Po Ming Law

Title: Po Ming Law: Innovator in Predictive Model Bias Detection

Introduction

Po Ming Law is an accomplished inventor based in Atlanta, GA (US). He has made significant contributions to the field of predictive modeling, particularly in the detection and isolation of biases within these models. His innovative approach addresses a critical issue in data science, ensuring that predictive models are fair and reliable.

Latest Patents

Po Ming Law holds a patent titled "Methods and systems for detection and isolation of bias in predictive models." This patent involves a sophisticated process where a processing device receives test data and training data from a client device. The device identifies feature groups from both datasets and generates performance metrics and baseline metrics for each feature group. By comparing these metrics, the processing device detects biases and isolates portions of the training data that correspond to the detected bias. Ultimately, it generates a model correction that can be used to remove the bias from the predictive model. He has 1 patent to his name.

Career Highlights

Po Ming Law is currently employed at Adobe, Inc., where he continues to develop innovative solutions in the realm of predictive analytics. His work is instrumental in enhancing the accuracy and fairness of predictive models, which are widely used across various industries.

Collaborations

Some of his notable coworkers include Sana Malik Lee and Moumita Sinha, who contribute to the collaborative environment at Adobe, Inc. Their combined expertise fosters innovation and drives advancements in technology.

Conclusion

Po Ming Law is a pioneering inventor whose work in detecting and isolating biases in predictive models is shaping the future of data science. His contributions are vital for creating fair and effective predictive systems.