Planning & Forecasting in the Age of AI

Forecasting and planning are some of the very oldest use cases of modern statistics – businesses as far back as the 1950s used computer-based modeling to anticipate risks and make decisions. 

But traditional forecasting and planning methods can be wrought with manual processes and, therefore, unintended bias. For example, when it comes to forecasting, over-forecasting is a safer choice for a business because it ensures sufficient supply. In order to be more exact, these manual processes and decisions need to be removed entirely to make way for truly data-driven decisions.

Dataiku for Advanced Planning & Forecasting

Dataiku is the platform democratizing access to data and enabling enterprises to build their own path to AI. By making AI accessible to a wider population within the enterprise, facilitating and accelerating the design of machine learning models, and by providing a centralized, controlled, and governable environment, Dataiku allows businesses to massively scale AI efforts.

Dataiku offers a forecast plugin, which provides visual recipes to work on time series data and solve forecasting problems. The plugin offers a set of three visual recipes to forecast yearly to hourly time series. It covers the full cycle of data cleaning, model training, evaluation and prediction:

1. Cleaning, aggregation, and resampling of time series data.
2. Training of forecasting models of time series data (and evaluation of these models).
3. Predicting future values based on trained models.