Dione is a web based software analytics tool that has been developed by the members and alumni of DSL (formerly Softlab) since 1997. The earlier version of the tool is called Prest which is an open access tool. Dione provides a complete set of tools to address a wide range of problems in software development. It includes modules for metric collection, analysis, and prediction models to suport critical decisioins in software project management: cost estimation of projects, the quality of code, release management, and resource allocation. Dione offers state of the art research and tecniques to help decision making under uncertainty. For more information please contact us.
IBM Toronto Lab
In this project aim to deploy DIONE to IBM to address practical challenges to test case prioritisation.
IBM Watson Analytics Project
This proposal is a collaborative effort between IBM Watson Analytics and the Data Science Laboratory at Ryerson University to build a context aware recommender system. The fundamental question that a recommender system aims to answer is: "what does the end-user really want?" If the end-user does not know the answer to this question, s/he would benefit from using a recommender system. IBM Watson Analytics - is one of the global leaders in the field of recommender systems. The end product of this project will be a software prototype recommender system empowered by contextual information that increases the level of engagement and acts as a catalyst in ultimately helping the end-user find what s/he really wants.
In this project we analyse customer behaviour and build predictive model to improve customer retention and risk management.
Toronto Stock Exchange Project
The Toronto Stock Exchange has chosen to partner with the Data Science Laboratory at Ryerson University and to provide access to most of its proprietary intraday trading data. This raw data contains information about trades, quotes and brokers occurring on a nanosecond time scale. Today, there is a real demand from customers not just to buy the raw data, but to buy analytics products that provide insights into the raw data. The end product of this project will be a proof of concept showing the conversion of raw intraday trading data from the Toronto Stock Exchange into analytics insights of trading strategies using intelligent algorithms. Ultimately, the Toronto Stock Exchange will be in a position to provide analytics products to market participants and market regulators.
Life science and Healthcare
Various collaborative projects with St. Michael hospital to improve clinical and operational outcomes using
In this project we empirically investigate how process, product and people related attributes of code review process enable the prediction of patch quality after code review task is conducted, and before patch is submitted to the mainline. The output of this study is beneficial for developers and managers in getting a better insight of review process and how to improve the overall quality of its output, in terms of providing patches with lower risk of being defective.
In this project we analyse user action behaviour to build a monetisation hybrid model and improve customer experience.
Selected Past Projects
Globe and Mail project
In this project, we propose a ranking based recommender model to rank the upcoming online news articles. We mined the web data of Globe and Mail. The data included types of articles, user subscription information, user behavior on the web page such as the duration, median time spent on reading, the number of visits, etc. We built a clustering and ranking model based on keyword to predict the popularity of upcoming online news articles and place them in the corresponding ranked section on the homepage of the newspaper to maximize the number of visits.
Relationship Mapping Analytics for Fundraising and Sales Prospect Research
NSERC Engage project with Charter Press Ltd. (in progress, 2015-16). Third Sector Publishing (TSP) has been successful selling CharityCAN subscriptions to fundraising organizations across Canada. This has been the result of incorporating a large volume of data from different sources that prospect researchers find useful as they attempt to identify potential donors for their organizations. There is an abundance of publicly available data that will be useful to CharityCAN subscribers. TSP will be able to extract this data from websites through automated extraction processes.
In this project, we empirically examine how social networks that constraint individual access to information about the behaviours and cognitions of other people evolve and change over time. We also use user’s location information to build a