​Demand planning and statistical forecasting software play a pivotal role in effective business management by incorporating features that significantly enhance forecasting accuracy. One key aspect involves the utilization of smoothing-based or extrapolative models, enabling businesses to quickly make predictions based solely on historical data. This foundation rooted in past performance is crucial for understanding trends and patterns, especially in variables like sales or product demand. Forecasting software goes beyond mere data analysis by allowing the blending of professional judgment with statistical forecasts, recognizing that forecasting is not a one-size-fits-all process. This flexibility enables businesses to incorporate human insights and industry knowledge into the forecasting model, ensuring a more nuanced and accurate prediction.

Features such as forecasting multiple items as a group, considering promotion-driven demand, and handling intermittent demand patterns are essential capabilities for businesses dealing with diverse product portfolios and dynamic market conditions.  Proper implementation of these applications empowers businesses with versatile forecasting tools, contributing significantly to informed decision-making and operational efficiency.

Extrapolative models

Our demand forecasting solutions support a variety of forecasting approaches including extrapolative or smoothing-based forecasting models, such as exponential smoothing and moving averages.  The philosophy behind these models is simple: they try to detect, quantify, and project into the future any repeating patterns in the historical data.

  There are two types of patterns that might be found in the historical data:

• Trend
• Seasonality

These patterns are illustrated in the following figure along with random data.

Illustrating trending, seasonal, and random time series data

If the pattern is a trend, then extrapolative models such as double exponential smoothing and linear moving average estimates the rate of increase or decrease in the level of the variable and project that rate into the future.

If the pattern is seasonality, then models such as Winters and triple exponential smoothing estimate either seasonal multipliers or seasonal add factors and then apply these to projections of the nonseasonal portion of the data.

Very often, especially with retail sales data, both trend and seasonal patterns are involved. If these patterns are stable, they can be exploited to give very accurate forecasts.

Sometimes, however, there are no obvious patterns, so that plots of the data look like random noise. Sometimes patterns are clearly visible, but they change over time and cannot be relied upon to repeat. In these cases, the extrapolative models don’t try to quantify and project patterns. Instead, they try to average through the noise and make good estimates of the middle of the distribution of data values. These typical values then become the forecasts.  Sometimes, when users see a historical plot with lots of ups and downs they are concerned when the forecast doesn’t replicate those ups and downs. Normally, this should not be a reason for concern.  This occurs when the historical patterns aren’t strong enough to warrant using a forecasting method that would replicate the pattern.  You want to make sure your forecasts don’t suffer from the “wiggle effect” that is described in this blog post.

Past as a predictor of the future

The key assumption implicit in extrapolative models is that the past is a good guide to the future. This assumption, however, can break down. Some of the historical data may be obsolete. For example, the data might describe a business environment that no longer exists. Or, the world that the model represents may be ready to change soon, rendering all the data obsolete. Because of such complicating factors, the risks of extrapolative forecasting are lower when forecasting only a short time into the future.

Extrapolative models have the practical advantage of being cheap and easy to build, maintain and use. They require only accurate records of past values of the variables you need to forecast. As time goes by, you simply add the latest data points to the time series and reforecast. In contrast, the causal models described below require more thinking and more data. The simplicity of extrapolative models is most appreciated when you have a massive forecasting problem, such as making overnight forecasts of demand for all 30,000 items in inventory in a warehouse.

Judgmental adjustments

Extrapolative models can be run in a fully automatic mode with Demand Planner with no intervention required. Causal models require substantive judgment for wise selection of independent variables. However, both types of statistical models can be enhanced by judgmental adjustments. Both can profit from your insights.

Both causal and extrapolative models are built on historical data. However, you may have additional information that is not reflected in the numbers found in the historical record. For instance, you may know that competitive conditions will soon change, perhaps due to price discounts, or industry trends, or the emergence of new competitors, or the announcement of a new generation of your own products. If these events occur during the period for which you are forecasting, they may well spoil the accuracy of purely statistical forecasts. Smart Demand Planner’ graphical adjustment feature lets you include these additional factors in your forecasts through the process of on- screen graphical adjustment.

