PlanIQ

PlanIQ and related data
Author: Evgy Kontorovich, Sr. Director Product Management at Anaplan. 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…
Plan IQ
Hi All, How many predictions does Plan IQ offer per month? Also, how can we identify that the number of predictions that Plan IQ offers will be suitable for the client. Thanks in advance!
New Data collection in planIQ if the horizon is updated?
If the horizon for a data collection is changed, is it needed to: re-run the data assembly? retrain the forecast model? Or create a new data collection?
Explainability enhancements in Anaplan Prophet and MVLR
Our Forecasting data science team has recently released new enhancements to Explainability in Anaplan Prophet and MVLR. Previously, PlanIQ engine was able to identify lagging indicators among the related data. So, for example, if change in certain indicator, for example fuel price, would have a delayed impact of 1 month or…
Sometimes ETS and ARIMA generate "flat" forecast. Why would that be? Is that expected?
Sometimes this is the kind of output that ETS and ARIMA produce. When the historical data doesn't have strong seasonality the forecasting model may find it difficult to predict the future. Therefore it simply takes average of your previous values.
Plan IQ forecast model - is there any way to detour a limit in forecast horizon
Hi I'm new to PlanIQ - I'm curious with simple prediction setting can I make a prediction of, for example, data in 2022 with the historical data of 2020 in planIQ when my forecast horizon is limited? (without setting 24 prediction months & giving more data?) since it has a forecast horizon limit when creating a forecast…
PlanIQ backtest update
Following the discussion in https://community.anaplan.com/discussion/comment/154792 seems that there's a need to update backtest results as new actuals are flowing in.
Ability to load in Model Quality Metrics from Plan IQ
Currently there is no way to import back in the model quality metrics back into anaplan after your forecast has run in Plan IQ. These metrics would be key to show to a planner when they are evaluating the forecasts. For example MAPE of a particular forecast model. These metrics are exposed in planIQ but there is no way to…
PlanIQ - Probabilistic forecasting using forecast quantiles
Probabilistic forecasts & forecast quantiles PlanIQ produces probabilistic forecasts. This means that PlanIQ 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, quantiles…
PlanIQ Academy Training Updates
Good morning, We have recently updated PlanIQ training for most up to date features and insights - Enjoy!
Plan IQ. Data Collections. Data format
Hi! I have a question in regards to the 1st step of Plan IQ. (I went through Anaplan Plan IQ learning, but still cannot really figure it out) I set up data like in the example, but still it failed. It says: Historical or Related data Time column contains time format that is not recognised. Refer to the Anapedia article…
PlanIQ Blank Output
Hi, I'm facing an issue with PlanIQ output. Everything was running smoothly, without errors. Otherwise, I can not see any forecast results. ( Seasonlity, trends and predictions) Would someone help Please ? Thank you !
PlanIQ Backtest data automation and Backtest data should come for all Actual periods
PlanIQ Backtest data automation and Backtest data should come for all Actual periods as we import data let's suppose of 60 months for forecasting of 3 months then Backtest result come out for only past 3 months not for 60 months
Unable to see PlanIQ accuracy % for any algorithm run
As we are able to see the Metrics for Error, we also need the Accuracy % as well to know how best it forecast for future
PlanIQ Data Collection Scheduler
Need PlanIQ Data Collection Scheduler as if the months of actual data increases we need to rerun the Data Set once again by going to PlanIQ section
Add a Dimension in Forecasting PlanIQ
Hi, I want to use PlanIQ to forecast the demand of different products over time. I've managed to do so on PlanIQ, but now I would like to be able to forecast the demand of different products, over different countries. Every product exists in every country, and I would like to predict the demand. Therefore what I wanted to…
Varying level between backtest and results
Hello, After importing backtest results I'm noticing that the level of the backtest does not agree with the level of the forecast results (screenshots below) and this is across all foreecast nodes. Thankfully, the level of the forecast results seems to align with the level of historical actuals. Unfortunately, the…
Plan IQ - Import Actions
Recently i have been running a lot of IQ models then attempted import them back into Anaplan. However they often time out after 24 hours and i waste a lot of time. As when i re-run import they work. These are small models which no one else is using. I am only importing one IQ run at a time into the model so it shouldn't be…
__Exclude Anaplan IQ Functionality
Hi As many of your would be aware with time series forecasting which incorporates covid data we would like to exclude some dates with the historical data. Or exclude some volume shocks. Anaplan provides "Exclude" functionality. Wondering if anyone out there has used it?
PlanIQ - Deep dive on the algorithms under the hood
Baseline time series algorithms Advanced statistical time series algorithms Flexible local algorithms Neural network algorithms Summary Companies often develop plans and business strategies to drive decisions and actions around finance, operations, supply chain and other areas. They do this based on how they perceive the…
Anaplan AutoML and Amazon Ensemble
This article explains individual algorithms provided by PlanIQ. However, it does not address the automated methods provided by PlanIQ. As a customer you have several options: Use one of the automated methods as described below. Use combination of individual algorithms and automated methods and perform algorithm or method…
Plan IQ - Prophet Algorithm - End of year Dips
Hi I have been using prophet to do some forecasting and with my item i have a lot of end of year dips around christmas. I know IQ has holidays functionality which i have been using. I have also added a holiday boolean as an explanatory variable to help. But the forecast is still not diminishing enough on these weeks. My…
PlanIQ – Considerations Before Starting to Forecast
Before starting to forecast with PlanIQ, there are a few topics we recommend considering around the data, properties of the forecast, and forecast evaluation. While it is important to define clear goals for each forecasting scenario, PlanIQ's forecast accuracy will mostly be determined by the quality of the available data.…
PlanIQ – Considerations Before Starting to Forecast
https://community.anaplan.com/discussion/155032/planiq-considerations-before-starting-to-forecast
AWS Forecast used by Plan IQ
Regarding the AWS Algorithms that Plan IQ uses. Does AWS improve these over time and make version changes. The reason i ask is that lets i decide an algorithm isnt working for my forecast so i stop using it. But then months later the algorithm is enhanced and becomes more appropriate. How would know?
Impact of Attributes in the data collection
As some of you may know, attributes component of the data collection is mainly used by advanced ML algorithms, such as Amazon Ensemble, Anaplan AutoML, DeepAR+ and CNN-QR. Attributes allows those methods and algorithms to look at similarities across time series (items) and learn from them in order to improve forecast…
Easier troubleshooting of Forecast Action errors with new enhancement
We're happy to announce an enhancement that will make troubleshooting of Forecast Action errors easier. We know that in some cases, import errors are causing forecast actions to fail. Until now it was fairly difficult to troubleshoot them but with the recent enhancement it really becomes super easy. Now, if forecast action…
Best practices and documentation
Fellow PlanIQ users, we are constantly working on adding more best practices and documentation. Are there issues that you feel you're struggling with? Is there anything where we could provide better documentation? Let us know!
PlanIQ: 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 PlanIQ forecast with the data…
PlanIQ: Introduction to forecast evaluation
Before making business decisions based on PlanIQ 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…

PlanIQ

Discussion List