Share these talks and lectures with your colleagues
Invite colleaguesWe noted you are experiencing viewing problems
-
Check with your IT department that JWPlatform, JWPlayer and Amazon AWS & CloudFront are not being blocked by your network. The relevant domains are *.jwplatform.com, *.jwpsrv.com, *.jwpcdn.com, jwpltx.com, jwpsrv.a.ssl.fastly.net, *.amazonaws.com and *.cloudfront.net. The relevant ports are 80 and 443.
-
Check the following talk links to see which ones work correctly:
Auto Mode
HTTP Progressive Download Send us your results from the above test links at access@hstalks.com and we will contact you with further advice on troubleshooting your viewing problems. -
No luck yet? More tips for troubleshooting viewing issues
-
Contact HST Support access@hstalks.com
-
Please review our troubleshooting guide for tips and advice on resolving your viewing problems.
-
For additional help, please don't hesitate to contact HST support access@hstalks.com
We hope you have enjoyed this limited-length demo
This is a limited length demo talk; you may
login or
review methods of
obtaining more access.
Printable Handouts
Navigable Slide Index
- Introduction
- Measurements
- Agenda
- What about metrics
- What metrics do and don’t tell us
- Error metrics
- Error
- Percentage error metrics
- Comparison metrics
- Bias and tracking signals
- Bias and % bias metrics
- Forecastability measures
- Tracking signals
- Types of tracking signals
- Other types of forecast metrics
- Other forecast metrics to consider
- Measured = managed
- What is forecast value added?
- Translation
- For the best effect – combine metrics
- Using forecast measures to tell a story
- Forecast error bias and accuracy: Low bias & high accuracy
- Forecast error bias and accuracy: High bias & low accuracy
- Forecast error bias and accuracy: High bias & high accuracy
- Forecast error bias and accuracy: High FVA%
- Forecastability and forecast value added
- Demand forecast profile segmentation
- Demand forecast profile segmentation: Avoid forecasting
- Demand forecast profile segmentation: Selective forecasting
- Demand forecast profile segmentation: Collaborative forecasting
- Demand forecast profile segmentation: Market forecasting
- Metrics
- Summary
- Thank you
This material is restricted to subscribers.
Topics Covered
- Error metrics
- Bias
- Tracking signals
- Forecastability measures
- Bias and accuracy
Links
Series:
Categories:
Talk Citation
Eldridge, M. (2025, March 31). Performance metrics and measuring forecast accuracy and bias [Video file]. In The Business & Management Collection, Henry Stewart Talks. Retrieved April 2, 2025, from https://doi.org/10.69645/SNEW9655.Export Citation (RIS)
Publication History
- Published on March 31, 2025
Other Talks in the Series: Business Forecasting and Projections
Transcript
Please wait while the transcript is being prepared...
0:00
Hello and welcome
to today's session,
understanding the
forecasting process.
My name is Misty Eldridge,
and I've been in the planning and
forecasting arena for well over 20 years,
in a lot of different
companies of different sizes.
Today, we're going
to take a look at
the elements that go into
an end-to-end structured
forecasting process,
from data to collaboration
and consensus and
things to consider when
presenting the forecast.
0:26
There's a lot of things
that we need to measure in
our businesses and
how we perform.
Forecast measures are just as
important as anything else.
One of the things or stories
I like to tell people is
when you think about the
measures that you use,
how you use them, and
what you're grabbing can
really tell a difference in the
story you're trying to tell.
For example, I worked
for a company where
we were measuring service level.
I get it, it's not necessarily
a straight-up forecast,
but it illustrates
this point very well.
In this service level measure,
we were just doing
a simple shipment divided
by ordered quantity,
pulling it out of a major ERP,
pulling the fields
that said shipped and
fields that said
ordered or booked.
The problem we were
getting is that
we weren't really
measuring fill rates.
There weren't any on-time
considerations as part of this,
but we still weren't
measuring fill rates.
What happened is that
we were measuring actually
inventory accuracy.
Let me tell you how
that came about.
It was considered acceptable on
the morning of the shipment to
call customer service and change
the quantity on the order to
the booked quantity,
to the amount showing as
on hand in inventory.
When shipping would
go out and pull
the inventory to ship
on the truck that day,
they would then find
something different,
and so then they would
ship that amount.
For example, hypothetically,
the customer ordered 200 pieces,
the morning after, we had
100 pieces of inventory.
We then call
customer service and
we would change the quantity
on the order to 100 pieces.
We would go to
ship the order and
we could only find 98 pieces.
Then we would report that
we had a 98% fill rate on
this order when in reality,
we only had a 98%
inventory accuracy because
our fill rate was below 50%.
You can imagine the issues that
would cause and
the perception of
our customer on how
we were not able to
perform and fulfill a
customer service level.
Just as important as
forecast accuracy,
grabbing the right fields,
the right formulas,
using the right measures
in the right way can
really impact the
communication of
how you're performing
in forecasts and
how you use those measures.
Forecasting is not a
precision business.
But the measures that we use,
they tell us a lot
about our business
and are extremely valuable.