How Can I Improve My Forecast Accuracy?

Imagine

Imagine that Amanda (a completely imaginary person) is a demand planner at Kool Komfort Foods (a completely imaginary company, also branded as K2), a nationwide producer of healthy comfort foods.  She got her bachelor’s in Mechanical Engineering about five years ago.  After a short stint in manufacturing process engineering in another industry, she got interested in the business side of things and moved into supply chain planning, starting in demand planning.  After taking a couple of on-line courses and getting an APICS certification, she seized on the opportunity to be a junior demand planner at K2.  Through her affinity for math and her attention to detail, Amanda earned a couple of promotions and is now a senior demand planner.  At present, she currently manages a couple of product lines, but has her sights set on becoming a demand planning manager and mentoring others.

Amanda has been using some of the common metrics for forecast accuracy, including MAPE (mean absolute percentage error) and weighted MAPE, but the statistical forecast doesn’t seem to improve and the qualitative inputs from marketing and sales are hit or miss.  Her colleague, Jamison, uses the standard deviation of forecast error to plan for safety stock, but there are still a lot of inventory shortages and overages.  

Amanda has heard her VP, Dmitry, present to other department heads how good the forecast is, but when he does that, he uses aggregate measures and struggles when he is asked to explain why order fill rate is not improving, if the forecast is so good.

Amanda wonders what is preventing her from getting better results at the product/DC level, where it counts.  She would love to have it at the product/customer or product/store level, but she knows that she will need better results at the product/DC level before she can do that.  She is running out of explanations for her boss and the supply planning team.  She has been using some basic forecasting techniques that she has programmed into Excel, like single and double exponential smoothing as well as moving average, and even linear regression.  She is sure the math is correct, but the results have been disappointing. 

Amanda’s company just bought a commercial forecasting package.  She was hoping that would help.  It is supposed to run a bunch of models and select the best one and optimize the parameters, but so far, the simpler models perform the best and are no better – and sometimes worse – than her Excel spreadsheet.

Amanda has been seeing a lot of posts on LinkedIn about “AI”.  She has been musing to herself about whether there is some magic bullet in that space that might deliver better results.  But, she hasn’t had time to learn much about the details of that kind of modeling.  In fact, she finds it all a bit overwhelming, with all of the hype around the topic.

And, anyway, forecasts will always be wrong, they will always change, and the demand planner will always take the blame.  Investments in forecasting will inevitably reach diminishing returns, but for every improvement in forecast accuracy, there are cascading benefits through the supply chain and improvements in customer service.  So, what can Amanda and her company do to make sure they are making the most of the opportunity to anticipate market requirements without overinvesting and losing focus on the crucial importance of developing an ever more responsive value network to meet constantly changing customer requirements?

Unfortunately, there really is no “silver bullet” for forecasting, no matter how many hyperbolic adjectives are used by a software firm in their pitch.  That is not to say that a software package can’t be useful, but you need to really understand what you need and why before you go shopping.  

Demand planning consists of both quantitative and a qualitative analysis.  Since the quantitative input can be formulated and automated (not that it’s easy or quick), it can be used for calculating and updating a probabilistic range for anticipated demand over time. 

A good quantitative forecast requires hard work and skilled analysis.  Creating the best possible quantitative forecast (without reaching diminishing returns) will provide a better foundation for, and even improve, qualitative input from marketing, sales, and others.

Profiling

One of the first things you need to do is understand the behavior of the data.  This requires profiling the demand by product and location (either shipping plant/DC or customer location – let’s call that a SKU for ease of reference) with respect to volume and variability in order to determine the appropriate modeling approach.  For example, a basic approach is as follows: High volume, low variability SKU’s will be easy to mathematically forecast and may be suited for lean replenishment techniques.  

• Low volume, low variability items may be best suited for simple reorder point replenishment.
• High volume, high variability SKU’s will be difficult to forecast and may require a sophisticated approach to safety stock planning.
• Low volume, high variability SKU’s may require a thoughtful postponement approach, resulting in an assemble or make-to-order process.  
• A more sophisticated approach would involve the use of a machine learning for classification that might find clusters of demand along more dimensions.

Profiling analysis can be complemented nicely by a Quantitative Reasonability Range Check (see below), which should be an on-going part of your forecasting process.

Once you have profiled the data, you can start to develop the quantitative forecast, but you will need to consider the questions:

1. What is the appropriate level of aggregation for forecasting?
2. What forecast lag should I use?
3. How frequently should I forecast?
4. What are the appropriate quantitative forecast models?
5. How should I initialize the settings for model parameters?
6. How should I consume the forecast?
7. How will I compensate for demand that I couldn’t capture?
8. What metrics should I use to measure forecast accuracy?

