About

Hi! My name is Pat. I am a machine learning engineer and data scientist living and working in Cleveland Ohio.

I started my professional life working in consulting and finance but then I gradually moved to data science and machine learning. I designed and developed machine learning and data products for SaaS, sporting goods, and biotech companies in the US, EU, and Asia.

In my spare time, I enjoy beer, cooking, SCUBA diving, and looking at soccer stats.

Reach me at @pat_thon or LinkedIn


Noteable Publications

A Tale of Two Recommender Systems: The Moderating Role of Consumer Expertise on Artificial Intelligence Based Product Recommendations

Not all recommendation systems are the same. We show that expert beer drinkers prefer user-based collaborative filtering systems, whereas there is no difference between the two systems among novice beer consumers. Learn more

Teaching Artificial Intelligence and Machine Learning in Marketing

Machine learning is widely used in marketing. We show how marketing educators can introduce AI and ML concepts in their marketing classes and incorporate a cloud-based platform (AzureML Studio) by teaching students to create ML models. Learn more

Group Affiliation and Earnings Management of Asian IPO Issuers

Group-affiliated IPO firms in Asia can raise funds more easily than non-group firms, and as a result they have a lower need to manipulate earnings. Reputable underwriters help certify the validity of information for smaller IPOs. Learn more

Corporate Governance and Stock Returns in Asia

Only investors who can predict in advance which firms will improve their governance can earn abnormal returns. We investigate the returns of governance-based trading strategies in Asia, using bias-free return data. Learn more

Education
Harvard University

MLA in Software Engineering at Harvard Extension School, 2020

Mahidol University

PhD in Finance at the College of Management, 2013

University of Illinois at Urbana-Champaign

MBA in Finance, 2008

Thammasat University

BBA in Accounting, 2004