Top questions to consider when selecting

a demand forecasting solution

Is your demand forecasting solution working for you or are you working for it? We’ve
got the questions you need to ask (and what to do if the answers are “No”).

27 October 2020
AddThis Sharing Buttons
Share to LinkedIn
Share to TwitterShare to FacebookShare to Email

The world of retail is vastly different than it was a year ago, and retailers are more
challenged than ever to remain competitive. FMCG retailers understand that accurate
demand forecasting across all categories, including fresh, is key to maintaining their
competitive edge, staying profitable, and increasing sales – all of which are “reflectors”
of today’s shopper demand.

While there is no shortage of forecasting solutions, there is scarcity of solutions that

take into full consideration the complexity and reach of today’s FMCG retail supply
chain.

In this series, I’ll explore the key questions and the underlying issues that must be
addressed when evaluating your current demand forecasting solution and what to do if
that system comes up lacking.

The Question: Are demand planners working for the system or is it

working for them?

If your demand planners are struggling, it’s likely that data quality is a problem. Take
out-of-stocks, for example. When they occur, you’ve lost sales for a given item for a
period. Your planners bear the brunt of this because they must compensate and
manually input data into the forecasting system.
How about new product introduction? With most forecasting solutions, planners must
manually indicate to the forecast engine how to link this new item to a previous “like’’
item so that they can use that item’s history to forecast. And there are many types of
“new items.” It might be a brand-new item, a substitution of an existing item, or a
variant of an existing item. These all require substantial manual intervention.

Seasonality is another manual time sink for planners. Many forecasting tools have
features that attempt to help with this, but they are not fully automated. Add to this,
complicating factors like new store openings, which can have a significant impact on
forecasting, and things become even more manual and error prone.

The Solution

A recent survey conducted by EnsembleIQ Research revealed that 52% of retail supply
chain executives say they spend too much time crunching data. This lost time and
energy was the second greatest catalyst for new investment SCM solutions behind
availability (which I’ll be covering in a later part of this series).

To manage and successfully analyze the massive amounts of data retailers face, AI-
based forecasting with machine learning has become the new standard for retail demand
forecasting. With AI-based systems, there’s no need for retailers to hire additional data
scientists, which are a scarce (and costly) resource. Instead, the system serves as an
automated data scientist for your data, with new levels of information, alerts and
insights.

AI isn’t just for the largest retailers, either. The emergence of new Software as a Service
(SaaS) solutions makes AI a practical reality for retailers of all sizes, enabling them to
take advantage of the power of machine learning and free up their supply chain
managers for more strategic work.

Simply put, there are many activities for which maintaining good data is critical for the
forecast engine to perform correctly. Ensure the demand forecasting solution you
choose removes the manual intervention present in many systems today and has
advanced data-cleansing capabilities, that learn.
Don’t just take my word for it

“You have to be able to anticipate the precise expectations of each customer and the
exact needs of each point of sale in order to meet demand and to deliver maximum
fluidity and reliability. It is essential to manage the supply chain from end to end, with
great flexibility and responsiveness,” said Jean-Michel Balaguer, STIME President,
CTO of Groupement Les Mousquetaires, Intermarché entrepreneur, and Région Centre
Est administrator. “This is exactly what the AI-based technologies from SymphonyAI
bring us.”

Read the full Intermarche story here

Read the full survey report from Ensemble IQ: Strengthening the Retail
Supply Chain

Read part 2 in the series: Are your demand forecasting systems connecting all
categories across the store?