Let’s consider each of these questions, in turn.

A. Level of Aggregation

The point of this analysis is to determine which of the following approaches will provide you with the best results:

• Forecasting at the lowest level and then aggregating up
• Forecasting at a high level and just disaggregating down
• Forecasting at a mid-level and aggregating up and, also, disaggregating down

B. Correct Lag

If you forecast today for the demand you expect tomorrow, you should be pretty accurate because you will have the most information possible, prior to actually receiving orders.  The problem with this is obvious.  You can’t to react to this forecast (which will change each day up until you start taking orders for the period you are forecasting) by redistributing or manufacturing product because that takes some time.

Since you cannot procure raw materials, manufacture, pack, or distribute instantly, the “lead time” for these activities needs to be taken into account.  So, you need to have a forecast lag.  For example, if you need a month to respond to a change in demand, then, you would need to forecast this month for next month.  You can continue to forecast next month’s demand as you move through this month, but it’s unlikely you will be able to react, so when you measure forecast accuracy, you need to measure it at the appropriate lag.

C. Frequency

Should you generate a new forecast every day? Every week?  Or, just once a month?  This largely depends on when you can get meaningful updates to your forecast inputs such as sales orders, shipment history, or updates to industry and any syndicated or customer data (whether leading or trailing indicators) that are used in your quantitative forecast.

D. Appropriate Forecasting Model(s)

So, what mathematical model should you use?  This is a key question, but as you can see, certainly not the only one.

The mathematical approach can depend on many factors, including, but not limited to, the following:

• Profiling (discussed above)
• Available and meaningful trailing and leading indicators
• Amount of history needed for the model vs. history that’s still relevant
• Forecasting a distribution of demand vs. forecasting the actual distribution 
• Explainability vs. accuracy of the model
• The appearance of accuracy vs. useful accuracy (overfitting a model to the past)
• Treatment of qualitative data (e.g., geography, holiday weekends, home football game, etc.)

A skilled data scientist can be a huge help.  A plethora of techniques is available, but a powerful machine learning (or other) technique can be like a sharp power tool.  You need to know what you’re doing and how to avoid hurting yourself.

E. Initializing the Steady State Settings for Parameters

Failure to properly initialize the parameters of a statistical model can cause it to underachieve.  In the case of Holt-Winters 3 parameter smoothing, for example, the modeler needs to have control over how much history is used for initializing the parameters.  If too little history is used, then forecasts will likely be very unreliable. 

When it comes to machine learning, there are two kinds of parameters – hyperparameters and model parameters.  Training can optimize the model parameters, but knowledge, experience and care are required to select techniques that are likely to help and to set the hyper parameters for running models that will give you good results.

F. Forecast Consumption Rules

There are a few things to consider when you consume the forecast with orders.  For example, you might want to bring forward previously unfulfilled forecasts (or underconsumption) from the previous period(s), or there may be a business reason to simply treat consumption in each week or month in isolation.

You may want to calculate the forecast consumption more frequently than you generate a new forecast.

G. Compensating for Demand You Couldn’t Capture

This is a particular challenge in the retail and CPG industries.  In CPG, many orders from retail customers are placed and fulfilled on a “fill or kill” basis.  The CPG firm fulfills what it can with the inventory on hand and then cancels or “kills” the rest of the order.

In retail, a consumer may simply go to a competitor or order online if the slot for the product on the shelf in a given store is empty.

In either case, sales or shipment history will under-represent true demand for that period.  If you don’t accurately compensate for this, your history will likely drive your forecast model to under-forecast.

H. Metrics and Measurement

There are many measures of forecast accuracy that can be used.  A couple of key questions to answer include the following:

1. Who is the audience and what is their interest?  Consider the sales organization which is interested in an aggregate measure of sales against their sales target, perhaps by sales group or geography.  On the other hand, customer service doesn’t really happen in aggregate.  If you want to have better customer service, you need to look at forecast accuracy at the SKU level.
2. Are you measuring forecast error based on an assumed normal distribution that you have defined by projecting a mean and standard deviation?  Or, have you been able to use the actual distribution of forecast error, perhaps created through bootstrapping? 

Remember that you will need to measure forecast error at the correct lag.

Another thing you may need to keep in mind is that not everyone has been trained to understand forecast error and its interrelationship to inventory, safety stock, and fill rate.  You may have a bit of education to do from time to time, even for executives.

