Fusion of heterogeneous machine learning models to identify broker mismanagement

Lexington Innovations serve AI based data analytics solutions to financial institutions across North America Institutions recommend financial products and instruments from different brokers to their customers. The institutions are required to ensure that the trades serve their customer interests. The existing rule-based system results in high false positives. The recommendations that are identified as positives are scrutinized by financial analysts, which is costly and inefficient.

Designing Student Success: Building a Mobile Application to Improve Student Retention and Persistence

Ipse is creating a mobile application platform to support student success. Although many elements of the platform have been created and tested, this particular project focuses on the final development, testing and refinement of the minimum viable version o f the platform. Working with the Canadian partner, the US intern will act as a lead programmer and a technical coordinator for this project.

Development of natural antimicrobial topical product from traditional Philippine medicinal plants

Antimicrobial resistance (AMR) occurs when antibiotic drugs and products stops working, making it difficult to treat infections and diseases which could lead to further health complications and death. Therefore, development of antibiotic products is needed to control the increasing cases of AMR. Medicinal plants are a great source of natural antibiotic compounds to make antibiotic drugs and products.

Building a Mobile Application to identify Factors that Impact Student Success and Mental Health Amongst Living Arrangements: Part 2

This research seeks to inform the development of, and fully test and develop a mobile application designed to improve the process in which students’ find accommodation and roommates. I will develop wireframes and ask users to provide feedback on how to improve the platform. Then I will take the information collected to develop a prototype that can successfully match students based on preferences to help them in selecting a roommate.

Continuous calibration, interpolation and predictive analytics using Machine Learning

The company provides devices to measure quality of curing light used in dental procedures. These devices produce high volume and high velocity data. This data is then used to forecast a future state and to make a well informed business/operation decision according to an expected future state. One of the challenges in application of such technology is to improve prediction accuracy of the forecast. The company has developed prediction models based on physical chemistry that have been very useful to both the vendors and dentists.

Financial Portfolio Reconciliation using Deconstructed Deep Learning

Citco provides financial products and services to hedge funds, private equity and real estate firms, investors, institutional banks, Global 1000 companies, and high net worth individuals in the Netherlands and internationally. The previous research was focused on optimizing operations by automating trade resolution and reducing risk using machine learning. Given its success in matching individual transactions, the proposed project plans to extend the research to overall portfolio management for identifying discrepancies in the portfolio at the end of the trading day.

Understanding Coastal Ecosystem Response to Nature-Based Climate Adaptation Methods in a Cold Climate

The maritime provinces are currently facing questions around how to create more resilient coastal communities in the face of a changing climate, specifically due to impacts of sea level rise and increasing severity and frequency of storm events. One option for adapting to climate change is to move away from hard infrastructure towards softer/greener approaches, such as nature-base adaptation solutions, also known as “building with nature”.

Temporal soft clustering for profiling and predictive analytics in elderly care homes

Nxtgen Care provides monitoring services for elderly care homes across North America. Their product provides detailed analysis in visual formats to understand the resident’s requirements and directing care in that direction. To meet this goal, voluminous data is collected from the various activities of the residents. Through this project, this data is processed and directed in a way to optimize resources for effective scheduling in a timely manner. This is done with the help of advanced Machine Learning (ML) and Artificial Intelligence (AI) techniques.

Identifying leading safety culture improvement practices to drive innovation to assist in the prevention of workplace injuries

When safety critical organizations develop safety culture improvement strategies they are rarely shared widely outside the organization as there is limited benefit in sharing with others. In contrast to healthcare there is not a tradition of publishing safety improvements in journals or professional magazines. When innovations are shared externally, the description is often sanitized and does not contain then challenges encountered and missteps. In addition, consultancy companies provide a large proportion of the widely shared safety innovations, as they wish to promote their services.

Impact Evaluation and Developmental Evaluation Planning with a Community- Based Not-for-Profit Organisation Focussed on Poverty Reduction

The purpose of this project is to assist a community non-profit organisation to build a comprehensive plan to evaluate its poverty reduction initiatives and activities. The agency partners with other non-profit agencies as well as with government partners, other stakeholders, and persons with lived/living experience.