Jeremy Schmitt
About Jeremy Schmitt
Jeremy Schmitt is a Staff Data Scientist at Flock Freight, where he has worked since 2023. He has extensive experience in data science, having held various roles at FICO and the University of California San Diego, and has contributed to significant advancements in fraud detection and machine learning.
Work at Flock Freight
Jeremy Schmitt has been serving as a Staff Data Scientist at Flock Freight since 2023. In this role, he developed an efficient algorithm to address a complex NP-Hard pooling vehicle routing problem. This algorithm enables a shared truckload solution that effectively reduces emissions and costs. Prior to his current position, he worked as a Senior Data Scientist at Flock Freight from 2022 to 2023, contributing to various data-driven projects aimed at optimizing freight logistics.
Previous Experience at FICO
Jeremy Schmitt held multiple positions at FICO, starting as a Data Scientist II from 2017 to 2019. He then progressed to Lead Data Scientist from 2019 to 2021, and subsequently served as a Senior Data Scientist from 2021 to 2022. During his tenure at FICO, he collaborated with a diverse team of scientists and contributed to the development of over 100 patents in the field of fraud detection. His work focused on constructing machine-learning solutions to combat payment fraud, emphasizing fast algorithms to meet sub-second decision constraints.
Academic Background
Jeremy Schmitt has an extensive academic background from the University of California San Diego. He earned his Doctor of Philosophy (Ph.D.) in Mathematics from 2014 to 2017. Prior to that, he completed his Master’s Degree in Applied Mathematics in 2014 and a Bachelor’s Degree in Mathematics/Economics in 2010. Additionally, he served as a Graduate Teaching Assistant/Researcher from 2013 to 2017 and as an Associate Instructor for six months in 2016, gaining valuable teaching and research experience.
Research Contributions
During his academic career, Jeremy Schmitt focused on understanding the stability of non-fraud behavior patterns and the adaptability of fraudsters. His research emphasized the importance of learning stable behaviors to enhance fraud detection methodologies. This work contributed to his expertise in connecting information across multiple domains, which is crucial for developing effective machine learning solutions.
Skills and Expertise
Jeremy Schmitt possesses a strong skill set in data science, particularly in machine learning and algorithm development. His experience includes constructing algorithms that address complex problems in logistics and fraud detection. He has demonstrated proficiency in creating solutions that minimize false positives and meet stringent decision-making time constraints. His background in mathematics and economics further enhances his analytical capabilities in data-driven environments.