While the AIssisted™ Time Series Prediction Wizard makes predictions based on previous data, the AIssisted™ Driver-Based Prediction Wizard fine-tunes results 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 wizard guides you through the simple, three-step process of bringing predictive forecasting technology to your custom work environment. It begins with the Driver-Based Prediction Overview.
Driver-Based Prediction Overview
The 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:
You may choose any cube for predictive planning purposes, so long as it has at least three dimensions that AIssisted™ Driver-Based Prediction can utilize as the
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 chooses the most accurate calculation. Alternatively, you can prescribe a specific algorithm (Liner Model, Holt Winter, etc.).|
|LAST EDITED||Shows the last time each cube’s forecast was edited.|
|PREDICTIVE RANGE||Shows the start date, end date, and duration (in months) of the time period undergoing the predictive forecast.|
|START (button)||Runs predictive forecasting for your cube.|
|EDIT (button)||Allows you to adjust the input data of the cube (e.g. change the predictive range, use a different algorithm, or choose different dimensions/elements).|
|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)||Shows a preview of the populated data and compares the actual data with your predicted data. It also provides you with an accuracy percentage.|
|New Setup (button)||Adds AIssisted™ predictive setup for a cube.|
Click New Setup to make a predictive forecast. The 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 has the necessary parts for predictive forecasting to function. A validated cube must have a
Time dimension, a
Version dimension, and a
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
Measure dimensions, 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 AIssisted™ Time Series Prediction Wizard, the AIssisted™ 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 to which the driver points.
You can select your drivers by clicking on the adjustment icon () next to the
Source Measure dimension and choosing the elements you want to set, with a short pause between each selection. You must pick at least two different measures, but you may indicate more as you like, e.g.
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 topmost elements for additional dimensions. You may, of course, also select your source material manually. Simply select the start and end
Time dimensions from the combo boxes, then click the adjustment icons to pick the rest of your source material, which can include multiple elements per dimension, with the exception of the
Note: when setting your prediction source, more specific element selections result in more accurate forecasts.
When you are finished, click Next.
Step 3: select Prediction Properties
Now you must select the Prediction Properties, namely the interval, duration, and type.
You can choose 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 1-24 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 drivers have a direct impact (such as weather), others 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 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 the Driver-Based Prediction or simply save your prediction settings. Either way, your forecast for this data set will now appear in the Overview. Here it can be viewed, modified, and executed at any future point.
Once executed, the data automatically becomes available in the cube and can be implemented in reports and templates.