17806550. UTILIZING AN ENSEMBLE-BASED MACHINE LEARNING MODEL ARCHITECTURE FOR LONG TERM FORECASTING OF DATA simplified abstract (Juniper Networks, Inc.)
Contents
UTILIZING AN ENSEMBLE-BASED MACHINE LEARNING MODEL ARCHITECTURE FOR LONG TERM FORECASTING OF DATA
Organization Name
Inventor(s)
Shruti Jadon of San Jose CA (US)
Ajit Krishna Patankar of Fremont CA (US)
UTILIZING AN ENSEMBLE-BASED MACHINE LEARNING MODEL ARCHITECTURE FOR LONG TERM FORECASTING OF DATA - A simplified explanation of the abstract
This abstract first appeared for US patent application 17806550 titled 'UTILIZING AN ENSEMBLE-BASED MACHINE LEARNING MODEL ARCHITECTURE FOR LONG TERM FORECASTING OF DATA
Simplified Explanation
The patent application describes a device that processes time series data using machine learning models to generate future predictions. The device can adjust the steps into past data, future predictions, and skipping steps to optimize the predictions.
- The device receives time series data
- Defines steps into past data, future predictions, and skipping steps
- Determines if future predictions do not overlap
- Processes data with machine learning models
- Generates a list of non-overlapping future predictions
- Provides the list for display
---
- Potential Applications
This technology can be applied in various fields such as financial forecasting, weather prediction, and stock market analysis.
- Problems Solved
This technology helps in making accurate future predictions by optimizing the steps into past data and future predictions.
- Benefits
The benefits of this technology include improved accuracy in forecasting, better decision-making based on predictions, and increased efficiency in data analysis.
- Potential Commercial Applications
Optimized future prediction technology can be utilized in industries such as finance, agriculture, and logistics to improve planning and decision-making processes.
- Possible Prior Art
One possible prior art for this technology could be existing machine learning models used for time series analysis and prediction.
---
- Unanswered Questions
- How does the device determine the optimal steps into past data and future predictions?
The patent application does not specify the exact method used by the device to determine the optimal steps for processing time series data.
- What types of machine learning models are used in the processing of time series data?
The patent application mentions the use of machine learning models but does not provide details on the specific types of models utilized in generating future predictions.
Original Abstract Submitted
A device may receive time series data, and may define a first quantity of steps into past data utilized to make future predictions, a second quantity of steps into the future predictions, and a third quantity of steps to skip in the future predictions. The device may determine whether the second quantity is equal to the third quantity. When the second quantity is equal to the third quantity, the device may process the time series data, with a plurality of machine learning models, to generate a plurality of future predictions that do not overlap, may merge the plurality of future predictions into a list of future predictions, and may provide the list for display. When the second quantity is not equal to the third quantity, the device may process the time series data, with the plurality of machine learning models, to generate another plurality of future predictions that do overlap.
