Rong Yuan

Title: Innovations of Rong Yuan in Time Series Forecasting

Introduction

Rong Yuan is an accomplished inventor based in Mountain View, CA (US). He has made significant contributions to the field of time series forecasting, particularly through his innovative patent. His work focuses on enhancing the accuracy and efficiency of forecasting methods, which are crucial in various industries.

Latest Patents

Rong Yuan holds a patent titled "System and method for multi-horizon time series forecasting with dynamic temporal context learning." This patent describes a system and method for time series forecasting. The method includes providing input feature vectors corresponding to a plurality of future time steps. It involves performing a bi-directional long-short term memory network (BiLSTM) on the input feature vectors to obtain hidden outputs corresponding to the future time steps. For each future time step, the method performs temporal convolution on the hidden outputs using a plurality of temporal scales to obtain context features. These context features are then summed using various weights to obtain multi-scale context features, which are converted to achieve time series forecasting for the future time steps.

Career Highlights

Throughout his career, Rong Yuan has worked with notable companies, including Beijing Jingdong Shangke Information Technology Co., Ltd. and JD.com American Technologies Corporation. His experience in these organizations has allowed him to apply his innovative ideas and contribute to advancements in technology.

Collaborations

Rong Yuan has collaborated with talented individuals such as Chenyou Fan and Yuze Zhang. These collaborations have likely enriched his work and fostered a creative environment for innovation.

Conclusion

Rong Yuan's contributions to time series forecasting through his patent demonstrate his expertise and commitment to innovation. His work continues to influence the field and showcases the importance of advancements in forecasting methods.