Prof. Blessy Joy

Assistant Professor

[email protected]

Blessy Joy is an accomplished data engineering and analytics professional with a strong track record of blending international corporate expertise with management education. Specializing in machine learning architectures, predictive modeling, and business intelligence, her work focuses on translating complex data infrastructures into actionable corporate strategy.

Prior to joining the faculty at Sahrdaya Institute of Management Studies (SIMS), she built extensive cross-functional experience abroad, serving in key technical and analytical roles, including data engineering at Heartland and data analysis at Beca, New Zealand. Throughout her corporate tenure, she managed large-scale data architectures, deployed machine learning pipelines, and spearheaded analytics initiatives designed to optimize organizational decision-making and digital governance.

Driven by a highly practical, industry-aligned pedagogy, she is committed to bringing advanced computational concepts and data-driven frameworks into accessible, strategic tools to mentor the next generation of business leaders.

·        PhD in Computer and Health Science; completed 1 year of research at the University of Waikato, New Zealand, specializing in Machine Learning

·        PG Diploma in Computing specializing in Data Science and Machine Learning from Unitec Institute of Technology, Auckland, New Zealand

·        M.Tech in Cyber Security, University of Calicut

·        B.Tech in Computer Science

Academic Experience

  • Assistant Professor in Computer Science at Nehru college of Engineering and research Centre, Pampady, Thrissur
  • Casual Lecturer in Computing at Unitec Institute of Technology, Auckland, New Zealand

Industry Experience

  • Data Engineer at Heartland Bank, New Zealand
  • Data Analyst at Beca NZ
  • Undertook various contract roles in several reputed Organizations in NZ

·        Accuracy vs Interpretability trade-off in machine learning in high-stakes decision models

·        GA2Ms models and other interpretable models