Demand planning goes beyond simply forecasting product needs; it’s about ensuring your business meets customer demands with precision, efficiency, and cost-effectiveness. Latest demand planning technology addresses key challenges like forecast accuracy, inventory management, and market responsiveness. In this blog, we will introduce critical demand planning trends, including data-driven insights, probabilistic forecasting, consensus planning, predictive analytics, scenario modeling, real-time visibility, and multilevel forecasting. These trends will help you stay ahead of the curve, optimize your supply chain, reduce costs, and enhance customer satisfaction, positioning your business for long-term success.

Data-Driven Insights

Advanced analytics, machine learning, and artificial intelligence (AI) are becoming integral to demand planning. Technologies like Smart UP&O allow businesses to analyze complex data sets, identify patterns, and make more accurate predictions. This shift towards data-driven insights helps businesses respond quickly to market changes, minimizing stockouts and reducing excess inventory.

Probabilistic Forecasting

Probabilistic forecasting focuses on predicting a range of possible outcomes rather than a single figure. This trend is particularly important for managing uncertainty and risk in demand planning. It helps businesses prepare for various demand scenarios, enhancing inventory management and reducing the likelihood of stockouts or overstocking​.

Consensus Forecasting

Modern manufacturing is moving towards an integrated approach where departments and stakeholders collaborate more closely. Collaborative forecasting involves sharing insights across the supply chain, from suppliers to distributors and internal teams. This approach breaks down silos and ensures that everyone is working towards a common goal, leading to a more synchronized and efficient supply chain​.

Predictive and Prescriptive Analytics

Predictive analytics forecasts future outcomes based on historical data and trends, helping businesses anticipate demand fluctuations. For example, Smart Demand Planner (SDP) automates forecasting to adjust inventory and production levels accordingly​.

Prescriptive analytics goes further by offering actionable recommendations. Smart Inventory Planning and Optimization (IP&O), for instance, prescribes optimal inventory policies based on service levels, costs, and risks​. ogether, these tools enable proactive decision-making, allowing companies to both predict and optimize their responses to future challenges.

Scenario Modeling

Scenario modeling is becoming a key part of demand planning, enabling businesses to simulate different scenarios and assess their impact on operations. This method helps companies create adaptable strategies to effectively handle uncertainties. Smart IP&O enhances this capability by offering What If Scenarios that allow users to test different inventory policies before implementation. By adjusting variables like service levels or order quantities, businesses can visualize the effects on costs and service levels, empowering them to select the optimal strategy for minimizing risks and controlling costs​​.

Real-Time Visibility

As supply chains become more global and interconnected, real-time visibility into inventory and supply chain activities is crucial. Enhanced collaboration with suppliers and distributors, combined with real-time data, enables businesses to make quicker, more informed decisions. This helps optimize inventory levels, reduce lead times, and improve overall supply chain resilience​.

Multilevel Forecasting

This involves forecasting at different levels of the product hierarchy, such as individual items, product families, or even entire product lines. Multilevel forecasting is vital for businesses with complex product portfolios, as it ensures that forecasts are accurate at both the micro and macro levels​.

 

Demand planning is a decisive aspect of modern supply chain management, offering businesses the ability to enhance operational efficiency, reduce costs, and better meet customer demands. Leveraging advanced platforms like Smart IP&O significantly improves forecasting accuracy and inventory management, enabling swift responses to market fluctuations. Automated statistical forecasting, combined with capabilities like hierarchy forecasting and forecast overrides, ensures that forecasts are accurate and adaptable, leading to more realistic planning decisions. Additionally, with tools like scenario modeling, businesses can explore various demand scenarios across their product hierarchy, facilitating informed decision-making by providing insights into potential outcomes and risks. This approach allows businesses to anticipate the impact of policy changes, make better decisions, and ultimately optimize their inventory and overall supply chain management, staying ahead of key trends in the process.

 

 

 

In this blog, we will analyze the automatic forecasting for time series demand projections, focusing on key techniques, challenges, and best practices. There are multiple methods to predict future demand for an item, and this becomes complex when dealing with thousands of items, each requiring a different forecasting technique due to their unique demand patterns. Some items have stable demand, others trend upwards or downwards, and some exhibit seasonality. Selecting the right method for each item can be overwhelming. Here, we’ll explore how automatic forecasting simplifies this process.

