Understanding the likelihood and trends in the occurrence and severity of natural disasters is an intricate part of insurance risk analytics. In today’s marketplace, the task of quantifying such risks is handled by vendors of catastrophe modeling tools. Due to proprietary, the vendors do not disclose the scientific and technical at sufficient detail for the users (insurance companies) to understand the modeling output thoroughly, such as sensitivity to assumptions, difference among different models, etc.
The research will analyze and investigate the range of development opportunities in historic buildings within a two hour radius of Kitchener/Waterloo, Ontario that have become vacant in the last few years as a result of economic and social restructuring. It will help to preserve sites of cultural significance in the province which is in support of a number of principles in the Ontario Heritage Act (2005). Some possible research questions are: should municipalities have special policies for these buildings? What role can Municipal Heritage Committees play in promoting these developments?
This project will require the intern to use statistical techniques such as a K-means to cluster customers into different groups based upon their relationship to Kraft and how those relationships drive business value for Kraft. The intern will also use logistical progression and decision trees to create models that will be able to predict the business value of future customers.
Sparkmatrix, a provider of online tools for property managers, has positioned one of its next-generation service provisioning commodities at IEEE 802.16 networks (or Wimax). The company successfully delivered IEEE 802.11 and IEEE 802.16 services to their customers. To improve the service quality and coverage, they considered deploying relays in order to erase any possible black notes and service deficiencies in buildings and offices.
Research In Motion (RIM) is a leading designer, manufacturer and marketer of innovative wireless solutions. High-quality reliable products are critical in today’s competitive manufacturing environment. To help monitor and improve their processes and products, manufacturers collect large amounts of data from a variety of sources including warranty claims, customer surveys, usage data, inspection, reliability testing and the manufacturing process. The goal of this research project is to determine how to model and make sense of these complex data.
The Property and Casualty Insurance Council of Canada (PACICC) is an umbrella body which insures Canadians against the risk that their providers of car and house insurance fail. It comprises many insurance companies, both large and small. The concern is that a local disaster might force the collapse of a locally concentrated insurance company, at large cost to PACICC. Such events are rare but costly. As such, it makes sense for PACICC to join with other similar bodies (such as CDIC, CUCC, and CIDO) to share these risks.
The nature of Statistics Canada's National Population Health Survey (NPHS) allows the use of event history analysis techniques to study relationships among events. The output from a series of health related questions to explore an association between pregnancy and smoking cessation was of especial interest. A methodology was proposed based on the notions of time order. In essence, the research team investigated whether one of the two events tended to precede the other closely in time. In this way, a causal interpretation of an association between these events would be more plausible.
Detecting ovarian cancer is, in general, difficult because of the lack of effective screening tests. If the disease is discovered when confined to the ovaries, surgery alone is curative in more than 90% of patients - however, in most patients, diagnosis only occurs after dissemination beyond the ovaries. In these cases, a combined treatment of surgery and chemotherapy is necessary. Unfortunately prognosis is grim and median survival is only 3 years despite treatment.