Hsiao Chien Shih
About Hsiao Chien Shih
Hsiao Chien Shih is a Data Scientist with a PhD in Geography from UC Santa Barbara. He currently works as an Adjunct Postdoctoral Scholar at San Diego State University and as a Data Scientist at E Source, where he has made significant contributions to data analysis and model accuracy.
Work at E Source
Hsiao Chien Shih has been employed as a Data Scientist at E Source since 2021. In this role, he focuses on utilizing data to provide insights and solutions for utility clients. His work includes the creation of graph datasets from geospatial data to analyze utility asset effects and the development of end-to-end data pipelines that have significantly reduced data ETL time by 50% on cloud infrastructure.
Current Role at San Diego State University
Since 2020, Hsiao Chien Shih has served as an Adjunct Postdoctoral Scholar at San Diego State University. In this position, he engages in research and academic activities, contributing to the university's academic community. His background in Geography and data science supports his role in advancing research initiatives within the institution.
Previous Experience at San Diego State University
Prior to his current roles, Hsiao Chien Shih worked at San Diego State University as a Researching and Teaching Associate from 2013 to 2020. During this seven-year period, he was involved in both teaching and research activities, enhancing his expertise in Geography and data analysis.
Education and Expertise
Hsiao Chien Shih earned his Doctor of Philosophy (Ph.D.) in Geography from UC Santa Barbara, where he studied from 2015 to 2020. His academic background is complemented by his studies at San Diego State University, where he also focused on Geography. This educational foundation supports his current work in data science and research.
Data Science Achievements
In his data science career, Hsiao Chien Shih has achieved notable outcomes, including a 30% cost savings for utility clients through the utilization of public and commercial remotely sensed data. He has also enhanced model accuracy by 20% by extracting time series features for identifying tree growth and building age, demonstrating his analytical skills and expertise in the field.