Automatic forecasting becomes fundamental in managing large-scale demand projections. With thousands of items, manually selecting a forecasting method for each is impractical. Automatic forecasting uses software to make these decisions, ensuring accuracy and efficiency in the forecasting process. It’s importance lies in its ability to handle complex, large-scale forecasting needs efficiently. It eliminates the need for manual selection, saving time and reducing errors. This approach is particularly beneficial in environments with diverse demand patterns, where each item may require a different forecasting method.

 

Key Considerations for Effective Forecasting

1. Challenges of Manual Forecasting:
   • Infeasibility: Manually choosing forecasting methods for thousands of items is unmanageable.
   • Inconsistency: Human error can lead to inconsistent and inaccurate forecasts.
2. Criteria for Method Selection:
   • Error Measurement: The primary criterion for selecting a forecasting method is the typical forecast error, defined as the difference between predicted and actual values. This error is averaged over the forecast horizon (e.g., monthly forecasts over a year).
   • Holdout Analysis: This technique simulates the process of waiting for a year to elapse by hiding some historical data, making forecasts, and then revealing the hidden data to compute errors. This helps in choosing the best method in real-time.
3. Forecasting Tournament:
   • Method Comparison: Different methods compete to forecast each item, with the method producing the lowest average error winning.
   • Parameter Tuning: Each method is tested with various parameters to find the optimal settings. For example, simple exponential smoothing may be tried with different weighting factors.

 

The Algorithms Behind Effective Automatic Forecasting

Automatic forecasting is highly computational but feasible with modern technology. The process involves:

• Data Segmentation: Dividing historical data into segments helps manage and leverage different aspects of historical data for more accurate forecasting. For instance, for a product with seasonal demand, data might be segmented by seasons to capture season-specific trends and patterns. This segmentation allows forecasters to make and test forecasts more effectively.
• Repeated Simulations: Using sliding simulations involves repeatedly testing and refining forecasts over different periods. This method validates the accuracy of forecasting methods by applying them to different segments of data. An example is the sliding window method, where a fixed-size window moves across the time series data, generating forecasts for each position to evaluate performance.
• Parameter Optimization: Parameter optimization involves trying multiple variants of each forecasting method to find the best-performing one. By adjusting parameters, such as the smoothing factor in exponential smoothing methods or the number of past observations in ARIMA models, forecasters can fine-tune models to improve performance.

For instance, in our software, we allow various forecasting methods to compete for the best performance on a given item.  Knowledge of Automatic forecasting immediately carries over to Simple Moving Average, linear moving average, Single Exponential Smoothing, Double Exponential Smoothing, Winters’ Exponential Smoothing, and Promo forecasting. This competition ensures that the most suitable method is selected based on empirical evidence, not subjective judgment. The tournament winner is the closest method to predicting new data values from old. Accuracy is measured by average absolute error (that is, the average error, ignoring any minus signs). The average is computed over a set of forecasts, each using a portion of the data, in a process known as sliding simulation, which we have explained previously in a previous blog.

 

Methods used in Automatic forecasting

Normally, there are six extrapolative forecasting methods competing in the Automatic forecasting tournament:

• Simple moving average
• Linear moving average
• Single exponential smoothing
• Double exponential smoothing
• Additive version of Winters’ exponential smoothing
• Multiplicative version of Winters’ exponential smoothing

The latter two methods are appropriate for seasonal series; however, they are automatically excluded from the tournament if there are fewer than two full seasonal cycles of data (for example, fewer than 24 periods of monthly data or eight periods of quarterly data). These six classical, smoothing-based methods have proven themselves to be easy to understand, easy to compute and accurate. You can exclude any of these methods from the tournament if you have a preference for some of the competitors and not others.

Automatic forecasting for time series data is essential for managing large-scale demand projections efficiently and accurately. Businesses can achieve better forecast accuracy and streamline their planning processes by automating the selection of forecasting methods and utilizing techniques like holdout analysis and forecasting tournaments. Embracing these advanced forecasting techniques ensures that businesses stay ahead in dynamic market environments, making informed decisions based on reliable data projections.

 

 

 

In this blog, we will explore how organizations can achieve exceptional efficiency and accuracy with AI-driven inventory optimization. Traditional inventory management methods often fall short due to their reactive nature and reliance on manual processes. Maintaining optimal inventory levels is fundamental for meeting customer demand while minimizing costs. The introduction of AI-driven inventory optimization can significantly reduce the burden of manual processes, providing relief to supply chain managers from tedious tasks. With AI, we can predict demand more accurately, reduce excess stock, avoid stockouts, and ultimately improve our organization’s bottom line. Let’s explore how this approach not only boosts sales and operational efficiency but also elevates customer satisfaction by ensuring products are always available when needed.

