Riley Moher

About Me

I apply my experience in knowledge graphs, ontology engineering, process mining, and data science to understand and transform data into meaningful insights. My recent work focuses on transforming process mining workflows with knowledge graphs and ontologies to enable more sophisticated, transparent, and explainable process mining. I am also passionate about making formal ontology work more grounded and data-driven to improve the quality and usability of ontologies in practice. I hold a BASc and MASc in Industrial Engineering from the University of Toronto, with research in knowledge engineering, data science, & enterprise modelling.

Here’s what I've been up to.

These are some of the projects, publications, and experiences I've been involved in.

Ontology-driven Process Mining Analysis Engine (OPAL)

A python library which implements ontology-driven process mining techniques. Currently in active development, this project aims to provide a comprehensive framework for analyzing and improving business process analysis using ontologies.

What's in a (Data) Type? Meaningful Type Safety for Data Science

Presented at the 2022 Research Challenges in Information Science (RCIS) conference in Barcelona, Spain, this paper details a framework to model and automatically detect common errors in data science.

Engineering Capstone Project

Forecasting Model for Air Canada Pilot Productivity. In a small team, I developed a machine learning forecasting model for pilot scheduling at Air Canada. It resulted in a 40% improvement in forecasting accuracy.

Developing Graph-Based Evaluation Methods for Business Process Model Querying

With evolving and increasingly digital processes, enterprises are faced with large process repositories of complex process models. This paper introduces new ways for enterprises to develop and evaluate models to perform meaningful searches of their enterprise process repositories.

Towards an Ontology-Based Execution Monitoring Framework

In this paper, I developed a framework for ontology-based execution monitoring based on a case study in compliance issue remediation at a major Canadian bank.

MASc Thesis

"Meaningful Datatypes: Ontologically-Sound Dependent Type Systems for Data Science" combines the research domains of data science, ontology engineering, & functional programming to detail a framework to encode real-world rules as sophisticated types for use in data science.

Medium Publications

On Medium, I write beginner-friendly articles on advanced computer science concepts.

Find Me Online

Learn more or contact me about my work