Be aware that applying user adjustments to the forecast is a two-edged sword. Used appropriately, it can enhance forecast accuracy by exploiting a richer set of information. Used promiscuously, it can add additional noise to the process and reduce accuracy. We advise that you use judgmental adjustments sparingly, but that you never blindly accept the predictions of a purely statistical forecasting method.  It is also very important to measure forecast value add.  That is, the value added to the forecast process by each incremental step.  For example, if you are applying overrides based on business knowledge, it is important to measure whether those adjustments are adding value by improving forecast accuracy.  Smart Demand Planner supports measurement of forecast value add by tracking every forecast considered and automating the forecast accuracy reports. You can select statistical forecasts, measure their errors, and compare them to the overridden ones.  By doing so, you inform the forecasting process so that better decisions can be made in the future. 

Multiple-level forecasts

Another common situation involves multiple-level forecasting, where there are multiple items being forecast as a group or there may even be multiple groups, with each group containing multiple items. We will generally call this type of forecasting Multilevel Forecasting. The prime example is product line forecasting, where each item is a member of a family of items, and the total of all the items in the family is a meaningful quantity.

For example, as in the following figure, you might have a line of tractors and want forecasts of sales for each type of tractor and for the entire tractor line.

Illustrating multiple-level product forecasts

 Smart Demand Planner provides Roll Up/Roll Down Forecasting. This function is crucial for obtaining comprehensive forecasts of all product items and their group total. The Roll Down/Roll Up method within this feature offers two options for obtaining these forecasts:

Roll Up (Bottom-Up): This option initially forecasts each item individually and then aggregates the item-level forecasts to generate a family-level forecast.

Roll Down (Top-Down): Alternatively, the roll-down option starts by forming the historical total at the family level, forecasts it, and then proportionally allocates the total down to the item level.

When utilizing Roll Down/Roll Up, you have access to the full array of forecast methods provided by Smart Demand Planner at both the item and family levels. This ensures flexibility and accuracy in forecasting, catering to the specific needs of your business across different hierarchical levels.

Forecasting research has not established clear conditions favoring either the top-down or bottom-up approach to forecasting. However, the bottom-up approach seems preferable when item histories are stable, and the emphasis is on the trends and seasonal patterns of the individual items. Top-down is normally a better choice if some items have very noisy history or the emphasis is on forecasting at the group level. Since Smart Demand Planner makes it fast and easy to try both a bottom-up and a top- down approach, you should try both methods and compare the results.  You can use Smart Demand Planner’s “Hold back on Current”  feature in the “Forecast vs. Actual” to test both approaches on your own data and see which one yields a more accurate forecast for your business. 

In this video blog, we explore the integral role that inventory models play in shaping the decision-making processes of professionals across various industries. These models, whether they are tangible computer simulations or intangible mental constructs, serve as critical tools in managing the complexities of modern business environments. The discussion begins with an overview of how these models are utilized to predict outcomes and streamline operations, emphasizing their relevance in a constantly evolving market landscape.

​The discussion further explores how various models distinctly influence strategic decision-making processes. For instance, the mental models professionals develop through experience often guide initial responses to operational challenges. These models are subjective, built from personal insights and past encounters with similar situations, allowing quick, intuitive decision-making. On the other hand, computer-based models provide a more objective framework. They use historical data and algorithmic calculations to forecast future scenarios, offering a quantitative basis for decisions that need to consider multiple variables and potential outcomes. This section highlights specific examples, such as the impact of adjusting order quantities on inventory costs and ordering frequency or the effects of fluctuating lead times on service levels and customer satisfaction.

In conclusion, while mental models provide a framework based on experience and intuition, computer models offer a more detailed and numbers-driven perspective. Combining both types of models allows for a more robust decision-making process, balancing theoretical knowledge with practical experience. This approach enhances the understanding of inventory dynamics and equips professionals with the tools to adapt to changes effectively, ensuring sustainability and competitiveness in their respective fields.

For some of our customers, weather has a significant influence on demand. Extreme short-term weather events like fires, droughts, hot spells, and so forth can have a significant near-term influence on demand.

There are two ways to factor weather into a demand forecast: indirectly and directly. The indirect route is easier using the scenario-based approach of Smart Demand Planner. The direct approach requires a tailored special project requiring additional data and hand-crafted modeling.

