Hypersensitivity to sensory stimuli causes overstimulation, inducing overwhelming emotional distress in individuals with an autism spectrum disorder (ASD). Reveal is a wearable device designed by Awake Labs that monitors anxiety levels in ASD children and interfaces with parents and caregivers. It predicts behavioural “meltdowns” by tracking and classifying key physiological markers of anxiety using machine learning technology. However, the features between which this model is trained to differentiate were developed ad hoc, and built from data that was collected from adults without ASD.

Planetary boundaries can be understood as limits for the Earth’s tolerance towards environmental impacts in the form of, for example, greenhouse gas emissions, water use and the release of nitrogen and phosphorous. This project aims at making planetary boundaries useful to the environmental management within companies. This will happen by developing a method that quantifies environmental impacts of a company in the language of planetary boundaries.

The continuum of HIV care is highly complex. It includes prevention, testing, patient care, treatment, and support services. This project will help Providence Health Care utilise its limited resources to provide the best treatment and care for people living with HIV in Vancouver. Care for HIV patients includes antiretroviral therapy, treatment of co-morbidities, monitoring clinical markers of disease progression (CD4 count and viral load), and support services to ensure treatment adherence and retention in care.

User intention prediction of event data, collected during the business process, has become an important topic in Web Analysis and Business Intelligence. Commercial organizations have realized its importance for providing cost-effective opportunities to improve their decision-making in digital marketing strategies. We aim to develop and implement a statistical prediction model to make the prediction of user intention, using the retroactive video tracking data, while the anonymous customer navigates on the website.

Solar cells which convert solar energy directly into electricity are among one of the most viable solutions to the world’s foreseeable energy crisis and global environmental issues. One key strategy to improve the efficiency of solar cells is to enhance the overlap between their absorption spectra and the solar spectrum. When two or more subcells with distinct and complementary absorption spectra are stacked, the tandem solar cells are created and a broader range of the solar spectrum can be absorbed and more solar energy can be harvested.

Monte Carlo simulation methods are commonly used as a risk management tool to estimate the risk exposure of financial asset portfolios. However, the traditional brute-force Monte Carlo (BFMC) method is often very timeconsuming, which makes it difficult to serve the risk management needs of modern insurance industry. An alternative approach, the least-squares Monte Carlo (LSMC) method, could substantially reduce the computation cost by fitting a proxy function of liabilities using simple nonlinear regression methods.

In recent years, improvements in technology provide the opportunity for investors to use computer algorithms to produce low-cost guidance on possible portfolio investment mixes and strategies. This project is directed at the research and development of one such “Robo- Advisor” algorithm based on forward-looking scenario optimization, in order to determine the efficacy of the strategy. Here optimal portfolios are selected based on investor’s views on future scenarios, goals and risk tolerance.

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.

The goal of this project is to create a statistical model to forecast the future price of steel, which will rely on sector indexes and material prices. We will identify which variable has the most explanatory power. Multiple models will be created to identify the one that performs best. In order to increase the accuracy of the information generated by the model, risk forecasting will be added. The resulting model is meant to aid internal buyers in decision making. As our partner buys over 100 M USD worth of steel annually, an improvement in profits will be of great benefit to him.

Traditional insurance models build on the assumption of independence of risks. One of the main causes of the recent financial crisis, this assumption has facilitated the quantification of risks for decades, but it has often lead to risks' under-estimation and as a result under-pricing. Importantly, one of the prime pillars of the novel concept of Enterprise Risk Management is the requirement that insurance companies have a clear understanding of risks' interconnections within the risk portfolios. However, modeling dependence is not an easy call.