Company Filing History:
Years Active: 2014-2020
Title: Innovations of Fenglin Liao
Introduction
Fenglin Liao is an accomplished inventor based in San Francisco, CA. He has made significant contributions to the field of machine learning and inventory management. With a total of 3 patents, Liao's work focuses on enhancing the efficiency of time-expiring inventory utilization.
Latest Patents
One of Liao's latest patents is titled "Regression-tree compressed feature vector machine for time-expiring inventory utilization prediction." This innovation includes systems for regression-tree-modified feature vector machine learning models aimed at predicting utilization in time-expiring inventory. The online computing system receives a feature vector for a listing and inputs it into a demand function to generate demand estimates. These estimates are then processed through a likelihood model to produce a set of request likelihoods. Each request likelihood indicates the probability that the time-expiring inventory will receive a transaction request at various test prices and times to expiration. Furthermore, the system trains a regression tree model based on training data that includes request likelihoods and the corresponding test parameters.
Career Highlights
Fenglin Liao has worked with notable companies such as Airbnb, Inc. and Google Inc. His experience in these leading tech firms has allowed him to refine his skills and contribute to innovative projects that leverage machine learning for practical applications.
Collaborations
Liao has collaborated with talented individuals in his field, including Spencer De Mars and Yangli Hector Yee. These partnerships have fostered a creative environment that encourages the development of groundbreaking technologies.
Conclusion
Fenglin Liao's contributions to the field of machine learning and inventory management are noteworthy. His innovative patents and experience with leading companies highlight his role as a significant inventor in the industry.