Indirect Accounting for Weather

The standard model built into Smart Demand Planner (SDP) accommodates weather effects in four ways:

1. If the world is steadily getting warmer/colder/drier/wetter in ways that impact your sales, SDP detects these trends automatically and incorporates them into the demand scenarios it generates.
2. If your business has a regular rhythm in which certain days of the week or certain months of the year have consistently higher or lower-than-average demand, SDP also automatically detects this seasonality and incorporates it into its demand scenarios.
3. Often it is the cussed randomness of weather that interferes with forecast accuracy. We often refer to this effect as “noise”. Noise is a catch-all term that incorporates all kinds of random trouble. Besides weather, a geopolitical flareup, the surprise failure of a regional bank, or a ship getting stuck in the Suez Canal can and have added surprises to product demand. SDP assesses the volatility of demand and reproduces it in its demand scenarios.
4. Management overrides. Most of the time, customers let SDP churn away to automatically generate tens of thousands of demand scenarios. But if users feel the need to touch up specific forecasts using their insider knowledge, SDP can make that happen through management overrides.

Direct Accounting for Weather

Sometimes a user will be able to articulate subject matter expertise linking factors outside their company (such as interest rates or raw materials costs or technology trends) to their own aggregate sales. In these situations, Smart Software can arrange for one-off special projects that provide alternative (“causal”) models to supplement our standard statistical forecasting models. Contact your Smart Software representative to discuss a possible causal modeling project.

Meanwhile, don’t forget your umbrella.

In this video blog, the spotlight is on a critical aspect of inventory management: the analysis and interpretation of inventory data. The focus is specifically on a dataset from a public transit agency detailing spare parts for buses. With over 13,700 parts recorded, the data presents a prime opportunity to delve into the intricacies of inventory operations and identify areas for improvement.

Understanding and addressing anomalies within inventory data is important for several reasons. It not only ensures the efficient operation of inventory systems but also minimizes costs and enhances service quality. This video blog explores four fundamental rules of inventory management and demonstrates, through real-world data, how deviations from these rules can signal underlying issues. By examining aspects such as item cost, lead times, on-hand and on-order units, and the parameters guiding replenishment policies, the video provides a comprehensive overview of the potential challenges and inefficiencies lurking within inventory data. 

We highlight the importance of regular inventory data analysis and how such an analysis can serve as a powerful tool for inventory managers, allowing them to detect and rectify problems before they escalate. Relying on antiquated approaches can lead to inaccuracies, resulting in either excess inventory or unfulfilled customer expectations, which in turn could cause considerable financial repercussions and inefficiencies in operations.

Through a detailed examination of the public transit agency’s dataset, the video blog conveys a clear message: proactive inventory data review is essential for maintaining optimal inventory operations, ensuring that parts are available when needed, and avoiding unnecessary expenditures.

Leveraging advanced predictive analytics tools like Smart Inventory Planning and Optimization will help you control your inventory data. Smart IP&O will show you decisive demand and inventory insights into evolving spare parts demand patterns at every moment, empowering your organization with the information needed for strategic decision-making.

​BACKGROUND

Most of Smart Software’s blogs, webinars and white papers describe the use of our software in “normal operations.” This one is about “irregular operations.”  Smart Software is in the process of adapting our products to help you cope with your own irregular ops. This is a preview.

I first heard the term “irregular operations” when serving a sabbatical tour at the U.S. Federal Aviation Administration in Washington, DC. The FAA abbreviates the term to “IROPS” and uses it to describe situations in which weather, mechanical problems or other issues disrupt the normal flow of aircraft.

Smart Inventory Optimization® (“SIO”) currently works to provide what are known as “steady state” policies for managing inventory items. That means, for instance, that SIO automatically calculates values for reorder points (ROP’s) and order quantities (OQ’s) that are meant to last for the foreseeable future. It computes these values based on simulations of daily operations that extend years into the future. If and when the unforeseeable happens, our regime change detection method reacts by removing obsolete data and allowing recalculation of the ROP’s and OQ’s.

We often note the increasing speed of business, which shortens the duration of the “foreseeable future.” Some of our customers are now adopting shorter planning horizons, such as moving from quarterly to monthly plans. One side effect of this change is that IROPS have become more consequential. If a plan is based on three simulated years of daily demand, one odd event, like a large surprise order, doesn’t matter much in the grand scheme of things. But if the planning horizon is very short, one big surprise demand can have a major effect on key performance indicators (KPI’s) computed over a shorter interval – there is no time for “averaging out”. The planner may be forced to place an emergency replenishment order to deal with the disruption. When should the order be placed to do the most good? How big should it be?

