17644350. Time Series Model Update simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
Contents
Time Series Model Update
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
Time Series Model Update - A simplified explanation of the abstract
This abstract first appeared for US patent application 17644350 titled 'Time Series Model Update
Simplified Explanation
The patent application describes a computer implemented technique for updating a time series model using historical data. The technique involves splitting the data into subsets, selecting relevant data to update the model, exploring pattern changes in the new data, and incorporating new predictors of pattern change to obtain an updated version of the model.
- Splitting data of a historical time series data set into subsets
- Updating a time series model by backwards data selection to obtain an interim version of the model
- Exploring pattern changes in the new data to obtain new predictors of pattern change
- Updating the interim version of the time series model by applying the new predictors of pattern change to obtain an updated version of the model
Potential Applications
- Forecasting future trends in financial markets
- Predicting customer demand for products or services
- Analyzing patterns in weather data for climate prediction
- Monitoring and predicting changes in stock prices
Problems Solved
- Outdated time series models can lead to inaccurate predictions
- Difficulty in identifying relevant data for updating time series models
- Inability to capture pattern changes in the data
- Lack of efficient techniques for updating time series models
Benefits
- Improved accuracy in time series predictions
- More efficient and automated process for updating time series models
- Ability to capture and incorporate pattern changes in the data
- Enhanced decision-making based on up-to-date time series models
Original Abstract Submitted
A computer implemented technique including: splitting data of a historical time series data set into subsets; updating a time series model by backwards data selection to obtain an interim version of the time series model; exploring pattern changes in the new data to obtain new predictors of pattern change; and updating the interim version of the time series model by applying the new predictors of pattern change to obtain an updated version of the time series model.