 

Insights for Improved Decision-Making in Inventory Management

1. Enhanced Forecast Accuracy Advanced Machine Learning algorithms analyze historical data to identify patterns that humans might miss. Techniques like clustering, regime change detection, anomaly detection, and regression analysis provide deep insights into data. Measuring forecast error is essential for refining forecast models; for example, techniques like Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) help quantify the accuracy of forecasts. Businesses can improve accuracy by continuously monitoring and adjusting forecasts based on these error metrics. As the Demand Planner at a Hardware Retailer stated, “With the improvements to our forecasts and inventory planning that Smart Software enabled, we have been able to reduce safety stock by 20% while also reducing stock-outs by 35%.”

2. Real-Time Data Analysis State-of-the-art systems can process vast amounts of data in real time, allowing businesses to adjust their inventory levels dynamically based on current demand trends and market conditions. Anomaly detection algorithms can automatically identify and correct sudden spikes or drops in demand, ensuring that the forecasts remain accurate. A notable success story comes from Smart IP&O, which enabled one company to reduce inventory by 20% while maintaining service levels by continuously analyzing real-time data and adjusting forecasts accordingly. FedEx Tech’s Manager of Materials highlighted, “Whatever the request, we need to meet our next-day service commitment – Smart enables us to risk adjust our inventory to be sure we have the products and parts on hand to achieve the service levels our customers require.”

3. Improved Supply Chain Efficiency Intelligent technology platforms can optimize the entire supply chain, from procurement to distribution, by predicting lead times and optimizing order quantities. This reduces the risk of overstocking and understocking. For instance, using forecast-based inventory management, Smart Software helped a manufacturer streamline its supply chain, reducing lead times by 15% and enhancing overall efficiency. The VP of Operations at Procon Pump stated, “One of the things I like about this new tool… is that I can evaluate the consequences of inventory stocking decisions before I implement them.”

4. Enhanced Decision-Making AI provides actionable insights and recommendations, enabling managers to make informed decisions. This includes identifying slow-moving items, forecasting future demand, and optimizing stock levels. Regression analysis, for example, can relate sales to external variables like seasonality or economic indicators, providing a deeper understanding of demand drivers. One of Smart Software’s clients reported a significant improvement in decision-making processes, resulting in a 30% increase in service levels while reducing excess inventory by 15%. “Smart IP&O enabled us to model demand at each stocking location and, using service level-driven planning, determine how much to stock to achieve the service level we require,” noted the Purchasing Manager at Seneca Companies.

5. Cost Reduction By optimizing inventory levels, businesses can reduce holding costs and minimize losses from obsolete or expired products. AI-driven systems also reduce the need for manual inventory checks, saving time and labor costs. A recent case study shows how implementing Inventory Planning & Optimization (IP&O) was accomplished within 90 days of project start. Over the ensuing six months, IP&O enabled the adjustment of stocking parameters for several thousand items, resulting in inventory reductions of $9.0 million while sustaining target service levels.

 

By leveraging advanced algorithms and real-time data analysis, businesses can maintain optimal inventory levels and enhance their overall supply chain performance. Inventory Planning & Optimization (IP&O) is a powerful tool that can help your organization achieve these goals. Incorporating state-of-the-art inventory optimization into your organization can lead to significant improvements in efficiency, cost reduction, and customer satisfaction.

 

 

​​In a highly configurable manufacturing environment, forecasting finished goods can become a complex and daunting task. The number of possible finished products skyrockets when many components are interchangeable. A traditional MRP would force us to forecast every single finished product, which can be unrealistic or even impossible. Several leading solutions introduce the concept of the “Planning BOM,” which allows the use of forecasts at a higher level in the manufacturing process. In this article, we will discuss this functionality in Epicor Kinetic and how you can take advantage of it with Epicor Smart Inventory Planning and Optimization (Smart IP&O) to get ahead of your demand in the face of this complexity.

Why Would I Need a Planning BOM?

Traditionally, each finished product or SKU would have a rigidly defined bill of materials. If we stock that product and want to plan around forecasted demand, we will forecast demand for those products and then feed MRP to blow this forecasted demand from the finished good level down to its components via the BOM.