Price & Forecast

In most cases, demand is elastic with respect to price.  In other words, there is a relationship between what you charge for something and the demand for it.  This is why consumer packaged goods companies run promotions and fund promotions with retailers, and also, why retailers run their own promotions.  The goal is to grow sales without losing money and/or gain market share (possibly, incurring a short-term loss).  The overall goal is to increase gross margin in a given time period.  Many CPG companies make competing products – think of shampoo or beverages, or even automobiles or car batteries.  And, of course, retailers sell products from their CPG suppliers that compete for shelf space and share of wallet.  Many retailers even sell their own private label goods.  The trick is how to price competing products such that you gain sales and margin over the set of products.  

Just as in forecasting demand, there are both quantitative and qualitative approaches to optimizing pricing decisions which, then, in turn, need to be incorporated into the demand forecast.  The quantitative approach has two components:

1. Using ML techniques to predict prie elasticity, considering history, future special events (home football game, holiday weekend, football team in playoffs, etc.), minimum and maximum demand, and perhaps other features.
2. Optimizing the promotional offers so that margin is maximized.  For this, a mathematical optimization model may be best so that the total investment in promotional discount and allocations of that investment are respected, limits on cannibalization are enforced, and upper limits on demand are considered.

The Quantitative Reasonability Range Check

There is a process that should be part of both your demand planning and your sales and operations planning.  The concept is simple – how do you find the critical few forecasts that require attention, so that planner brainpower is expended on making a difference and not hunting for a place to make a difference?  A Quantitative Forecast Reasonability Range Check (or maybe QRC, for short) accomplishes this perfectly.  If the historical data is not very dense, then a “reasonability range” may need to be calculated through “bootstrapping”, a process of randomly sampling the history to create a more robust distribution.   Once you have this distribution, you can assign a probability to a future forecast and leverage that probability for safety stock planning as well.

At a minimum, a QRC must consider the following components:

• Every level and combination of the product and geographical hierarchies
• A quantitative forecast
• An asymmetric prediction interval over time
• Metrics for measuring how well a point forecast fits within the prediction interval
• Tabular and graphical displays that are interactive, intuitive, always available, and current

If you are going to attempt to establish a QRC, then I would suggest five best practices:

Eliminate duplication.  When designing a QRC process (and supporting tools), it is instructive to consider the principles of Occam’s razor as a guide:

– The principle of plurality – Plurality should not be used without necessity

– The principle of parsimony – It is pointless to do with more what can be done with less

These two principles of Occam’s razor are useful because the goal is simply to flag unreasonable forecasts that do not pass a QRC, so that planners can focus their energy on asking critical questions only about those cases.

Minimize human time and effort by automating the math.  Leverage automation and, potentially, even cloud computing power, to deliver results that are self-explanatory and always available, providing an immediately understood context that identifies invalid forecasts. 

Eliminate inconsistent judgments.  By following #1 and #2 above, you avoid inconsistent judgments that vary from planner to planner, from product family to product family, or from region to region.

Reflect reality.  Calculations of upper and lower bounds of the prediction interval should reflect seasonality and cyclical demand in addition to month-to-month variations.  A crucial aspect of respecting reality involves calculating the reasonability range for future demand from what actually happened in the past so that you do not force assumptions of normality onto the prediction interval (this is why bootstrapping can be very helpful).  Among other things, this will allow you to predict the likelihood of over- and under-shipment.

Illustrate business performance, not just forecasting performance with prediction intervals.  The range should be applied, not only from time-period to time-period, but also cumulatively across periods such as months or quarters in the fiscal year.

Summary

Demand planning is both quantitative and qualitative.  In this paper, we have touched on the high points of the best practices for building a good quantitative forecasting foundation for your demand planning process.  In our imaginary case, Amanda still has some work to do, some of which lies outside of her expertise.  She will need to articulate the case for making an investment to improve the quantitative forecast and building a better foundation for qualitative input and a consensus demand planning process.  A relatively small improvement in forecast accuracy can have significant positive bottom and top-line impact.  

Amanda needs to convince her management to invest in a consulting service that will deliver the math, without the hype, and within the context of experience, so that she can answer the key quantitative questions every demand planner faces:

• What is the profile of my demand data?
• What is the appropriate level of aggregation for forecasting?
• What forecast lag should I use?
• How frequently should I forecast?
• What are the appropriate quantitative forecast models?
• How should I initialize the settings for model parameters?
• How should I consume the forecast?
• How will I compensate for demand that I couldn’t capture?
• What metrics should I use to measure forecast accuracy?

Advertisement

Who Is Spending Your Cash?

