Demand forecasting using weighted mixed machine learning models
A technology of demand forecasting and machine learning, applied in the field of computer systems, which can solve problems such as difficulty in adapting to market conditions, inaccurate forecasting, and forecasting methods not working very well
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0011] One embodiment generates multiple trained models by training multiple algorithms / methods and multiple features using historical sales data input, and then weighting each trained model based on an error value to predict demand for a product. Using weights and multiple models, a demand forecast is generated by combining the weighted forecasts generated by each trained model.
[0012] Sales and demand forecasting methods can be roughly divided into judgment methods, extrapolation methods, and causal methods. Extrapolation methods use only the time-series data from the activity itself to generate forecasts. Known specific algorithms / methods range from the simpler moving average and exponential smoothing methods to the more complex Box-Jenkins methods. While these known methods successfully identify and extrapolate trend, seasonality, and autocorrelated time series patterns, they do not account for external factors such as price changes and promotions.
[0013] Vector auto...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