Many companies, however, offer highly configurable products where customers can select options on the product they buy. As an example, recall the last time you bought a cellphone. You chose a brand and model, but from there, you were likely presented with options: what screen size do you want? How much storage do you want? What color do you prefer? If that business wants to have these cellphones ready and available to ship to you in a reasonable time, suddenly, they are no longer just anticipating demand for that model—they must forecast that model for every type of screen size, for all storage capacities, for all colors, and all possible combinations of those as well! For some manufacturers, these configurations can compound to hundreds or thousands of possible finished good permutations.

There may be so many possible customizations that the demand at the finished product level is completely unforecastable in a traditional sense. Thousands of those cellphones may sell every year, but for each possible configuration, the demand may be extremely low and sporadic—perhaps certain combinations sell once and never again.

This often forces these companies to plan reorder points and safety stock levels mostly at the component level, while largely reacting to firm demand at the finished good level via MRP. While this is a valid approach, it lacks a systematic way to leverage forecasts that may account for anticipated future activity such as promotions, upcoming projects, or sales opportunities. Forecasting at the “configured” level is effectively impossible, and trying to weave in these forecast assumptions at the component level isn’t feasible either.

Planning BOM Explained This is where Planning BOMs come in. Perhaps the sales team is working on a big B2B opportunity for that model, or there’s a planned promotion for Cyber Monday. While trying to work in those assumptions for every possible configuration isn’t realistic, doing it at the model level is totally doable—and tremendously valuable.

The Planning BOM can use a forecast at a higher level and then blow demand down based on predefined proportions for its possible components. For example, the cellphone manufacturer may know that most people opt for 128GB of storage, and far fewer opt for upgrades to 256GB or 512GB. The planning BOM allows the organization to (for example) blow 60% of the demand down to the 128GB option, 30% to the 256GB option, and 10% to the 512GB option. They could do the same for screen sizes, colors, or other available customizations.

The business can now focus its forecast at this model level, leaving the Planning BOM to determine the component mix. Clearly, defining these proportions requires some thought, but Planning BOMs effectively allows businesses to forecast what would otherwise be unforecastable.

The Importance of a Good Forecast

Of course, we still need a good forecast to load into Epicor Kinetic. As explained in this article, while Epicor Kinetic can import a forecast, it often cannot generate one, and when it does it tends to require a great deal of hard-to-use configurations that don’t often get revisited, resulting in inaccurate forecasts. It is, therefore, up to the business to come up with its own sets of forecasts, often manually produced in Excel. Forecasting manually generally presents a number of challenges, including but not limited to:

• The inability to identify demand patterns like seasonality or trend.
• Overreliance on customer or sales forecasts.
• Lack of accuracy or performance tracking.

No matter how well configured the MRP is with your carefully considered Planning BOMs, a poor forecast means poor MRP output and mistrust in the system—garbage in, garbage out. Continuing along with the “cellphone company” example, without a systematic way of capturing key demand patterns and/or domain knowledge in the forecast, MRP can never see it.

 

Smart IP&O: A Comprehensive Solution

Smart IP&O supports planning at all levels of your BOM, though the “blowing out” is handled via MRP inside Epicor Kinetic. Here is the method we use for our Epicor Kinetic customers, which is straightforward and effective:

• Smart Demand Planner: The platform contains a purpose-built forecasting application called Smart Demand Planner that you will use to forecast demand for your manufactured products (usually finished goods). It generates statistical forecasts, enables planners to make adjustments and/or weave in other forecasts (such as sales or customer forecasts), and tracks accuracy. The output of this is a forecast that goes into forecast entry inside Epicor Kinetic, where MRP will pick it up. MRP will subsequently use demand at the finished good level, and also blow out material requirements through the BOM, so that demand is recognized at lower levels as well.
• Smart Inventory Optimization: You simultaneously use Smart Inventory Optimization to set min/max/safety levels both for any finished goods you make to stock (if applicable; some of our customers operate purely make-to-order off of firm demand), as well as for raw materials. The key here is that at the raw material level, Smart will leverage job usage demand, supplier lead times, etc., to optimize these parameters while at the same time using sales orders/shipments as demand at the finished good level. Smart handles these multiple inputs of demand elegantly via the bidirectional integration with Epicor Kinetic.

When MRP runs, it nets out supply & demand (which, once again, includes raw material demand blown out from the finished good forecast) against the min/max/safety levels you have established to suggest PO and job suggestions.

 

Extend Epicor Kinetic with Smart IP&O

Smart IP&O is designed to extend your Epicor Kinetic system with many integrated demand planning and inventory optimization solutions. For example, it can generate statistical forecasts automatically for large numbers of items, allows for intuitive forecast adjustments, tracks forecast accuracy, and ultimately allows you to generate true consensus-based forecasts to better anticipate the needs of your customers.

