Food waste occurs at all stages of the value chain: from production until it reaches consumers’ homes. This is why, to reduce food waste, global plans must be implemented that incorporate all the actors involved.

Worldwide, it is estimated that more than 1/3 of the food produced is wasted for several reasons. ReFED Insights Engine studies show that, in the United States, households are responsible for 37% of waste, followed by restaurants and retailers, with 29%; farms, 21%; and finally, production, with 13%.

It is clear that retailers have a relevant role to play in this fight. However, the balance between managing an optimal inventory and presenting a varied and attractive product mix to consumers is a constant challenge. The equilibrium becomes even more complex for those who handle low shelf-life products, such as supermarkets and convenience stores. Today, there is also the need to consider climate change-conscious consumers, 45% of whom consider reducing food waste a priority, according to the retail data science company, 84.51°.

More than a requirement, meeting this challenge becomes an opportunity. Through their contribution, retailers will be able to make a positive impact while reducing their carbon footprint and improving their profitability. Here are some initiatives that can be implemented to do their bit.

1. Increase accuracy in demand forecasting: Maintaining an attractive display for customers usually involves keeping shelves full and stocked. The easiest way to achieve this is to maintain inventory levels higher than strictly necessary. However, overstocking carries the risk of having an excess product that ends up deteriorating and going to waste. The recommendation is to periodically evaluate surplus inventory and continuously adjust it, to have the right amount of product at every moment.
2.  Implement expiration projection systems: one of the leading causes of food waste in retailers is product expiration. Items are lost because their expiration date has passed and can no longer be sold. Retailers can implement expiration projection analytical systems that will alert the stores about soon-to-expire products so that they can manage them, for example, through discounts.
3. Train store staff: Some leading-edge retailers have defined protocols to reduce waste, such as not restocking prepared food products near closing time and allowing them to sell out. But this rule will not be respected if employees are not aware of it. Unfortunately, retailers face a staff turnover rate of over 60%, according to the NRF, making it challenging to implement and maintain food safety, storage, and product management protocols. Therefore, an additional effort should be made to ensure that all personnel has up-to-date knowledge of the protocols, thus improving in-store products’ handling and management and effectively reducing waste.
   On the other hand, specific courses during the onboarding process can support food waste awareness. This way, staff will have a greater connection and understanding of the problem, increasing their commitment to the solution.
4.  Act before discarding: Retailers have several options for managing soon-to-be-expired products before deciding to dispose of them. They can, for example, sell old or slightly damaged products at a discount; establish partnerships with organizations to donate surplus, or have partners for composting food scraps. Each retailer can define its own processes to extend the useful life of products and avoid waste. But as mentioned above, an essential element of their effectiveness will be how management protocols are implemented so they do not remain only on paper.
5. Conduct waste audits: despite the efforts made, imponderables can always occur and limit their effectiveness. Measuring to manage is part of the solution. It is essential to record each case and analyze the root causes of food waste to identify excess patterns or management problems affecting the results. Defining standards, KPIs, and responsible parties will provide structure to drive a continuous improvement process.

Some of these initiatives may be more or less complex to implement. The good news is that today there is a wide range of technological solutions that make it possible to accelerate and optimize the process through different initiatives.

The effort is worth it. At Frogmi®, we have seen retailers reduce their food waste by 17% using our SKU-level task management solution, which allows them to automate task creation to manage soon-to-be-expired products and prevent waste. As an application, all information is digitally consolidated and available for analysis, management, and decision-making, supporting continuous improvement processes.

We have seen how the world is turning its efforts to reduce food waste. Now retailers have the tools and technical support to do their part.

Phantom inventory is one of the most complex problems to deal with for retailers because, as the name implies, it is challenging to discover. There is no single root cause or an identical manifestation between stores to identify it. Sometimes it presents itself as product availability errors, as the system indicates that the store has stock, even though no physical units are available. Other times, a stockout is alerted when in fact, there is none.

While retailers try to balance assortment variety in their stores with optimal inventory management, the discrepancy between physical and recorded stock can lead to significant complications. Considering that every time a customer faces a stockout, there is a 40% chance that the store will perceive a direct loss, it should come as no surprise that studies by the Consumer Brands Association (formerly known as the Grocery Manufacturers Association or GMA) estimate a $50 billion loss from out-of-stock issues in North America alone between 2017 and 2018.

