Studio platform: Forecaster

Forecaster is fast and user friendly way to execute AI/ML algorithm estimations

Studio platform:

Forecaster Studio Platform: Forecaster

The Forecaster section of the platform is designed to use a trained Artificial intelligence model and perform forecasts. Forecaster does have multiple ways to produce such forecasts (batch exports, API for one-by-one estimates). We encourage you to look into our optional integrations. Which will bring the best in class user experience and direct integration into ERP/CRM.

Trainer: Sources

On this screen, you can select sources of the data that will be used as input for forecasting. A list of sources is dependent and pre-configured specifically for each algorithm.

Sources could be in the form of CSV files or direct database/API integration into a specific ERP system. Data will be stored in memory and used for forecasting.

This configuration is stored in the project file so Forecaster could be triggered automatically, to reload data from specified sources when needed.

Forecaster: Columns and verification

On this screen you will be able to customize mapping between source data <-> expected internal fields as well as verify the data quality of the data.

Customise mapping: There may be cases where you need to change source column names in order to correctly process the data.

Verification of data quality: For each algorithm we prepared a set of rules which are designed to verify that data quality is sufficient to execute Machine learning. You may see warnings that will allow you to progress to the next step or errors which require correction before training could take place.

PDF data quality report: You are able to generate detailed data quality PDF reports which will help you understand what exactly needs to be corrected.

Forecaster: Data

On this screen, you see and browse data loaded into the system, add records and configure data for the Forecaster.

Data: During implementation, this screen will give you peace of mind that data has been correctly loaded. When you are performing forecasting, there may be a need to add or correct forecasting records and this can be accomplished on this screen.

Configuration of Data for Forecaster: Depending on the algorithm, different configurations for default values are configured. For example, for the discount recommendation, you can set up minimum margins, default values when new records appear, etc.

Forecaster: Forecasting

On this screen, you’ll execute forecasting using AI/ML algorithms based on your loaded data.

Forecasting: This is a process of combining data inputs from your system and trained models from the Trainer, to produce accurate predictions.

Forecaster Testing: The Studio application will allow you to execute the model directly from the user interface on record by record basis without the need to export data.

Forecaster CSV Output: Studio will combine all the data sources and produce a CSV output file. This functionality can be scheduled in order to link the Studio platform into external systems.

Forecaster API: Studio is able to start an industry-standard API server that will accept input on a record-by-record basis and execute on-demand forecasting. The Swagger portal for the API server is available in order to facilitate testing and development processes.