SCENARIO: NORMAL OPS

To make this concrete, consider the following scenario. Tom’s Spares, Inc. provides critical service parts to its customers, including SKU723, a replacement circuit board sold under the trade name WIDGET. Demand for WIDGET is intermittent, with less than one unit demanded per day. Tom’s Spares orders WIDGETs from Acme Products, who take either 7 or 10 days to fulfill replenishment orders.

Tom’s Spares operates with a short inventory planning horizon of 28 days. The company operates in a competitive environment with impatient customers who only grudgingly accept backorders. Tom’s policy is to set ROP’s and OQ’s to keep inventory lean while maintaining a fill rate of at least 90%. Management monitors KPI’s on a monthly basis. In the case of WIDGETS, these KPI targets are currently met using an ROP=3 and an OQ=4, resulting in an average on hand of about 4 units and average fill rate of 96%.  Tom’s Spares has a pretty good thing going for WIDGETS.

Figure 1 shows two months of WIDGET information. The top left panel shows daily unit demand. The top right shows daily units on hand. The bottom left panel shows the timing and size of replenishment orders back to Acme Products. The bottom right shows units backordered due to stockouts. In this simulation, daily demand was either 0 or 1, with one demand of 2 units. On hand units began the month at 7 and never dropped below 1, though in the next month there was a stockout resulting in a single unit on backorder. Over the two months, there were 4 replenishment orders of 4 units each sent to Acme, all of which arrived during the two-month simulation period.

GOOD TROUBLE DISRUPTS NORMAL OPS

Now we add some “good trouble” to the scenario: An unusually large order arises part way through the planning period. It’s “good” because more demand implies more revenue. But it’s “trouble” because the normal ops inventory control parameters (ROP=3, OQ=4) were not chosen to cope with this situation. The spike in demand might be so big, and so disadvantageously timed, as to overwhelm the inventory system, creating stockouts and their attendant backorders. The KPI report to management for such a month would not be pretty.

Figure 2 shows a scenario in which a demand spike of 10 units hits in the third day of the planning period. In this case, the spike puts the inventory under water for the rest of the month and creates a cascade of backorders extending into the next month. Averaging over 1,000 simulations, month 1 KPI’s show an average on hand of 0.6 units and a miserable 44% fill rate.

FIGHTING BACK WITH IRREGULAR OPERATIONS

Tom’s Spares can respond to an irregular situation with an irregular move by creating an emergency replenishment order. To do it right, they have to think about (a) when to place the order (b) how big the order should be and (c) whether to expedite the order.

The timing question seems obvious: react as soon as the order hits. However, if the customer were to provide early warning, Tom’s Spares could order early and be in better position to limit the disruption from the spike. However, if communication between Tom’s and the customer making the big order is spotty, then the customer might give Tom’s a heads-up later or not at all.

The size of the special order seems obvious too: pre-order the required number of units. But that works best if Tom’s Spares knows when the demand spike will hit. If not, it might be a good idea to order extra to limit the duration of any backorders. In general, the less early warning provided, the larger the order Tom’s should make. This relationship could be explored with simulation, of course.

The arrival of the replenishment order could be left to the usual operation of Acme Products. In the simulations above, Acme was equally likely to respond in 7 or 14 days. For a 28-day planning horizon, taking a risk on getting a 14-day response might be asking for trouble, so it may be especially worthwhile for Tom’s to pay Acme for expedited shipping. Maybe overnight, but possibly something cheaper but still relatively fast.

We explored a few more scenarios using simulation. Table 1 shows the results. Scenarios 1-4 assume a surprise additional demand of 10 units arrives on Day 3, triggering an immediate order for  additional replenishment. The size and lead time of the replenishment order varies.

Scenario 0 shows that doing nothing in response to the surprise demand leads to an abysmal 41% fill rate for that month; not shown is that this result sets of the next month for continued poor performance. Regular operations won’t do well. The planner must do something to respond to the anomalous demand.

Doing something in response involves making a one-time emergency replenishment order. The planner must choose the size and timing of that order. Scenarios 1 and 3 depict “half sized” replenishments. Scenarios 1 and 2 depict overnight replenishments, while scenarios 3 and 4 depict guaranteed one week response.

