AIssisted Driver-Based Prediction Wizard

image_pdfimage_print

While the Time Series Prediction Wizard makes predictions based on previous data, the Driver-Based Prediction Wizard fine tunes things further by considering further variables known as drivers. A driver is any set of data that affects a target. Weather is a common driver, but it means something quite different depending on whether you are predicting bike rentals or movie theater tickets sold.

The Driver-Based Predictive Forecasting Wizard guides you through the simple, three-step process of bringing predictive forecasting technology to your custom work environment. It begins with the Forecast Overview.

Driver-Based Prediction Series Prediction Overview

The prediction overview shows the cubes equipped with predictive forecasting. You can also see their database and information relevant to their forecast. 

The fields of the Driver-Based Prediction Overview are described below:

Field Description
Cube You may chose any cube for predictive planning purposes, so long as it has at least three dimension that AIssisted Predictive Forecasting can utilize as the Time, Version, and Measure dimension.
(DB) The database (DB) is your native work environment populated with custom data. We also provide demo data to allow you to familiarize yourself with predictive forecasting functionality outside of your own work environment.
Algorithm AIssisted planning uses a number of different algorithms. Each calculates predictive output for your actual data in a unique way. The Best algorithm calculates all other algorithms and choses the most accurate calculation. Alternatively, you can prescribe one a specific algorithms (Liner Model, Holt Winter, etc.).
Last Edited This shows the last time each cube’s forecast has been edited.
Predictive Range This shows the start date, the end date, and the duration (in months) of the time period undergoing the predictive forecast.
Start (button) Press start to run predictive forecasting for your cube.
Edit (button) The edit button allows you to adjust the input data of the cube (e.g. change the predictive range, use a different algorithm, or chose different dimensions/elements).
Remove (button) Selecting the remove button removes the AIssisted predictive setup for the cube. This prevents you from updating your predictive forecast for the cube, although the measure and data will remain unchanged. 
Preview (button) The predicted preview allows you to see the populated data and compare the actual data with your predicted data. It also provides you with an accuracy percentage.
New Setup (button) Click new setup to add AIssisted predictive setup for a cube.

Click New Setup to make a predictive forecast. The Driver-Based Prediction Forecasting Wizard will guide you through the necessary steps.

Step 1: Select and Validate Cube 

The combo box allows you to select a particular database and scroll through its assorted cubes. It also indicates whether each selected cube is validated for forecasting, i.e. whether it is has the necessary parts for predictive forecasting to function. A validated cube must have a Time dimension, a Version Dimension and a Measure dimension.

 

Once you have selected a validated cube, click next.

Step 2: Select Source

You have selected your cube. Now you must narrow your selection to a specific data slice.

The essential components of this slice are the Time, Version and Measure dimension, located in the upper portion of the wizard. You must pick more than one Measure dimension (please allow a slight pause between selections). Unlike the Time Series Prediction Wizard, the Driver-Based Prediction Wizard has both a source measure and a target measure. The source measure is the driver and the target measure is the data the driver point to.

You can select your drivers by clicking on the adjustment icon () next to the source measure dimension and selecting the elements you want to set, with a short pause between each selection. You must select at least two different measures, but you may select more as you like, e.g. Weather, Temperature, and Windspeed.

The Other Dimensions, found in the  lower portion, will further fine-tune your prediction. More exact specifications make your data slice smaller and may result in more accurate predictions. The Set Defaults button dynamically selects the first and last date elements as well as the top-most elements for additional dimensions. You may, of course, also select your source material manually. Simply select the start and end Time dimensions from the comboboxes, then click the adjustment icons to pick the rest of your source material. This can include multiple elements per dimension, with the exception of the Time dimensions. When setting your prediction source, please note: more specific element selections may make for more accurate forecasts.

When you are finished, click next.

Step 3: Select Prediction Properties

Now you must select the prediction properties, namely the prediction interval, duration and type.

You can chose to have monthly data or daily data (only select if daily data is available in the cube) for your prediction intervals and a predictive duration of between one and 24 months. There are various prediction types, each with different algorithms.  The Best prediction type runs all algorithms and selects the one that is the most accurate.

Prediction Shift allows for delayed drivers. While many drives have a direct impact (such as weather), some drivers take time before realizing their impact. If you hire new salespeople, it may take three months of training before they affect sales. In this case, you would set the Prediction Shift to 3 months.

Select the check boxes if you wish to apply either of our protective management tools. The accuracy cube stores the accuracy of the prediction for the chosen algorithm. When best mode is selected, the accuracy values for all algorithms are stored in the accuracy cube and the algorithm with the highest accuracy is chosen. Schedule Prediction automates a new prediction for a set interval: it will refresh your prediction along with incoming data at a set frequency (the default frequency is once per day , but you can customize the length of your prediction intervals in the Scheduler).

Once you have selected your prediction properties and chosen the predictive management you wish to incorporate, click next. 

You may now save and execute your predictive planning forecast or simply save your prediction settings. Either way, your forecast for this data set will now appear in the Forecast Overview. Here it can be viewed, modified, and executed at any future point.

Once you run predictive planning, the data automatically becomes available in the cube and can be implemented in reports and templates.

image_pdfimage_print