Read part 3 in the series: Why demand forecasting must be effective with all channels to
be effective with any

Read part 4 of the series: Avoiding the ‘blindside’: Inventory visibility and the agile
supply chain

Read part 5 of the series: Don’t let your demand forecasting depend on history to repeat
itself

Are your demand forecasting systems

connecting all categories across the
store?
Don’t let fragmented forecasting systems leave you with blind spots

02 November 2020
AddThis Sharing Buttons
Share to LinkedIn
Share to TwitterShare to FacebookShare to Email

Achieving a holistic understanding of customer demand across all categories and

channels improves the entire end-to-end supply chain. The recent rise of fresh demand
presents considerable challenges for retailers’ current technology to provide a complete
understanding of true demand. Add to that, the events of 2020 that caused sudden and
erratic shifts in shopping behavior, affecting both category and channel demand, and it’s
clear that retailers have to be able to see the full picture in order to be successful.
In this second part of my series on the key questions you need to consider about your
demand forecasting solution, I’ll be taking a look at the issues that arise when systems
only understand certain categories and cannot factor in the entire store.

The Question: Are your forecasting methods limited to specific

categories?

You may have an understanding of consumer demand across center store categories and
a separate system analyzing the perimeter categories and fresh – but are you able to
connect those dots to see how your customers fluctuate between categories and how all
sides of the business affect each other?

What happens in one part of the store does affect the others

Research conducted by EsembleIQ shows that only 36% of retail supply chain
professionals said their businesses operate on a single supply chain platform. Even
where this exists, demand is not complete.

Retailers often leverage best-of-breed solutions for the center store, but then manually
maintain or use home-grown solutions to manage fresh. Or, companies invest in a
separate vendor provider to manage fresh, isolating it from their center-store platform.

Indeed, most fresh-specific technology is not built to understand non-food categories.

And the systems in place for center-store planning don’t appreciate the nuances and
intricacies of managing fresh items. Thus, organizations are often operating with
disparate demand replenishment systems.
Fresh and perimeter categories (meat, dairy, produce, bakery, etc.) are particularly
challenging to forecast. These products are sensitive to external events, like weather, but
also have very short shelf life. Couple this with the demands of traceability and intra-
daily delivery for some products and the challenge of forecasting becomes even more
complex.

Using a primary system for general forecasting and a siloed method to forecast these
more challenging categories leaves retailers without a holistic view of all their products
and categories, further complicating things.

Your forecasting solution must be able to cope with the impact of all categories – center
and perimeter – while incorporating the nuances of each.

The Solution

To understand shopper demand patterns, you must understand all factors that impact
demand across all your categories and, not just a portion of them. As we’ve experienced
in 2020, there is much uncertainty in customer behavior and it can change rapidly.  The
agility to respond quickly to changes and adjust forecasts across all categories in single
system is key to avoiding costly mistakes. With a unified view of customer activity,
made possible with the right technology, you can gain a full understanding of customer
needs and motivations.

Artificial intelligence can perceive all impacts to store-wide demand. Applied correctly,
AI alleviates inconsistent inventory buys, overstocks (and the resulting markdowns),
out-of-stocks, and margin erosion. In fact, without proven AI and machine learning, you
cannot achieve a full understanding of consumer demand.

Seek out solution providers that have a proven track record in applied artificial
intelligence.

While customers will continue to be a moving target that retailers need to strive to
understand, the good news is that there is a way forward to achieve greater
understanding. Acquiring artificial intelligence and machine learning capabilities,
focused on a holistic understanding of demand, will bring a more complete, actionable
knowledge of today’s biggest retail disruptor: the customer.

Learn more about connecting all categories to create a unified supply

chain

Read part 1 of the series: Is your demand forecasting solution working for you or are
you working for it?

Read part 3 of the series: Why demand forecasting must be effective with all channels
to be effective with any

Read part 4 of the series: Avoiding the ‘blindside’: Inventory visibility and the agile
supply chain
Read part 5 of the series: Don’t let your demand forecasting depend on history to repeat
itself

Why demand forecasting must be

effective with all channels to be effective
with any
With shoppers today buying and receiving goods across multiple channels, are you able
to incorporate all your data sets to forecast demand for all?

19 November 2020
AddThis Sharing Buttons
Share to LinkedIn
Share to TwitterShare to FacebookShare to Email

Omnichannel retail and Click and Collect are not new concepts. However, the
occurrence of the COVID-19 pandemic turned what had previously been seen as a
matter of convenience into a matter of priority for health and safety. Now, as much of
the world enters a second wave of lockdowns, omni-channel retail remains as important
as ever.