The results make clear that immediate response is more important than the size of the replenishment order for restoring the Fill Rate. Overnight replenishment produces fill rates in the 70% range, while one-week replenishment lead time drops the fill rate into the mid-50% to mid-60% range.

TAKEAWAYS

Inventory management software is expanding from its traditional focus on normal ops to an additional focus on irregular ops (IROPS). This evolution has been made possible by the development of new statistical methods for generating demand scenarios at a daily level.

We considered one IROPS situation: surprise arrival of an anomalously large demand. Daily simulations provided guidance about the timing and size of an emergency replenishment order. Results from such an analysis provide inventory planners with critical backup by estimating the results of alternative interventions that their experience suggests to them.

Feynman’s perspective illuminates our journey:  “In its efforts to learn as much as possible about nature, modern physics has found that certain things can never be “known” with certainty. Much of our knowledge must always remain uncertain. The most we can know is in terms of probabilities.” ― Richard Feynman, The Feynman Lectures on Physics.

When we try to understand the complex world of logistics, randomness plays a pivotal role. This introduces an interesting paradox: In a reality where precision and certainty are prized, could the unpredictable nature of supply and demand actually serve as a strategic ally?

The quest for accurate forecasts is not just an academic exercise; it’s a critical component of operational success across numerous industries. For demand planners who must anticipate product demand, the ramifications of getting it right—or wrong—are critical. Hence, recognizing and harnessing the power of randomness isn’t merely a theoretical exercise; it’s a necessity for resilience and adaptability in an ever-changing environment.

Embracing Uncertainty: Dynamic, Stochastic, and Monte Carlo Methods

Dynamic Modeling: The quest for absolute precision in forecasts ignores the intrinsic unpredictability of the world. Traditional forecasting methods, with their rigid frameworks, fall short in accommodating the dynamism of real-world phenomena. By embracing uncertainty, we can pivot towards more agile and dynamic models that incorporate randomness as a fundamental component. Unlike their rigid predecessors, these models are designed to evolve in response to new data, ensuring resilience and adaptability. This paradigm shift from a deterministic to a probabilistic approach enables organizations to navigate uncertainty with greater confidence, making informed decisions even in volatile environments.

Stochastic modeling guides forecasters through the fog of unpredictability with the principles of probability. Far from attempting to eliminate randomness, stochastic models embrace it. These models eschew the notion of a singular, predetermined future, presenting instead an array of possible outcomes, each with its estimated probability. This approach offers a more nuanced and realistic representation of the future, acknowledging the inherent variability of systems and processes. By mapping out a spectrum of potential futures, stochastic modeling equips decision-makers with a comprehensive understanding of uncertainty, enabling strategic planning that is both informed and flexible.

Named after the historical hub of chance and fortune, Monte Carlo simulations harness the power of randomness to explore the vast landscape of possible outcomes. This technique involves the generation of thousands, if not millions, of scenarios through random sampling, each scenario painting a different picture of the future based on the inherent uncertainties of the real world. Decision-makers, armed with insights from Monte Carlo simulations, can gauge the range of possible impacts of their decisions, making it an invaluable tool for risk assessment and strategic planning in uncertain environments.

Real-World Successes: Harnessing Randomness

The strategy of integrating randomness into forecasting has proven invaluable across diverse sectors. For instance, major investment firms and banks constantly rely on stochastic models to cope with the volatile behavior of the stock market. A notable example is how hedge funds employ these models to predict price movements and manage risk, leading to more strategic investment choices.

Similarly, in supply chain management, many companies rely on Monte Carlo simulations to tackle the unpredictability of demand, especially during peak seasons like the holidays. By simulating various scenarios, they can prepare for a range of outcomes, ensuring that they have adequate stock levels without overcommitting resources. This approach minimizes the risk of both stockouts and excess inventory.

These real-world successes highlight the value of integrating randomness into forecasting endeavors. Far from being the adversary it’s often perceived to be, randomness emerges as an indispensable ally in the intricate ballet of forecasting. By adopting methods that honor the inherent uncertainty of the future—bolstered by advanced tools like Smart IP&O—organizations can navigate the unpredictable with confidence and agility. Thus, in the grand scheme of forecasting, it may be wise to embrace the notion that while we cannot control the roll of the dice, we can certainly strategize around it.