Evaluating models that rely on aggregate historical data
A technology of data sets and topic models, applied in the field of evaluating models that rely on aggregated historical data, can solve problems such as no repeatable standards
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0022] Complex systems involving a large number of variables include, for example, weather forecasting systems, market analysis systems, traffic forecasting systems, elevator demand forecasting systems, and the like. Often, these (and other) complex systems can be affected by a number of different factors. For example, weather forecasts use models based on variables such as precipitation levels, humidity, air pressure, temperature, wind speed, and movement of transition fronts. While it is easy to know whether the forecast was accurate (e.g., did it rain when it was predicted to rain, or did it not), it can be difficult to know how much influence any one variable exerted (e.g., did it rain because the temperature dropped or vice versa?). Similarly, when it comes to advertising, it is difficult to know how much sales are being driven by ad spending, and more specifically, how much ad spending in one format (e.g., broadcast media) is compared to another (e.g., online advertising...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