Retailers’ struggle to not only keep inventory on the shelves but also understand the
complete picture of demand, including click and collect and home delivery, is not just a
problem in the immediate term but can have long-term detrimental effects on shopper
loyalty.

Welcome to the third part of my series on the key questions you need to consider about
your demand forecasting solution, where I’ll be exploring the keys to omnichannel
forecasting.

The Question: With the explosion in omnichannel retail, can you

incorporate all your data sets to forecast demand and fulfillment across
all channels?
 

The pressures that retailers, especially fast-moving consumer goods (FMCG) retailers,
felt in the second quarter of 2020 exposed weaknesses in the execution of the modern
supply chain and proved that it is not prepared for sudden, dramatic shifts.

Further, research conducted by Brick Meets Click shows that, in March 2020, online
grocery sales rose 233% and the number of customers rose 202% over figures
gathered just 9 months previous.

As mature as supply chains have become, they are still challenged with the fundamental
understanding of demand predictions and inventory visibility across so many emerging
retail channels. In a benchmark report from RSR Research released in Q1 2020,
Designing new ways to satisfy Demand, retailers cited unpredictability, growth of
demand and the pacing of digital channel expansion as top challenges. Further, 75% of
the retailers surveyed said that cross-channel fulfillment would drive them to
rethink their supply chains in the next 5 years.

The report shows us clearly that, even before COVID-19, retailers recognized that it is
essential to understand customer demand and needs across all channels. Too many
retailers today simply cannot understand the total channel picture when it comes to
effective demand forecasting.

What items are needed in the stores? How many of those items are going to be slotted
for in-store picking? How much inventory will I need to have available for my home
delivery customers versus my click and collect or locker pick up customers? These are
all questions that have become critically important as online shopping moves even faster
after COVID-19.

In order to truly provide an effective omnichannel experience, retailers need an end-to-

end solution that can understand true demand across the enterprise and then manage
inventory allocation into each demand stream and fulfillment channel.

The Solution

An efficient omnichannel fulfillment program must ensure synchronized inventory to

ensure on-shelf availability for both in-store and online shoppers. It needs to be able to
be able to drive accurate pick times and locations for associates or third-party
fulfillment partners.

Accurate fulfillment forecasting enables retailers to map demand forecasts to

fulfillment channels to effectively prioritize and execute orders no matter when,
where or how they are received by consumers.

Costs are always a primary focus for retailers. By connecting systems to optimize order
management, retailers can lower fulfillment costs by sourcing from the most appropriate
inventory source. By being able to confidently determine the best source for the
inventory needed for any given fulfillment channel – be it on-shelf, warehouse, dark
store or other – you’re always able to fulfil the needs of the customer at the lowest
fulfillment execution cost.

Complexity in the omni-channel marketplace is here to stay, but how retailers manage it
doesn’t have to be. By creating a unified supply chain, retailers eliminate siloed
channels and, with them, the associated inefficiencies. Retailers need to be able to
take control and manage the high volume of orders and channels in one place: e-
commerce, click and collect, mobile apps, promotions and more.

Learn more about the vital role of omnichannel optimization in today’s

retail in the whitepaper, Omnichannel Imperative: Meeting the needs of a
new consumer

Read part 1 of the series: Is your demand forecasting solution working for you or are
you working for it?

Read part 2 of the series: Are your demand forecasting systems connecting all
categories across the store?

Read part 4 of the series: Avoiding the ‘blindside’: Inventory visibility and the agile
supply chain
Read part 5 of the series: Don’t let your demand forecasting depend on history to repeat
itself

Avoiding the ‘blindside’: Inventory

visibility and the agile supply chain
Empower the supply chain to react quickly to changes in demand with full inventory
visibility to the enterprise

21 January 2021
AddThis Sharing Buttons
Share to LinkedIn
Share to TwitterShare to FacebookShare to Email

FMCG retailers today are hyper-focused on being able to prepare for and respond to
sudden and significant changes in demand and buyer behavior. One of the key lessons
learned during the COVID-19 surge in the 2nd half of 2020 is that traditional demand
forecasting methods are no longer enough.

The key is putting a system in place that enables retailers to react to massive disruptions
in the supply chain while, and after, they are happening and make that system
sustainable moving forward. To do this, full inventory visibility is a must.

This will be the topic of the fourth part of my series on the key questions you need to
consider about your demand forecasting solution.

The Question: Are you able to react quickly enough, daily or even intra-
daily, and generate accurate forecasts to meet changing shopper needs?

Focus on inventory visibility is not new – but it’s become an essential priority

A research survey conducted in December 2019 revealed that 76% of retailers named
real-time inventory visibility as a key focus area for improvement in the supply chain.
Further, 70% of retailers named the ability to respond more rapidly to demand a “very
important” driver of supply chain strategy. In the wake of the events of the last year,
these issues have only come into sharper focus.

Shopper behavior has dramatically changed and continues to change as we all manage
the impacts of the events of 2020. Cross-channel demand and fluctuating purchasing
frequency have a high impact on retailers’ ability to forecast what needs to be available
and when and how it will be fulfilled. The demand for fresh, prepared and foods-to-go
remain high but are more subject to cross-channel demand than before. Retailers that
serve prepared foods must have data insight to guide forecasting and replenishment
decisions that meet the demands of shoppers as well as an understanding of how all the
categories are affecting each other.

Moving forward, the vital component for every retailer’s supply chain is full and
accurate visibility into their inventory. Considering true inventory availability across the
supply chain when responding to forecasted quantities gives you the ability to not only
confidently predict changes in demand but the agility to respond rapidly when they hit
unexpectedly. Further, it enables you to support complex logistics networks, sourcing
and pulling product from multiple locations and/or vendors during a period of
disruption.

The Solution

Demand forecasting systems that include AI and machine learning drive continuous
improvement of demand and forecast accuracy. Algorithms are continuously retrained
using historical, current and contextual data without requiring user intervention.

Further, the AI will be able to fully understand the event as an anomaly that would not
normally exist in the demand cycle. It will be able to incorporate historical data pre-
event, data during the event and the incoming data post-event. This results in a full
understanding of the impacts of the disruption on shopper behavior in the near and short
term.

AI-enabled systems also remove the need for manual data manipulation and can process
all the disparate data sources in seconds to deliver actionable insights to the entire
enterprise on any device. This enables buyers, analysts and demand planners to spend
less time chasing data and reports and more time on critical tasks.
Read more about the research mentioned in this post in the RSR Research Benchmark
Report, The Retail Supply Chain: Designing New Ways To Satisfy Demand

Learn more about SymphonyAI’s solutions and insights for inventory management,
mobile store operations and assessing demand across all categories from fresh to center
store.

Read part 1 of the series: Is your demand forecasting solution working for you or are
you working for it?

Read part 2 in the series: Are your demand forecasting systems connecting all
categories across the store?

Read part 3 in the series: Why demand forecasting must be effective with all channels to
be effective with any

Read part 5 of the series: Don’t let your demand forecasting depend on history to repeat
itself

Don’t let your demand forecasting

depend on history to repeat itself
Using historical data as the primary focus for forecasting for events omits vital aspects
of demand and leads to incorrect assumptions

10 February 2021
AddThis Sharing Buttons
Share to LinkedIn
Share to TwitterShare to FacebookShare to Email

Traditionally, when forecasting for events and promotions, retailers simply took the
sales from the last x years, combined that data with current sales information and
calculated a plan for the upcoming event. In the days of a single-channel environment
with more predictable shoppers, that system was fine.

However, that is no longer the world in which we live. Ever-emerging channels, the
battle for loyalty and the rise of the digitally informed consumer have rendered the old
methods completely obsolete. Add to those issues the unexpected and dramatic
disruptions that have occurred with health issues, weather and economic shifts that
we’ve endured over the last couple of years, and it seems impossible to predict what’s
coming next.