Thanks to highly flexible product hierarchies, Smart IP&O is perfectly suited to forecasting at the Planning BOM level, so you can capture key patterns and incorporate business knowledge at the levels that matter most. Furthermore, you can analyze and deploy optimal safety stock levels at any level of your BOM.

Leveraging Epicor Kinetic’s Planning BOM capabilities alongside Smart IP&O’s advanced forecasting and inventory optimization features ensures that you can meet demand efficiently and accurately, regardless of the complexity of your product configurations. This synergy not only enhances forecast accuracy but also strengthens overall operational efficiency, helping you stay ahead in a competitive market.

 

 

We believe the leading edge of supply chain analytics to be the development of digital twins of inventory systems. These twins take the form of discrete event models that use Monte Carlo simulation to generate and optimize over the full range of operational risks. We also assert that we and our colleagues at Smart Software have played an outsized role in forging that leading edge. But we are not alone: there are a small number of other software firms around the globe who are catching up.

So, what’s next for supply chain analytics? Where is the next frontier? It might involve some sort of neural network model of a distribution system. But we’d give better odds on an extension of our leading-edge models of “single echelon” inventory systems to “multi-echelon” inventory systems.

Figures 1 and 2 illustrate the distinction between single and multiple echelon systems. Figure 1 depicts a manufacturer that relies on a Source to replenish its stock of spare parts or components. When stockouts loom, the manufacturer orders replenishment stock from the Source.

Figure 1: A single-echelon inventory system

 

Single echelon models do not explicitly include details of the Source. It remains mysterious, an invisible ghost whose only relevant feature is the random time it takes to respond to a replenishment request. Importantly, the Source is implicitly assumed to never itself stock out. That assumption may be “good enough” for many purposes, but it cannot be literally true. It gets handled by stuffing supplier stockout events into the replenishment lead time distribution. Pushing back on that assumption is the rationale for multiechelon modeling.

Figure 2 depicts a simple two-echelon inventory system. It shifts domains from manufacturing to distribution. There are multiple warehouses (WH’s) dependent on a distribution center (DC) for resupply. Now the DC is an explicit part of the model. It has a finite capacity to process orders and requires its own reordering protocols. The DC gets its replenishment from higher up the chain from a Source. The Source might be the manufacturer of the inventory item or perhaps a “regional DC” or something similar, but – guess what? – it is another ghost. As in the single-echelon model, this ghost has one visible characteristic: the probability distribution of its replenishment lead time. (The punch line of a famous joke in physics is “But madame, it’s turtles all the way down.” In our case, “It’s ghosts all the way up.”)

Figure 2: A two-echelon inventory system

 

The problem of process design and optimization is much harder with two levels. The difficulty is not just the addition of two more control parameters for every WH (e.g., a Min and a Max for each) plus the same two parameters for the DC. Rather, the tougher part is modeling the interaction among the WH’s. In the single-level model, each WH operates in its own little world and never hears “Sorry, we’re stocked out” from the ghostly Source. But in a two-level system, there are multiple WH’s all competing for resupply from their shared DC. This competition creates the main analytical difficulty: the WH’s cannot be modeled in isolation but must be analyzed simultaneously. For instance, if one DC services ten WH’s, there are 2+10×2 = 22 inventory control parameters whose values need to be calculated. In nerd-speak: It is not trivial to solve a 22-variable constrained discrete optimization problem having a stochastic objective function.

If we choose the wrong system design, we discover a new phenomenon inherent in multi-echelon systems, which we informally call “meltdown” or “catastrophe.” In this phenomenon, the DC cannot keep up with the replenishment demands of the WH’s, so it eventually creates stockouts at the warehouse level. Then the WH’s increasingly frantic replenishment requests exhaust the inventory at the DC, which starts its own panicked requests for replenishment from the regional DC. If the regional DC takes too long to refill the DC, then the whole system dissolves into a stockout tragedy.

One solution to the meltdown problem is to overdesign the DC so it almost never runs out, but that can be very expensive, which is why there is a regional DC in the first place. So any affordable system design has a DC that is just good enough to last a long time between meltdowns. This perspective implies a new type of key performance indicator (KPI), such as “Probability of Meltdown within X years is less than Y percent.”

The next frontier will require new methods and new metrics but will offer a new way to design and optimize distribution systems. Our skunk works is already generating prototypes. Watch this space.