Yang Zhao

Title: Yang Zhao: Innovator in Machine Learning-Based Anomaly Detection

Introduction

Yang Zhao is a prominent inventor based in Shanghai, China. He has made significant contributions to the field of machine learning, particularly in the area of anomaly detection. His innovative approach has the potential to enhance real-time data monitoring across various industries.

Latest Patents

Yang Zhao holds a patent for a groundbreaking invention titled "Machine learning-based anomaly detection using a multi-layer predictor with hybrid inputs." This patent discloses a method and apparatus for real-time data monitoring based on machine learning. The method includes training a multi-layer predictor on actual values of historical indicator data, with each layer comprising a plurality of predictors of different types. The invention allows for the output of predicted values of future indicator data by inputting a future time period into the trained multi-layer predictor. It also calculates alarm thresholds from the predicted values and historical prediction errors, triggering an alarm when actual values exceed these thresholds. This innovation improves the accuracy of alarm thresholds and adapts well to constantly changing indicator data, reducing the need for manual configuration and minimizing missed and false alarms.

Career Highlights

Yang Zhao is currently employed at China UnionPay, where he applies his expertise in machine learning to develop advanced solutions for data monitoring. His work has garnered attention for its practical applications and effectiveness in enhancing operational efficiency.

Collaborations

Yang collaborates with talented colleagues, including WenQi Li and Gao Lin, who contribute to the innovative projects at China UnionPay. Their teamwork fosters a creative environment that drives technological advancements.

Conclusion

Yang Zhao's contributions to machine learning and anomaly detection exemplify the impact of innovation in technology. His patent reflects a commitment to improving data monitoring systems, showcasing the potential for future advancements in this field.