“Cash is king,” we hear.  I have seen this in the core values of major, multi-national corporations.  If you travel for your company, you likely face restrictions on the amount and/or cost of travel which you can book without very senior level approval.  I know of one company with revenues of about $15 billion in which the CFO has mandated approval of any air fare over $500, even for employees who routinely must book and re-book travel on short notice due to the nature of their duties.  I do not debate the wisdom of such policies.  I only use them to illustrate how carefully the expenditure of cash is scrutinized in many cases.  Capital expenditures require even greater examination and multiple approvals, perhaps even from the board of directors.  Despite these procedures, I pose this question:  “Do you really know who his spending your cash and how they are doing it?”

Consider where most of the cash is spent and who spends it.  In most manufacturing firms, the largest single expenditure of cash is for the acquisition of raw materials and their transformation and distribution, namely, the cost of goods sold.  What is not sold remains on the balance sheet as inventory.  A manufacturer with 40% gross margin is doing very well in most industries, although there are notable exceptions in pharmaceuticals and a few other manufacturing industries.

A 40% gross margin would mean that 60% of the cash inflow from sales is spent on inventory – inventory that is either sold or stored.  In fact, manufactured product (or at least the raw materials, components or intermediates/work-in-process) in every manufacturing operation is stored at some point before it is shipped to a customer.  That is why inventory turns or days in inventory (both relating inventory to sales through the cost of goods sold) are the most appropriate kinds of metrics for inventory rather than the absolute amount.

So, given the relative proportion of cash flow in the majority of manufacturing firms that is spent on inventory of one kind or another, compared to, say, the proportion of cash flow spent on travel, one might assume that the level of scrutiny and approval required for spending on inventory would be extraordinary and performed at the most senior level of the firm.  Is that true in your company?  Of course not.  Manufacturing and distribution operations would be paralyzed, and servicing customers effectively would be precluded by such a bureaucratic approach.

Supply chain planners or buyer/planners are people who must determine how much should be procured, when, and where.  Purchasing or sourcing professionals, whose mission is to make sure that the purchase price is minimized, support the planning function, but purchase orders are issued by buyer/planners.

Even if “buying” is separate from “planning”, it is the planner who decides how much is needed when and where.

Planners do not rank among the highest paid employees, yet they are pulling the lever to spend the majority of the company’s cash flow.

Most planners today have access to advanced planning and scheduling (APS) tools which embed material requirements planning (MRP – I know this should be “little mrp”, as opposed to “big MRP” for manufacturing requirements planning, but allow me this convention here for visual ease) and distribution requirements planning (DRP) calculations to aid them in determining how much to purchase.  These tools are very helpful.  They are particularly helpful if the forecast is exactly right, if forecast error is always normally distributed, if stated transit lead times are always reality, if yields are constant, if service from one internal manufacturing or distribution point to another is always constant and known.  However, almost none of these conditions are ever true, and they are never true all at the same time.

So, not only do planners have to ultimately determine what to move, make and buy for every item in the bill of material (or formula/recipe) at every location in every future time period in the planning horizon, they must do so in an environment with many unknown inputs.

(At this point, I will include a plug for recruiting, training and retaining the very best planners – not vp’s of planning or directors of planning, but planners themselves since they are likely spending most of your cash!)

This problem is called multi-echelon, inventory optimization (MEIO).   MEIO is fast becoming a best practice requirement.  MEIO optimizes the answer to the very challenging problem of how much extra inventory a planner should plan to have at each location, for every item, at every level, given the many other unknown factors as well.  Put differently, “What is the inventory safety stock level that should be targeted for every item at every location, such that the cost of holding inventory for achieving a given service level for the end customer is minimized.”  This question must be answered across all nodes while considering all of the unknown factors mentioned above.

When solved, the result is a lower required buffer inventory than could be planned with just MRP or APS in order to achieve an optimal service level.  That means more available cash and more revenue and profits.

Solving the MEIO problem remains a massive challenge for which many planners still do not have sufficient tools at their disposal.  However, algorithms have been developed and can be implemented through commercially viable software.  It’s also increasingly possible to build your own on an advanced analytics platform.  As MEIO continues to be adopted, more planners can go about their normal planning process of determining what to move, make and buy, but with a much better starting point, namely the amount of inventory buffer required at each item, location.  This buffer, or safety stock, already a standard row in a supply planner’s gross-to-net calculation in his or her advanced planning system, allows planners to perform their work without disruption while achieving significantly better results for the cash management of their firm – when populated through MEIO.

Questions:

1)      How do your planners account for the unknown factors in determining how much cash to spend on which inventory in which locations and when?

2)      Are you thinking about evaluating MEIO?  If not, why not?

