Machine Learning algorithms for Wealth/Asset Management solutions - ON-538

Project type: Research
Desired discipline(s): Engineering - computer / electrical, Engineering, Computer science, Mathematical Sciences, Mathematics
Company: PureFacts Financial Solutions
Project Length: Longer than 1 year
Preferred start date: As soon as possible.
Language requirement: English
Location(s): Toronto, ON, Canada; Canada
No. of positions: 1
Desired education level: Postdoctoral fellow
Search across Mitacs’ international networks - check this box if you’d also like to receive profiles of researchers based outside of Canada: 
Yes

About the company: 

Headquartered in Toronto, with offices in London and Zurich, PureFacts was founded in 1997 by Robert Madej. Today the wealthtech enterprise solution provider serves over 100 clients in North America, the EU and UK, as well as APAC. Solutions for wealth management include fees, billing, and commissions management; transparent frictionless reporting; and data aggregation, all built on an innovative augmented intelligence platform.

Describe the project.: 

Our main goal is to create a machine learning solution that can be deployed in the clients’ environment. Our clients are mainly wealth and asset management firms and we have access to an enormous amount of financial data. Our solution must consider the actions and decisions that will be taken by our clients and then update the parameters to address the changes.

The candidate will be responsible to identify and developing the best model that can not only handle data with anomalies but also data that is dynamically changing. The candidate also has to create innovative algorithms to solve some of the complicated problems in the wealth management domain.

We are using Azure products as well as some natural language processing algorithms. Our data is also tabular and SQLs are extensively used to access the data.

Required expertise/skills: 

  • Strong problem-solving skills with an emphasis on product development
  • Experience working with and creating data architectures
  • Partner closely with product, engineering, and other business leaders to influence product and program decisions with data
  • Design and implement end-to-end data pipelines: work closely with stakeholders to build instrumentation and define dimensional models, tables, or schemas that support business processes
  • Experience with applied statistics and quantitative modeling (e.g. regression, survival analysis, segmentation, experimentation, and machine learning when needed)
  • Deep understanding of advanced SQL techniques
  • Deep understanding of NLP
  • Optional: Wealth and Asset management experience in the financial domain is an asset.