Retailers should also not forget that lost sales are only one of the consequences of phantom inventory, affecting inventory management, customer experience, e-commerce fulfillment, and decision-making. So, are retailers forced to take the impact without acting? How can retailers address this problem?

The answer is simple: data. Phantom inventory is hard to see, so the best way to identify it is to have data and analytics solutions that leverage artificial intelligence (A.I.) and machine learning (M.L.) development to see its signs or symptoms. Algorithms are fed with sales projections, inventory level, POS sales information, and more and can determine if any product presents an anomalous behavior. An anomalous sale would be, for example, having sales of a product registered as out of stock; or not having sales of alcohol gel in the middle of the pandemic if there is stock available. Thus, the probabilistic analysis of the models will be able to raise alarms when there are signals that suggest anomalies.

The critical point for effectively managing phantom inventory comes after identifying abnormalities. The retailer must ask itself what to do with this information. What action to take now that they know that some product’s sales or turnover are not behaving as expected. We are talking about converting the data into action, into concrete activities that can effectively solve the problem on the sales floor.

In our experience, the best way to get the information down to the stores is in the form of product-specific tasks. Frogmi® offers a task management solution at SKU level, which can automatically trigger tasks against A.I. alerts for the store to check the product’s status. For example, a task can be sent to audit the product’s condition, answering some basic questions: Does it have enough stock? Are the products in good condition (undamaged, not expired)? Is it displayed correctly, following the planogram guidelines? Does it have a price tag? Is the price correct? And, if a problem is found, a new task is automatically triggered to provide the solution.

Effective phantom inventory management goes beyond traditional inventory management. It is a verification of all product’s commercial variables that will help retailers ensure shelf availability and validate that the protocols and standards defined by the company are being met. We are actively reducing the gap between what is planned and executed in every store for each item. In this way, customers will be able to find the products they are looking for, when they need them, and in the best condition, improving the shopping experience and ensuring sales.

Inventory is one of the retailers’ most significant assets, so it should not be a surprise the number of resources dedicated and technology developed for its optimization, such as software, artificial intelligence, and machine learning tools for demand forecasting and supply chain optimization.

However, despite all these efforts and the growing sophistication of inventory management systems, there is still an Achilles heel that no retailer has been able to overcome: phantom inventory.

Phantom inventory refers to goods that appear in the inventory system but are not available for sale, either because they are lost in the back room, out of display in the store, or simply no longer physically exist.

Phantom inventory is exceptionally costly and significantly affects retailers’ bottom line, as it essentially prevents products from being available to customers. But that’s not all. Phantom inventory also hurts inventory management, demand forecasting, online sales, analysis, and decision-making capabilities, to name a few. This blog will present the consequences of having phantom inventory problems for retailers.

Loss of sale

Loss of sales is the most obvious effect of phantom inventory since you cannot sell a product that is not physically available to the customer.
Phantom inventory generates a decrease in shelf availability, making it impossible for customers to find the products they are looking for. Studies show that when a customer faces a stock-out, they may decide to substitute a similar item, switch brands, choose to shop at another store or abandon the purchase. Regardless of the decision, the retailer will be affected, receiving 2-3% direct sales losses depending on the category.

Inventory management

As we have seen, one of the origins of phantom inventory is the discrepancy between physical and system inventory levels. Let’s consider that according to the GS1 US Survey, the average retailer in the United States has an inventory pressure of only 63%. The chances of having phantom inventory are pretty high.
Beyond accuracy, phantom inventory generates a chain reaction, disrupting processes that originate from recorded data, such as automatic purchases based on reorder points. An imbalance between the two inventories (systemic and physical) can generate stock-outs when the lack of stock in the store is identified too late; or overstocking, in case the system has registered a lower quantity than the actual one.

Non-compliance in online sales:

The adoption of e-commerce is a reality that has accelerated in recent years, putting pressure on retailers facing the highest levels of competition.
Discrepancies between the systems and physical stock create havoc in meeting online demand.
According to Peoplevox’s E-Commerce Fulfilment Report, 34% of retailers have delayed the shipment of a purchase order because they mistakenly sold a product that was not in stock. Phantom inventory leads to accepting purchase orders that cannot be fulfilled because the inventory is not actually available in the store. If you don’t pay attention, this problem will only be identified when an operator notices that there is insufficient produce to fill the order. Thus, phantom inventory tricks retailers who find themselves unable to meet their customers’ expectations.

