Recent Blogs and Best Practice articles
new!
-
Acing the Professional Solution Architect recertification
When the Anaplan Academy team first read Maryna Dunets' article on the new recertification process, we were thrilled to learn about her positive experience with the updated exams. Our goal has always been to design an exam that accurately measures a candidate’s ability to use the platform while minimizing unnecessary…
-
Forecaster algorithm properties
Review the table below for information on each algorithm and its specific properties.
-
Forecaster - Probabilistic forecasting using forecast quantiles
Probabilistic forecasts & forecast quantiles Forecaster produces probabilistic forecasts. This means that Forecaster algorithms output a distribution of possible values, rather than a single point forecast typically outputted by other solutions. This distribution can be divided into quantiles. Applied to forecasting,…
-
Forecaster - Using a backtest window to assess performance
In almost all cases, computing forecast accuracy requires a calculation of the difference between forecast versus actuals. One of the best ways to approximate the future accuracy of the forecast is to use a backtest window. With a backtest window, you can simulate “what if” you had run a Forecaster forecast with the data…
-
Forecaster - Introduction to forecast evaluation
Before making business decisions based on Forecaster forecast results, you should assess the expected performance of the forecast predictions in the real world. It’s important to evaluate forecast performance at the outset of your project as well as on an ongoing basis. Also consider that a range of factors unique to your…
-
Forecaster and related data
Background Customers are frequently wondering what can be used as related data. When thinking about related data, we can think about different types of “internal” time dependent inputs: Historical and future promotions Stockouts Price fluctuations Holidays and special events Actual data may be different dependent on a…
-
Forecaster - Deep dive into the Algorithms
Overview In this article, we review the algorithms that drive time series forecasting with Forecaster. These algorithms range from traditional statistical algorithms such as Exponential Smoothing (ETS), to those based on complex neural network algorithms such as DeepAR. Before talking about the algorithms in more detail,…
-
Forecaster - How to use item attributes to refine your forecast
Attributes are static, non-time-dependent categorical text features that describe the items in the historical time series data. Examples for attributes could be style, category, geographic location, size, item hierarchy level etc. The DeepAR algorithm can leverage the information captured in these attributes to produce…
-
Forecaster - Design and build your item list for forecasting
What is the best practice for concatenation in Anaplan? Step-by-step overview Level 1 – code inefficient Level 2 – code better Level 3 – Code to use Level 4 – Optimized code to use How do we handle items with limited to no history? Adding “Cold Start” Items In order to forecast forward based on historical data, the…
