Authored by: Abdul Sattar

In this two-part blog series, we will explore what is an Outlier all about, what are a demand planner’s problems and how can outlier help solve these problems. In this Part-1 of the blog, let us understand the background about Outlier in a layman term and deep dive about it in Part-2 in the following week.

Background

Analogically, if Sales is the reality then Forecast is a compass, which leads you to the future. It is the force that secures an organization’s future.

As a scholar once said, “Forecasting is hard but it’s harder to run a business without doing it.” It’ s mere not just assumptions of future but rather a more holistic approach to capture the effect of drivers of sales.

Its first step, as the same plan might be used, to –

• run the heuristics to share the material plan with supplier, or
• see the bottleneck, or
• used by optimizer to optimize the network & reduce the unnecessary expenses, or
• used by inventory planner to plan their inventory activity.

Thus, forecast is crucial as it directs us to success. Hence, one should not bungle up in the initial step.

Forecasts are based on historical trend and no forecast is perfect as all of them try to mimic the future and hence the ones which predict the future more accurately should be the best one.

Hence, capturing historical data is the most crucial step, as any anomalies at this juncture might affect the forecast, causing overstocking and stock out problem. This will increase the risk of either tying-up of working capital or loss of customer.

The anomaly in data could be because of either of the following reasons:

• Outlier
• Missing Value in data

In this blog we will shed some light on the outlier.

Outlier

Any Data point that falls outside the expected range of data.

The main reason for having outliers could be:

• When the data are scaled inappropriately
• Data corruption
• Error committed during data entry
• Unanticipated event which might not repeat, such as:
  • Trend in market
  • Supply disruption
  • Stock Outs
  • Independent demand
  • Any Opportunity
  • Marketing event

Planner’s Problems

• Which Data points should be considered as an outlier?
• How to remove right amount of outlier
• Planner process with huge number of planning combinations makes removal of outlier manually practically impossible

SAP IBP helps you to do that using two methods:

• IQR
• Variance Test

How can Krypt help?

Krypt is an SAP preferred partner and has assisted in the success of global businesses across industries & geographies. We have helped businesses through successful integration & implementation of SAP IBP, SAP GTS, SAP TM & SAP EWM.

If you are a global consumer products company looking for successful IBP deployment, and wish to explore more about our products/services, please request a DEMO or do contact us.

Follow us on: