You know that feeling when you open your closet and find it crammed with clothes you never wear? Well, that’s a bit like how traditional inventory management works. Imagine you run a retail store, and you’re stocking up on products, hoping they’ll fly off the shelves. But often, they don’t. You’re left with piles of unsold merchandise, and guess what? That’s money tied up in items that are just taking up space.

Now, let’s get down to some facts. According to a study by The Retail Owner, excessive inventory can gobble up a whopping 25-32% of your operating expenses. That’s a pretty penny, right? So, what’s the solution? It’s all about reducing inventory intelligently.

Traditional inventory management often relies on guesswork and gut feelings. You order products based on your instincts or past experiences, and sometimes, those instincts lead you astray. Imagine ordering a mountain of hot chocolate, soup, or baking ingredients products, only to have an unseasonably warm winter. Oops! Now you’re left with a load of unsold products gathering dust.

In fact, according to RTS food wastage across retail stores is as high as 30% contributing to inventory write-offs, due to the inability to sell items at full price. Yikes, right? That’s where reducing inventory with the help of AI-powered replenishment optimization comes into play.

Learn more about the problem with current forecasting frameworks.

Picture this scenario: You’re a customer, excited to purchase a specific product online. You head to your favorite e-commerce site, only to find that it’s out of stock. Frustrating, isn’t it? Now, flip the script. You’re the business owner, and your customers are experiencing these out-of-stock woes. It’s not a good look.

Did you know that 42% of shoppers will head to a competitor if an item they want is out of stock? That’s nearly half of your potential sales walking out the door! This is where AI steps in to forecast inventory demand prediction accurately and replenish your stores, ensuring you don’t run out of popular items while reducing inventory of slow-moving ones.

Imagine you run a small warehouse. It’s cozy, but not spacious. Traditional inventory management might fill it to the brim with goods, leaving little room to move. But then you receive a large order, and suddenly, you’re playing a game of warehouse Tetris, trying to fit everything in. It’s like trying to squeeze one more sweater into an overstuffed suitcase—it just won’t work.

In the world of warehousing, every square foot is valuable real estate. Did you know that optimizing your warehouse space can lead to a 20-50% reduction in carrying costs? That’s more room for your team to work efficiently and less clutter to navigate. Retail inventory optimization solution can help you achieve this while reducing inventory to just what you need.

Traditional inventory management can be a real headache, causing financial losses, out-of-stock nightmares, and space constraints. It’s like trying to find a needle in a haystack without a magnet. But don’t worry! The solution to these challenges lies in embracing AI-powered replenishment optimization.

By reducing inventory intelligently, you can save money, meet customer demands, and make the most of your valuable space. So, say goodbye to the guessing game and hello to a smarter, more efficient way of managing your inventory.

Learn why your replenishment optimization framework might be ineffective.

If you’ve been in the game long enough, you know that juggling inventory can sometimes feel like trying to solve a Rubik’s Cube blindfolded. But what if I told you there’s a magical tool in town that’s transforming the supply chain landscape? Enter AI-powered replenishment – the real game-changer for supply chains!

In the good ol’ days (well, not that good), managing inventory was like trying to predict the weather in a tropical rainforest. You could have too much, leading to wasted storage space and cash tied up in goods. Or you could have too little, risking lost sales and angry customers. It was a real Goldilocks situation – finding that “just right” level of inventory was a constant headache.

But wait, cue the superhero music because here comes AI to the rescue! Artificial Intelligence, the tech marvel that’s shaking up industries left and right, has set its sights on the supply chain. It’s like having a super-smart sidekick who’s amazing at predicting what you need, when you need it.

Imagine a solution that powers your category planners to effortlessly generate thousands of precise replenishment planning solutions for each store, category, and channel with just a click of a button.

Demand forecasts that feed into your replenishment planning are based not just on historical sales data but also on other influencing parameters: internal factors such as advertising campaigns and promotions, and external factors such as local weather and public holidays.

And the calculations are done at a much more granular level than standard systems are able to do: retailers can determine the effect of each parameter on each SKU in each store (and in each distribution center, where relevant) on a daily basis.

Moreover, order proposals are generated every 24 hours by intelligently taking into account supply-chain constraints such as supplier delivery times, expiration dates and minimum or maximum order quantities.

This isn’t just a utopian idea, but rather a concrete reality that retailers are rising to. Solutions such as Order Right are revolutionizing the way retailers plan replenishment.

You know that feeling when you walk into a store, and there’s an entire wall of unsold items that seem to have been gathering dust since the ’90s? That’s overstock, and it’s an inventory manager’s worst nightmare. AI helps you avoid this catastrophe by predicting exactly how many barbeque sauces you’ll need and when, reducing the chances of overstocking.

On the flip side, no one likes to tell a customer, “Sorry, we’re all out of that product.” That’s understock, and it’s equally cringe-worthy. AI’s got your back here too, ensuring you have just the right amount of inventory to meet customer demands and keep them smiling.

Picture this: your supply chain is as agile as a gymnast doing cartwheels. That’s the power of AI-powered replenishment. It adapts on the fly, responding to sudden changes in demand or supply chain disruptions. No more sweating bullets when a supplier’s shipment gets delayed or when demand spikes unexpectedly. AI has your inventory’s back, always.

Learn about the 9 best practices in replenishment planning every retailer must know.

In conclusion, implementing AI-driven inventory reduction successfully doesn’t have to be a daunting task. It’s all about getting your team on board, choosing the right AI solution, harnessing the power of data, starting small, training your team, embracing continuous improvement, and celebrating your wins. You’ve got this! Remember, reducing inventory is about working smarter, not harder. So, go ahead and take that first step towards a more efficient and cost-effective supply chain.

Learn more: Grocery Replenishment Has Evolved: 9 Things Every Retailer Must Know

Replenishment planning is a crucial aspect of grocery retail. It involves ensuring that shelves are stocked with the right products in the right quantities at the right time.

In today’s dynamic market, demand planners and supply chain managers have to deal with a new set of challenges such as volatile demand, supplier unpredictability, missing historical data, and various supply chain disruptions.

Moreover, they still need to do their everyday job – planning and balancing inventory across stores for all SKUs, meeting their customers’ expectations, and outperforming competitors.

Before the pandemic, demand and supply planners were accustomed to using reliable historical sales data. It was the same data showing similar patterns and seasonal trends year after year. Further, consumer behavior and the supply chain itself was rather predictable. Suppliers’ lead time was more or less stable. All of this made demand and supply chain planning much easier than it is now.

Nearly 90% of North American grocery shoppers say they have changed their shopping behaviors in some way since the pandemic began. – Mckinsey Survey

The pressure to maintain availability across stores, categories, and channels despite these challenges forces managers to look for new solutions, such as AI-powered ones, to help them play by these changing rules and succeed in this new reality.

In fact, according to Gartner, 60% of Chief Supply Chain Officers are expected to make faster, more accurate, and consistent decisions often in real time.

The traditional approach to replenishment planning involves manual forecasting based on historical sales data, which can lead to inaccurate demand forecasts and overstocking or stockouts.

Further, replenishment plans are typically manually modified to accommodate supply chain factors such as lead time, minimum order quantity, etc.

However, with the current unpredictability of demand and supply chains, such an exercise can easily become error-prone leading to larger problems like unforeseen stock outs and increasing inventory costs.

This is where Artificial Intelligence comes in.

The use of automation technologies such as artificial intelligence (AI) is expected to increase significantly in the next few years, with the potential to improve efficiency and reduce costs – Mckinsey State of Grocery Report

With AI-powered replenishment planning solutions, grocery retailers can now optimize inventory levels and reduce waste, thereby improving profitability and enhancing customer experience.

One of the key benefits of AI-powered replenishment planning solutions is their ability to provide accurate demand forecasting.

By analyzing historical sales data, current trends, and other factors (even weather patterns), these solutions can predict customer demand with a high degree of accuracy. This enables businesses to order the right amount of inventory, reducing the risk of overstocking or stockouts.

Another advantage of AI-powered replenishment planning solutions is their ability to optimize inventory levels.

By analyzing demand forecasts and other data, these solutions can identify which products are selling well and which ones are not. This enables businesses to adjust their inventory levels accordingly, reducing waste and improving profitability.

AI-powered replenishment planning solutions can also help businesses manage their supply chain more efficiently.

By automating many of the processes involved in ordering and receiving inventory, these solutions can free up staff time and reduce the risk of errors. This can result in faster turnaround times, more accurate order fulfillment, and improved customer satisfaction.

In the grocery industry, replenishment planning is especially important due to the perishable nature of many products.

AI-powered solutions can help businesses manage their perishable inventory more effectively, ensuring that products are sold before they spoil. This can reduce waste and improve profitability, while also ensuring that customers have access to fresh, high-quality products.

Therefore, implementing a replenishment planning solution powered by AI is becoming increasingly essential for grocery retailers to streamline their operations and stay competitive.

ADA Global’s Order Right is one such solution that leverages AI to provide grocery retailers with accurate demand forecasting, inventory optimization, and automated replenishment.

The solution uses hand-crafted ML-based algorithms curated specifically for retail to accurately predict demand at store, channel, and category level, and optimize orders to achieve category objectives and reduce supply chain costs.

The outcome: accurate, adaptive, and effective order plans every time in just a few clicks.

While marketing, merchandising, and buying take the center stage when one talks about retail planning and operations, what gets relatively less attention is the store replenishment optimization process.

How effectively you manage your store replenishment ultimately decides whether the product reaches the customer when she needs it. According to an estimate, it costs retailers over $1 trillion in lost sales due to stockouts. Between 70 and 90% of stockouts are caused by poor shelf replenishment planning solutions practices.

On the contrary, high inventory causes excessive inventory obsolescence, pilferage, and higher expenditure on maintenance, insurance, and taxes. The annual additional cost of holding excess inventory can be as high as 32%. In addition, excess inventory leads to margin erosion and increasing advertising costs.

As you might have guessed, no retailer can afford to ignore store replenishment processes as it has a major impact on profitability and sales. Building an effective and accurate replenishment optimization process improves sales and reduces store and supply chain costs.

Here are the top 5 reasons why your store replenishment planning might be ineffective.

For a large part of the retail era, demand planning based on historical data and human expertise has proven to be very effective. However, in today’s era, the demand complexities have increased manifold leading to elevated levels of forecasting errors. A major cause of this is the static one time forecasting framework that many retailers still use.

One of the best forecasting practices today is to build separate long-term demand planning and short-term demand sensing capabilities.

Demand sensing uses a range of dynamic demand predictors to forecast in the near term. It includes exogenous factors such as weather, temperature, holidays, etc. as well as internal factors such as promotions, pricing, inventory, etc. It usually uses ML-based algorithms to predict real-time demand. One such solution is ADA Global’s Order Right.

Although demand sensing and planning have different purposes, their relationship needs to be dynamic. For example, demand sensing capabilities can help you know well in advance when your long-term forecast is erroneous and accordingly offset it. Such an activity performed over time reduces the overall forecasting error and could potentially help you maintain high availability while reducing costs.

Demand forecasts can be course-corrected based on actual demand with demand sensing capabilities

Trends such as omnichannel, price, and convenience sensitive consumers and short product lifecycle have completely disrupted the retail scene. Today, every store, every channel, and every category behaves differently. One of the biggest mistakes that retailers make is treating them the same. This often leads to inconsistent experience for customers across channels and stores.

For example, even though your store might have enough supplies, an out-of-stock message on your site can put a serious damper on customer experience and may even result in lost sales.

In fact, there’s a 91% chance dissatisfied customers won’t do business with your brand again. Therefore, your retail replenishment software strategy should consider these nuances to be effective.

Ask any store manager and they would tell you that what happens on the shelf ultimately decides store success. Nothing is more excruciating for a customer than to see empty shelves. One of the main reasons why it happens is because of the dynamic effects that play in your store.

For example, a promotion for one product can lead to decreased (Cannibalisation) or increased sales (Halo effect) for other products. Promotions is just one aspect. There are several more such as product placement, visual merchandising, pricing, new product launch, and more.

While your store managers are smart to figure out some of them, they might not have the bandwidth to keep a tab on these effects every time they happen. Hence, what is needed is a systemic approach to identifying these effects and course correcting in your ai replenishment plans.

Planning is just half of the puzzle, the other half is the execution! As any learned and experienced supply chain expert would tell you, it’s all about the theory of constraints and most importantly economics.

Even if your replenishment planning is very accurately mapped to demand, it needs to be optimized for supply chain factors such as lead time, minimum order quantity, shelf life, expiration date, etc. This not only helps you meet store demand but also reduce costs such as shipping and handling costs, inventory optimization, ordering cost, shrinkage, etc.
Increasingly, retailers want to automate this process because of the complexities involved and the manual calculations required to get it right.

According to research, about 10-30% of stock outs happen due to supplier shortages. One of the major reasons why it happens is because of lack of transparency and collaboration between retailer and vendor.

Most retail firms have realized this gap and are proactively working to create a unified supplier collaboration platform similar to Vendor Link that would integrate all vendor processes and enable seamless data sharing for better outcomes.

What this results in is a lack of collaborative planning and mutual trust leading to low fulfillment rate, longer lead times, and vendor dissatisfaction.

Most retail firms have realized this gap and are proactively working to create a unified platform similar to Vendor Link that would integrate all vendor processes and enable seamless data sharing for better outcomes.

Also read: AI-Driven Replenishment Planning: A Game-Changer for Retailers

In fact, retailers who improved their retail vendor collaboration cited a 20% increase in revenue.

Fragmented vendor collaboration and data sharing

1-click Intelligent Replenishment

Retail companies, especially with a large number of SKUs, need to relook at their replenishment strategy. One of the most effective ways of achieving accurate, efficient, and cost-effective automatic store replenishment is with the help of a demand-driven and business operations tailored system.

However, given the breadth and depth of categories that need to be managed, and supply chain complexities in today’s era, manual ordering has become very inefficient and expensive.

Therefore, there is a need for “a layer of super-human intelligence on top of existing ERP systems that optimizes store replenishment to account for complex demand patterns, while reducing supply chain costs and markdowns”. One such solution is ADA Global’s Order Right.

Order Right builds a layer of Artificial intelligence on top of your existing planning tool and optimizes your store replenishment by making smart ordering suggestions to reduce out of stock, improve margins, and cut down wastage.

It uses a library of ML-based algorithms curated specifically for retail scenarios to accurately predict inventory demand prediction at store, channel, and category level, and optimize orders to achieve category objectives and reduce supply chain costs.

Download Order Right Brochure here or schedule a demo.

1. Point Of View: Does AI Really Improve Retail Planning?
2. Grocery Replenishment Has Evolved: 9 Things Every Retailer Must Know
3. 9 Best Practices in Demand Forecasting for Grocery Retailers

Demand and supply planning are often seen as the core activities for a retail organization. Simply put – it is all about placing the right product at the right place at the right time.

The planning that goes behind ensuring it is very complex and mostly manual. Most organizations rely on their category management and demand planning teams to make the right decisions such as what to put, in what quantities, at what time and where – consistently over time.

According to Mckinsey, applying AI-driven forecasting for retail planning can reduce errors by between 20 and 50%. That translates to a reduction in lost sales and product unavailability by up to 65%.

That is a significant value that retailers stand to miss out if they don’t adopt AI-driven technology in retail planning. While several retail leaders have wholeheartedly accepted AI as a strategic enabler for retail planning, many still believe that they are not ready.

“Too many companies still rely on manual forecasting because they think AI requires better-quality data than they have available. Nowadays, that’s a costly mistake.” – McKinsey

In this piece, we ask our expert Sankha Muthu Poruthotage to cut the clutter and tell us how AI translates to value on ground and who stands to benefit from it.

Sankha has decades of extensive experience in data science and ML engineering. He has spent the last several years of his career creating intelligent retail products by embedding ML algorithms to retail functions. At Ada Global, he plays the dual role of a product management leader and a consultant to clients.

Well, if you look at it broadly, the challenges can be categorized into two. Retailers obviously want to have more customers buying from them, and they want them to spend more money. It is all about increasing the market share and wallet share. So the challenges most retailers face revolve around customer acquisition, customer retention, upselling, and cross selling.

On the other side of the spectrum, you have the merchandise and supply chain optimization challenges. While getting customers to the store is the first challenge that retailers face, being able to serve them is a much more complex problem to solve simply because there are too many moving parts not under complete control.

The recent pandemic has exacerbated the situation as consumer behavior and preferences have irrevocably changed. Retailers today face complexities in several dimensions such as omnichannel retailing, value-oriented and convenience obsessed customers, new and fresh product launches, and volatile demand patterns.

As a result, retailers today are struggling to achieve optimal assortment, floor plans, replenishment planning solutions, and inventory plans with the pre-pandemic methods.

It is estimated that globally around $500 billion is lost due to wastage in retail. Wastage happens due to excess stock. On the other end, you have Out of Stock (OOS) which results in revenue losses and customer dissatisfaction. This is estimated to be even higher than the wastage at around $1 trillion annually in direct loss of sales.

There is an immediate impact on the P&L if OOS and wastages can be minimized. It can be as high as 10% increment on the operational profit. What most retailers realize is that these two are the biggest challenges in retail planning, and whoever aces this juggling act between the two extremes will eventually win the race.

AI is usually associated with cognitive abilities such as vision and voice. However, the underlying algorithms such as artificial neural networks and machine learning models can be used for many other use cases such as time series forecasting. Infact AI/ML models are proven to be very effective in areas such as demand forecasting.

The other main advantage of AI/ML models is that they can bring complex associations into light. I’m talking about pricing, promotions, events, weather, and even macro factors such as unemployment or consumer spending.

Once you have a good grasp of demand and how it reacts to these factors, it can lead to better optimal discount, promotion, and store replenishment strategies. Of course it needs a layer of optimization on top of forecasting which is very important to make things operationalized.

I’ll provide a simple example. A retailer and a supplier typically have a contractual agreement on the minimum order quantity. Hence, to make things operationalized, this parameter needs to be considered in the optimization layer. It is important to bring in the business parameters to automate these critical business functions.

I think most retailers with medium to large operations stand to benefit. However, in general, retailers who deal with perishable items will see greater benefits due to obvious reasons – they need to be more agile and accurate than others.

In my experience with clients, the ROI for demand planning solutions is very tangible. Our customers have seen almost instant improvement in metrics such as availability and wastage by using the solution.

As I mentioned earlier, combined impact on the P&L can be as much as 10%. And the investments are typically a fraction of it. So the return starts within a matter of a few months.

The last two years have exposed many gaps in businesses, and this was especially true of demand and supply chain planning. Many retailers remain unprepared to address challenges such as frequent out of stocks, increasing inventory optimization costs and wastage that come with fresher newer products, omnichannel retail, and shifting consumer behavior.

Ada Global’s Forecast Right and Order Right have helped major retailers leapfrog to an intelligent, adaptive, and agile demand forecasting and automatic store replenishment framework that simply works, every time.

Forecast Right is an easy-to-use intelligent demand forecasting solution created specifically for grocery retail demand and supply chain planners. Its robust and AI/ML powered framework helps planners go granular and capture channel-store-category nuances in their forecasts, avoiding the trap of “one-size-fits-all” associated with some of the existing solutions in the market.

Order Right is an intelligent replenishment optimization solution that helps category managers generate accurate SKU-level order plans every time. It consumes accurate demand forecasts from Forecast Right and, unlike many existing solutions in the market, optimizes order plans for supply chain constraints and parameters such as MOQ, lead time, replenishment frequency, etc. using advanced AI/ML techniques. It also powers users with advanced features such as future stock predictions, day zero predictive alerts, and retail replenishment software risk-based order planning.

Also read: Navigating the Beauty Maze: AI’s Role in Retail and Supply Chain Planning

Learn more about Algnonomy’s Forecast Right and Order Right.

Current business scenarios are proving that companies that plan for both best- and worst-case circumstances are the real winners.

In recent times, we’ve seen that well-prepared companies were the ones able to ride out the troughs and crests caused by the pandemic, an unprecedented geopolitical climate, and booms and busts of the stock market.

These companies were able to do so because they had a strong and efficient supply chain intelligence in place, one that could adapt to any kind of scenario and handle seemingly insurmountable challenges. They couldn’t have done it without careful planning and disaster preparedness in the supply chain and retail logistics.

What happened to those companies that weren’t well-prepared? Take the biggest disruption that happened in 2020 — that of the COVID-19 pandemic. The fallout was the huge impact on supply chain planning and scheduling, which up to then were well-oiled functions for companies.

In the aftermath of the pandemic, companies found themselves grappling with disruptions in the movement of goods and availability of raw materials, making it difficult to meet production demands. Most were compelled to move from the brick-and-mortar model to online platforms.

Suddenly, all companies, especially retailers, had to stop relying on historical data to engage in supply chain forecasting. Instead, they had to align themselves with changing customer demand. That’s when they realized that flexible supply chain planning was key to responding to business demands brought on by uncertain times.

This lesson has led businesses to focus on reviewing and revamping their supply chain planning capabilities to do contextual commerce. An example is autonomous supply chain planning enabled by artificial intelligence, which helps companies to correct situations on their own by managing fluctuating demand and realizing maximum value from the data provided by digital analytics tools.

Autonomous supply chain planning draws on advanced technologies such as machine learning and AI, wiring together huge amounts of data points to generate useful insights. It ties in historical data with current supply and demand to arrive at a better understanding of market needs. And it allows companies to fulfill dynamic customer requests resulting from fluctuating market conditions.

Apart from inventory forecasting, the system also enables companies to benefit from time and cost savings. Data-based reports and planning can help track supply chain performance over time, and find ways to enhance supply chain operations and keep associated costs as low as possible.

AI has several use cases and applications in the retail supply chain:

• Recognize and understand all opportunities and threats across the supply chain. This can be done by having an end-to-end supply chain perspective that’s not just objective-oriented, but also gives an appropriate response to the situation.
• Gather and interpret data in real time so that stock replenishments become timely.
• Employ the data to mitigate service-level failures and tackle challenges before they snowball into big issues.
• Efficiently use the autonomous supply chain, which offers a single and updated forecast. This eliminates inconsistencies between supply and demand, as well as the standard “out-of-stock” answer that eats into sales.
• Apply AI and ML to the company’s most critical supply chain functions, such as forecasting and inventory management, to realize higher and faster return on investment.

Supply chain autonomy is a catalyst for the retail sector to achieve cost controls and realize higher profit margins. This involves a gradual adoption process and isn’t always an overnight transformation. What’s crucial here is partnering with a company that can provide the full range of supply chain automation services, and support retail companies in accessing the power of autonomy in today’s digital-first world, to achieve last-mile efficiencies and delight customers.

This article was first published on SupplyChainBrain.

Download this article as a PDF

Grocery retail supply chains are getting more complex and unmanageable with traditional forecasting models. Matching supply with demand for a broad inventory that includes fresh and short shelf-life products on one end and ambient products on the other is not easy. Add to that the complexity that arises due to changing consumer behavior, who have started to incline towards convenience and price over brand loyalty. Yet traditional demand forecasting is still heavily reliant on constant monitoring and intervention from a supply chain expert.

Accurate and agile demand forecasting lies at the center of grocery retail’s customer-centric yet lean approach. Doing forecasting right has far-reaching benefits:

• You reduce your wastage by better inventory demand prediction planning
• Your displays look attractive and dynamic
• Customers get fresher goods
• You sell more by placing your product at the right place at the right time across channels

So, let’s look at nine secrets to improve your demand forecasting and take it to the next level.

With price sensitivity and convenience changing the way consumers shop, the demand for products has become much more volatile and difficult to predict with simple models. It has therefore become imperative for grocers to enrich data and not simply rely on traditional data. For accurate forecasting, it’s crucial to account for external factors such as weather, holidays, events, social media, and news as well as internal factors such as promotions, advertising, visual merchandising, etc.

With a huge range of internal and external causal variables affecting sales, every store, channel, and category combination behaves differently. One of the biggest mistakes that grocers make is to force-fit models without understanding the nuances that are at play.

In a multivariate framework, it is very difficult and cumbersome to determine the importance of each factor manually. ML algorithms, however, can help to sift through data and determine the effect of each factor. This can then feed in as an input for the planner to generate granular and accurate forecasts.

While forecasting sales of products, there is a slim chance that you will find a silver bullet algorithm that works for all products, locations, and situations. Therefore, champion grocers go the extra mile with an ensemble of algorithms that is customized based on the data. This ensures that grocers avoid over-fitting of models across product lines and achieve greater overall accuracy.

From fresh goods wholesalers to grocery retailers, from high-end to price-driven supermarkets, convenience stores to cash-and-carry chains, it is clear that replenishment optimization teams walk a tightrope between spoilage costs and shelf presentation. This makes it important to get the balance right every time.

Error functions such as RMSE and MAD are powerful tools that can be used to select the best model by analyzing the prediction error. Such methods are indifferent to over-forecasting and under-forecasting. However, depending on where the product lies in the fresh to ambient spectrum, these functions can be tuned to treat over-forecasting and under-forecasting differently based on the business requirement and impact.

What should be your forecasting accuracy? Should it be above 95%? Or 99%? The correct answer to this question is not so simple.

Most forecasting techniques aim to achieve the highest accuracy levels, giving very low importance to business outcomes. Tying your forecasting to outcomes such as reducing wastage, overstocking, or increasing availability has helped several leading retailers achieve great success even with forecasting accuracy as low as 70%.

While managing stocks at grocery stores, it is critically important for store managers to respond to what is happening on the shelf. For instance, a new product launch could lead to secondary effects on the demand for other products, which could range from an overstock situation in case of cannibalization to understock in case of multi-buy discounts. For true agile operations, business users should be able to swiftly identify and plan for such situations on a daily basis without the need of technical support.

Events that cause a secondary effect on other products:

• Multi-buy discounts
• Price change
• Promotions
• Advertising
• Change in in-store display
• Product launches and discontinuation
• Macro-level scenarios such as weather, local events

The effect of promotions of products via price discounts, advertisements, display changes, etc. on the supply chain is one of the least studied topics but has huge implications. For example, the promotion of one product may have significant effects on the sales of other products that are not in promotion. Not accounting for this effect leads to suboptimal retail inventory optimization solution and ill effects like increase in spoilage or overstock. Promotion forecasts can go a long way to satisfy the increase in demand while mitigating the ill effects.

With increased new product launches, fresh products, and increasingly complex channels, sparse and noisy data is a recurring theme across grocers worldwide. If you regularly face the roadblock of not having enough quality data for your planning needs, then it is time to look for a solution. Invest in a forecasting framework that uses data science techniques to deal with sparse and noisy data with ease.

Irrespective of you taking a top-down or a bottom-up approach to your demand planning, you will eventually have millions of demand forecasts at the SKU-store level. This planning is getting even more unmanageable due to changing consumer behavior and channel factors. Therefore, top grocers realize the importance of making sure that the system is scale-ready, both from a technical and user experience point of view.

In the ever-evolving, dynamic, and volatile grocery retail, your demand sensing and forecasting framework needs to be intelligent, agile, and scalable to be able to deal with the above-mentioned challenges. One such solution is ADA Global’s Forecast Right.

Forecast Right uses proprietary ML-based multivariate and algorithmic techniques to accurately and adaptively forecast demand. It is 100X faster and scalable than traditional forecasting solutions – 5-clicks is all it takes to generate 1000s of granular forecasts. Its proprietary AI provides tailor made feature engineering and model selection for demand forecasting and has a track record of improving forecast accuracy for over 90% of SKUs.

The output of a solution like Forecast Right can be plugged into various use cases. One such use case is replenishment planning solutions. Powered by Forecast Right, ADA Global’s Order Right generates accurate SKU-level order plans for even the most challenging categories – from fresh and seasonal to new and promoted products with ease. It does so by leveraging proprietary optimization algorithms that constantly monitor stock balance, sales and demand predictions while accounting for constraints such as shelf-life, lead-time, expiration date, minimum order quantity, minimum display stock, and automatic store replenishment constraints.

Also read: How Machine Learning Improves Retail Demand

Learn more about ADA Global’s Forecast Right and Order Right.