TIM Forecasting tool

TIM Forecasting tool is an implementation of TIM RTInstantML in Alteryx platform. Follow this manual to download it and install in the Alteryx Designer platform.

After installation, the tool is available in the Predictive category of the tool palette. You can drag & drop the tool into your workspace. The image below shows appearance of the tool icon in a workspace. The TIM Forecasting tool has one input and five outputs. By clicking on it, a configuration pane appears. We take a closer look on it in subsections below.

image.png

Inputs

D - Dataset

Input dataset used for the forecasting task. Follow this link to learn more about expected dataset structure. One additional requirement is that the timestamp has to be in the first column of the dataset.

Example:

image.png

Configuration Pane

By clicking on the tool a configuration pane appears. First you have to authenticate in order to be able to use the tool.

Then you can proceed to data configuration part of the pane, see image below.

image.png image.png

The available configuration is:

  • Predictors - which predictors to use for forecasting.
  • Target - target column (column/variable that is predicted).
  • Forecasting horizon - How many steps from last target record is desired to forecast

The advanced settings configuration is split into four sections:

Outputs

S - Status of the forecasting task

Status of the forecasting request sent to TIM API.

Example:

image.png

P - Prediction

Timestamps with corresponding predictions, upper and lower prediction interval bound and backtesting columns (backtesting is returned only if configured in advanced settings).

Example:

image.png

I - Importances

Percentual importance of individual predictors in the model.

Example:

image.png

E - Extended importances

Percentual importance of features built by the engine.

Example:

image.png

G - Graph path

Path for treemap rendering.

Example:

image.png