In the fifth installment of my series on demand forecasting, I’ll be talking about why
retailers need to be more agile when it comes to events and other disruptions.

The Question: Can you accurately forecast for promotions, seasonal

events and weather and share these forecasts with suppliers to improve
availability?
Events, holidays, and the promotions that typically accompany them are complex. What
makes them even more complex, from a forecasting perspective, is that, after the events
of 2020, it’s practically impossible to decipher historical demand that is inflated or
distorted due to running out of stock – which may include demand events or promotions
or may not. Traditional forecasting systems depend on recurring events to forecast the
future, and don’t understand anomalies in demand or fluctuations in events so this
presents a fundamental problem.

Traditional forecasting systems deal with the problem of “lost past” by grouping like
items together and making assumptions such as, two similar products in the same
category will behave the same way. Making these types of assumptions greatly
oversimplifies the actual demand for the various items in a given category and can lead
to out-of-stocks for one product and overstocks of another. Retailers need to be able to
assess the nuances of all products to determine the best levels for all dimensions – store,
cluster, promotion, event, and channel.

Then we come to the forecasting issues specific to promotions. In some cases, the
supply chain may not even be aware of a promotion, leading to out-of-stocks and a
potential detriment to shopper loyalty. Even when the promotion is known, the supply
chain may not know which mechanics have been applied and how the promotion needs
to roll out and be fulfilled. Lastly, the supply chain needs to be able to monitor whether
the promotion execution was carried out properly across all channels and, if not, what
specifically happened to reduce the effectiveness of the promotion.

An inaccurate forecast is bad enough…

But what happens when you go share the forecast? In an ideal supply chain, a retailer
would build a demand forecast built on a single version of the truth. That forecast would
then be shared across the business and with suppliers to execute based on desired
outcomes and align with end-to-end supply chain objectives. However, when forecasts
are built with mistakes or omissions it causes a ripple effect throughout the retail
organization and its partners resulting in accurate plans, poorly executed promotions,
and strained relationships with suppliers.

Today, retailers and suppliers must be more aligned than ever to ensure that any
disruptions in the supply chain don’t result in the issues we endured in 2020. However,
if forecasts for promotions cannot be effectively and accurately shared with suppliers,
disconnects will occur and the risks of over or under-stocking for the promotion grow
exponentially.

The Solution

Be certain that your prospective demand forecasting solution can respond to any
combination of recurring events – such as school breaks, holidays, sporting events
– and unexpected disruptions – such as weather, economic and health events – in
an automated way, removing human intervention and vastly increasing accuracy.

AI plays a critical role by recommending the best possible forecasts for events –
expected and otherwise – based on more robust modeling, machine learning, and
business rules. Because retailers have billions of data and decision points to consider,
AI is truly the only way to seamlessly and quickly address complexity by identifying
patterns to analyze and diagnose complex problems with accuracy that far exceeds
human capabilities.

The benefits of AI and machine learning:

 Machine learning takes forecasting to a new level – It constantly updates the

models in real time with additional data feeds that continuously refine the
forecast accuracy and optimize trade spend.
 AI performs many of the backend/administrative tasks typically done by
individuals (or worse that are not currently done because of the amount of time
and effort it takes today). For example, AI continuously monitors internal and
external data sources for signals that provide more granular alerts or prescriptive
recommendations at an item or store level – empowering retailers to course
correct more quickly.
 By providing a single version of the truth in near real-time, AI enables retailers
to confidently share accurate and up-to-date forecasts across the enterprise and
with suppliers. This results in faster reaction times to shifts, better executed
promotions, higher levels of collaboration and stronger relationships across the
entire supply chain.

Learn more about effective promotions demand management

Read part 1 of the series: Is your demand forecasting solution working for you or are
you working for it?

Read part 2 in the series: Are your demand forecasting systems connecting all
categories across the store?

Read part 3 in the series: Why demand forecasting must be effective with all channels to
be effective with any

Read part 4 of the series: Avoiding the ‘blindside’: Inventory visibility and the agile
supply chain