Geneva Forecasting API: An Expert System for Time-Series Forecasts
The article introduces the Geneva Forecasting API, a powerful time-series forecasting engine that has been powering forecasts for over 25 years, now available to all developers through a simple, modern API.
Why it matters
The Geneva Forecasting API provides developers with easy access to a powerful, proven time-series forecasting engine, which can be valuable for a wide range of applications that require accurate predictions.
Key Points
- 1The Geneva Forecasting Engine has been used as the core forecasting engine inside many Oracle products for years
- 2The Geneva Forecasting API is now available to all developers, with a free tier of 1,000 forecasts per month
- 3The API uses an expert system architecture to automatically evaluate and select the best forecasting method for a given time series
Details
The Geneva Forecasting Engine is a lightweight, rule-driven engine that automatically evaluates 10 statistical forecasting methods, each with best-fit parameter tuning and seasonality detection. It selects the strongest performer for the specific time series and returns the forecast, usually in under 200 ms. The engine uses an expert system architecture, which encodes the knowledge and decision-making process of human specialists into software, instead of training a large neural network. This allows the API to provide accurate forecasts without requiring extensive training data or complex model tuning.
No comments yet
Be the first to comment