Poor information, analysis, and conclusions

The existence of phantom inventory is undoubtedly a problem of data, a discrepancy between physical stock and that recorded in the system. And as the saying goes: garbage in, garbage out. This means that when a retailer has a phantom inventory problem – and we have already established that it is very likely to have one – the analysis and conclusions drawn from this data will be compromised.
Phantom inventory can lead to misreporting sales under projections, leading the retailer to think that a promotion is not delivering the expected result, or a product was not as successful as thought. The sales team could be analyzing and concluding without knowing that the product was not in stock or that the promotion was never implemented because there was not enough merchandise, even leading to take actions in terms of product mix or promotional strategy.

On the other hand, incorrect inventory recording will affect the supply chain. Phantom inventory will distort sales, and consequent demand projections, since the system will show available stock that has not been sold when in fact, it is not displayed correctly or available for sale. Thus, the inaccuracy will be perpetuated in the future, affecting the following projections, sales plans, store performance measurements, and the replenishment system without even knowing it.

At Frogmi®, we know that phantom inventory is highly costly for retailers. Solving the complicated dilemma of keeping stock under control while delivering the best assortment and service level to customers is no easy task.
In our experience, an efficient solution to address phantom inventory is to support the operation with advanced analytics, artificial intelligence, and machine learning to identify deviations in product sales. Studying demand patterns at a granular level will make it possible to investigate the possibility of facing a case of phantom inventory. The information may be used to trigger alarms -or even better, targeted tasks- to perform a product’s field auditory and analysis.

Implementing these technologies together with a task manager at SKU level will improve inventory assertiveness, reduce stock-outs, ensure shelf availability, and consequently increase sales. Thus, retailers can begin to make decisions based on reliable information and improve their results by paying attention to the data and the in-store operation.

Let’s put ourselves in the following situation: an in-store walk-through.

The objective is to experience the store from the customer’s perspective to assess whether the standards defined by the company are met.

When walking down the aisles, it is impossible to avoid noticing empty shelves, locations that do not have enough stock, out-of-stock products generating dead areas, and others that cover more than the optimum, taking advantage of open spaces.

When checking the system, the inventory indicates that there is sufficient stock. Then, the replenishment of the product is coordinated since -theoretically- the backroom has enough inventory. It only needs to display it and make it available to customers.

However, the problem does not end there. When looking for the products, it is discovered that they are not there, there is no stock inside the store or in warehouses. This situation is called phantom inventory.

What is Phantom Inventory

Phantom inventory is inventory that does not exist in reality but appears to be in stock, like a ghost. Thus, the inventory system shows existing on-hand units, even though it is not actually in the warehouse or available on the shelf for the customer to see and buy.

These discrepancies between system information and reality can originate for several reasons, such as typing errors in the sale, carelessness in inventory receipt, and product shrinkage. But regardless of its origin, the detection and management of phantom inventory become complex since the system considers that the product is in stock, even though the store has no physical units.

The pain for retailers is evident when they believe that a product is available but – in reality – it is not, risking OOS and the associated loss of sales, as we saw in our previous blog. Another drawback of phantom inventory is its perpetuity. As the system indicates that the retailer has enough stock, the reorder point is never reached to restock, maintaining the situation over time. Thus, a pivotal act to break this vicious cycle is detecting signs of phantom inventory.

The symptoms of phantom inventory

To manage phantom inventory, the first step is to identify it and locate these gaps. However, as phantom inventory can originate for several reasons, it is difficult to detect the root cause for its management. That’s why retailers should focus on recognizing the visible symptoms, those that make the existence of phantom inventory evident.

One such symptom is stockouts. We have already seen that one way to recognize this symptom is to have eyes and hands in the store, spend time physically verifying where there are stockouts, and then check them against the system to identify an inconsistency in the inventory.

Considering that the average retailer handles around 16,000 SKUs simultaneously, this manual task can be challenging to tackle. In addition, it is clear that the larger the assortment, the greater the complexity of the job, making the management of phantom inventory uphill.

The second option for pinpointing symptoms of phantom inventory will be to rely on data analytics and artificial intelligence (A.I.) tools that can predict potential stock outs through analytical observation, identifying patterns and inconsistency in the data. There are three alerts that may suggest some deviation and phantom inventory risk.

1. Decrease in turnover: a decrease in the turnover of any SKU in respect to the normal or the projection.
2. Sales $0: the data shows that there are no product sales, despite having positive inventory. It can also be considered an alert when sales show anomalies concerning the demand projection.
3. Changes in sales trend: The sales pattern of a product changes abruptly, for no apparent reason.

