Shivam Srivastava

Title: Shivam Srivastava: Innovator in Time Series Forecasting

Introduction

Shivam Srivastava is a notable inventor based in Amherst, MA (US). He has made significant contributions to the field of forecasting, particularly in handling multivariate irregularly sampled time series data. His innovative approach addresses the challenges posed by missing values in time series data.

Latest Patents

Shivam holds a patent for his work titled "Forecasting in multivariate irregularly sampled time series with missing values." In this approach, a processor receives time series data that may contain one or more missing values. The processor identifies non-missing values present in the data and determines zero or more mask values. It also calculates time interval values. By inputting the missing values, non-missing values, mask values, and time interval values into a recurrent neural network, the processor predicts values for the missing data. This patent showcases his expertise in utilizing advanced computational techniques for data analysis.

Career Highlights

Shivam is currently employed at International Business Machines Corporation, commonly known as IBM. His role at IBM allows him to work on cutting-edge technologies and contribute to innovative solutions in data forecasting.

Collaborations

Shivam has collaborated with esteemed colleagues such as Berthold Reinwald and Prithviraj Sen. These collaborations have further enriched his work and expanded the impact of his innovations.

Conclusion

Shivam Srivastava is a pioneering inventor whose work in forecasting multivariate time series data has the potential to transform data analysis practices. His contributions at IBM and his innovative patent reflect his commitment to advancing technology in this field.