Estimation of Joint Distribution from Marginal Totals with Applications to Database Marketing

In many customer surveys and database marketing applications such as segmentation, profiling and predicting consumers’ choices, the joint distributions of covariates of interests are required. However, for variety of reasons, such as protection of clients’ confidentiality, the data are often available only in marginal frequency distribution format. This makes it difficult to use the covariates in a meaningful way where joint distributions are required for analysis decision making.

Automatic Map Layouts for Social Coordination with Location-Aware Mobile Devices

The research will identify aspects of a location-aware map application that could be automated (either directly or with user guidance) to reduce the amount of interaction required and to make effective use of the display space for smart phones. The research will involve designing a prototype location-aware map application and extending the prototype to include intelligent zoom features to effectively and intelligently present pertinent location information.

Analysis of Transaction Data on Graph Structure

The Communications Security Establishment (CSE) is Canada’s national cryptologic agency. CSE is mandated to acquire and provide foreign signals intelligence and to provide advice, guidance and services to help ensure the protection of Government of Canada electronic information and information infrastructures. It also provides technical and operational assistance to federal law enforcement and security agencies. The intern’s research centred on developing a model, or clustering technique, that will enable CSE to predict communications activity.

Statistical Learning for Technical Portfolio Management

ApSTAT Technologies Inc. provides insurance companies with analytical systems based on exclusive data mining technologies, enabling insurers to maximize the profitability of their operations. The company is working with a large financial institution to develop new financial products based on statistical learning techniques. The research team based at l’Université de Montréal had two objectives.

RuleML FOAF: A Web Rule Language for Social Networking

NRC-IIT creates and commercializes software and systems technology to help Canada prosper in the knowledge economy. The institute in Fredericton has been working with rule systems, semantic web standards and social networking since its inception. Web-based Social Networking is emerging as a major application area for semantic web metadata. Most social networking sites are based on a centralized architecture: all user descriptions are stored in one database.

Pattern Recognition and Its Application in Customers’ Family Composition Detection

Rogers Communications, a diversified communications and media company, wanted to investigate the kinds of strategies that it should employ to attract new customers and meet customer demands thus maintaining a profitable market share. To develop these strategies, the client needed new efficient tools that could extract useful patterns, which was representative of actual customer behaviour, from the company's data warehouses.

Algebraic Foundations of Structure Prediction

Axonwave Software Inc. of Burnaby, BC, is a leader in the field of unstructured data analysis and processing. The company provides solutions that enhance business intelligence and improve the efficiency of business processes through the ability to analyze and extract information from text-based information sources. In collaboration with Axonwave, the project involves unifying a number of algorithms unified for structure prediction into a single formal framework that will be the basis of a software toolkit.

Security of Routing Protocols

Alcatel, a leader in fixed and mobile broadband networks, applications and services, was interested in increasing the security of routers which are at the core of the Internet. It is generally acknowledged by experts that abusing routing protocols presents an easy way for launching attacks on the Internet infrastructure, and that a single misbehaving router can completely disrupt routing protocols and cause disaster. The intern and research team proposed a new security extension for BGP (Border Gateway Protocol) named Pretty Secure BGP (psBGP).