One of the most significant advantages of using a data analysis system with A.I. and Machine Learning is that the algorithms refine the predictions as they are used. In this way, the alarms will become more and more accurate, improving the ability to diagnose phantom inventory.

What to do to treat your stores

Once the symptoms and products at risk of phantom inventory have been recognized, the hypothesis must be validated. Regardless of the method used (manual or through A.I.), a cross-check should be made between the system and total physical inventory (units displayed in the store plus backroom units). This evaluation will shed light on inventory disparities and where adjustments need to be made so that the system information reflects the store’s reality again.

At Frogmi, we know that managing phantom inventory is a complex process and one that must be performed constantly. Regardless of the methodology used to detect the problem, the solution involves manual in-store work to validate the possible inventory discrepancy. Our SKU-level task management solution is ideal for addressing this challenge from both methodologies, as it allows you to view information at the store-product level.

For example, a manual phantom inventory survey can be performed. One of the functions of Frogmi is the ability to generate tasks from a product (or the absence of it), which means that when stockouts are identified during a store walk-through, an automatic replenishment task can be created by simply scanning the product. If the area in charge of replenishment does not have enough units to replenish, a case of phantom inventory will have been found, enabling its immediate management.

On the other hand, if an A.I. system is used to alert phantom inventory, Frogmi can be easily integrated to generate automatic validation tasks specific to each store at SKU level. Thus, each store will have the opportunity to manage those products that behave atypically in sales or inventory turnover.

In our experience, the ideal plan of action is to use both tools simultaneously, facilitating the diagnosis of phantom inventory and decreasing the associated losses. This reaps the benefits of A.I. while empowering store personnel with self-management tools, improving inventory management, shelf availability, and, consequently, sales.

Analytics and data science offer opportunities to avoid stockouts

Source: www.freightwaves.com

Shoppers across the globe will likely be greeted by empty shelves or website stock-outs during the 2021 holiday season. It’s a perfect supply chain storm of increased demand and severely constrained supply and labor. Pent-up demand from the pandemic is leading to an increase in both online and in-store orders while Covid-19-related restrictions, combined with container shortages, labor and driver shortages, port congestion and railroad bottlenecks, have constricted supply like never before.

Retailers’ inventories are near a 30-year low and toymakers are urging consumers to shop months early for holiday gifts. Shipping costs have increased by over 300% compared to January 2020. An unprecedented number of ships are waiting to dock at Southern California ports. By the end of September, 73 container ships were anchored off California, waiting for a berth. U.S. President Joseph Biden announced on Oct. 9 that the Los Angeles port will operate 24×7 to clear the backlog, but even that is not going to be enough. There is no end in sight for any of these problems.

• More than 20% of supply chain executives are planning to reduce the number of SKUs in their product portfolio but are not sure of the overall rationalization strategy
• More than 45% of supply chain executives want to multi-source materials and expand their supplier base but lack an expansion plan
• More than 40% of supply chain executives aim to maintain a higher level of inventory for critical SKUs and reduce stock-out scenarios but have no visibility.

How can CPG firms deal with these unavoidable supply chain issues in the short term?

Interestingly, CPG companies that turn to data science and analytics will have a real advantage this season and beyond. Now is the right time for companies to bring in data science to address these issues, irrespective of their data journey. In most cases, companies have a better chance to succeed if they choose the right partner to help them with data science and analytics.

Following are 5 steps CPG companies can take in the immediate short term to deal with these ongoing challenges.

1.  Simplify product portfolio

CPG companies can decrease complexity within the supply chain by reducing product variations or discontinuing less profitable or high complexity SKUs. This involves 3 simple steps:

1. SKU classification: Classify SKUs by stockout possibility score (SPS). SPS is calculated at an SKU/store (or warehouse) level and depends on:
   • Whether the item is locally sourced or not
   • Predicted suppliers’ performance (based on past performance with respect to demand).
   • Suppliers’ risk score (financial, geopolitical, operational, number of suppliers)
   • Current inventory levels compared to forecasted demand (days of supply)

2. SKU segmentation: Segment SKUs based on profit versus the stockout possibility score. Calculate profit considering increased transportation and labor costs.
3. SKU rationalization: Discontinue SKUs in the high SPS and low-profit segments. Keep an eye on the SKUs with high profit and high SPS scores, then take immediate steps to reduce the SPS score of these SKUs.