors for high stress and poor mental health and to provide individuals with information to improve their health and well-being. Wearable and mobile devices are an efficient and effective mean to achieve this goal in a very cost-effective manner.
Chronic obstructive pulmonary disease (COPD) is a 3rd leading cause of death (1) which decreases lung function due to irreversible airway obstruction. The main indicator of the progression of COPD is a rate of the forced expiratory volume of 1 second (FEV1) decline. The intern will build the prediction model for the slope of FEV1 decline and find the genetic variants that affect these FEV1 changes. Some variable selection machine learning algorithms will be applied to screen important genetic variants and the performance of prediction on FEV1 change will be compared.
The objective of the proposed research program is to develop a flexible and unified multivariate framework for modeling the returns of financial assets. The program is innovative since it establishes closed-form formulas for an efficient and reliable calculation of risk measures and derivative prices. For financial institutions and government regulators, who are performing pricing and risk management calculations very frequently with thousands of assets, closed form solutions are of immense importance.
The intern will research new modelling technology to determine if the new models can make a significant improvement in servicing customers for loan approvals, debt collections, and open banking. The intern will work closely with the partner to understand the banking process and opportunity. The partner organization will receive several benefits from working with the innovative and knowledgeable intern including cross-training of techniques through collaboration, enhanced model accuracy, and enabling the partner to test new techniques.