3)      Can you afford not to pay more attention to where the majority of your cash flow is going?

Ava Ex Machina and the Retail Supply Chain

There is a lot of buzz about the “autonomous” supply chain these days.  The subject came up at a conference I attended where the theme was the supply chain of 2030.  But, before we turn out the lights and lock the door to a fully automated, self-aware, supply chain “Ava Ex Machina”, let’s take a moment and put this idea into some perspective.

The Driverless Car Analogy

From CBC News https://www.cbc.ca/news/business/driverless-cars-stratford-1.3390279

I’ve heard the driverless vehicle used as an analogy for the autonomous supply chain.  However, orchestrating the value network where goods, information and currency pulse freely, fast, and securely between facilities, organizations, and even consumers, following the path of least resistance (aka the digital supply chain), may prove to be even more complex than driving a vehicle.  Digital technologies, such as additive manufacturing, blockchain, and more secure IoT infrastructure, advance the freedom, speed and security of these flows.  As these technologies makes more automation possible, as well as a kind of “autonomy”, the difficulty and importance of guiding these flows becomes ever more crucial.  

Most sixteen-year-old adolescents can successfully drive a car, but you may not want to entrust your global value network to them.

Even Elon Musk says that Tesla autopilot will never be perfect.

Before you can have an autonomous supply chain, you need to accelerate the Detect, Diagnose, Direct Cycle – let’s call it the 3-D Cycle, for short, not just because it’s alliterated, but because each “D” is one of three key dimensions of orchestrating your value network.  In fact, as you accelerate the 3-D Cycle, you will learn just how much automation and autonomy makes sense.

Figure 1

Detect, Diagnose, Direct

The work of managing the value network has always been to make the best plan, monitor issues, and respond effectively and efficiently.  However, since reality begins to diverge almost immediately from even the best plans, perhaps the most vital challenges in orchestrating a value network are monitoring and responding.

In fact, every plan is really just a response to the latest challenges and their causes.

So, if we focus on monitoring and responding, we are covering all the bases of what planners and executives do all day . . . every day.

Monitoring involves detecting and diagnosing those issues which require a response.  Responding is really directing the next best action.  That’s why we can think in terms of the “Detect, Diagnose, Direct Cycle”:

1. Detect (and/or anticipate) market requirements and the challenges in meeting them
2. Diagnose the causes of the challenges, both incidental and systemic
3. Direct the next best action within the constraints of time and cost

The 3-D Cycle used to take a month, in cases where it was even possible.  Digitization – increased computing power, more analytical software, the availability of data – have made it possible in a week.  Routine, narrowly defined, short-term changes are now addressed even more quickly under a steady state – and a lot of controlled automation is not only possible in this case, but obligatory.  However, no business remains in a steady state, and changes from that state require critical decisions which add or destroy significant value.   

You will need to excel at managing and accelerating the 3-D Cycle, if you want to win in digital economy.

There is no industry where mastering this Cycle is more challenging than in retail, but the principles apply across most industries.

 

Data Is the Double-edged Sword

The universe of data is exploding exponentially from growing connections among organizations, people and things, creating the need for an ever-accelerating 3-D Cycle.  This is especially relevant for retailers, and it presents both a challenge and an opportunity for competing in the digital economy with a digital value network.  Redesigned, retail supply chains, enabled with analytics and augmented reality, are not only meeting, but raising consumer expectations.

Figure 2

Amazon’s re-imagination of retail means that competitors must now think in terms of many-to-many flows of information, product, and cash along the path of least resistance for the consumer (and not just to and from their own locations).  This kind of value network strategy goes beyond determining where to put a warehouse and to which stores it should ship.  Competing in today’s multi-channel world can mean inventing new ways to do business, even in the challenging fashion space – and if it is happening in fashion, it would be naive to think rising consumer expectations can be ignored in other retail segments, or even other industries.  Consider a few retail examples:

Zara leverages advanced analytics, not only to sense trends, but also to optimize pricing and operations in their vertically integrated supply chain.

Stitch Fix is changing the shopping model completely, providing more service with less infrastructure.

Zolando has been so successful in creating a rapid response supply chain that they are now providing services to other retailers.

Nordstrom, of all organizations, is opening “inventoryless” stores.

Walmart has been on an incredible acquisition and partnership spree, recently buying Flipkart and, as early as two years ago, partnering with JD.com.  And, then, there is the success of Walmart.com.

Target is redesigning the way their DC’s work, creating a flow-through operation with smaller replenishment quantities.

Yet, many companies are choking on their own ERP data, as they struggle to make decisions on incomplete, incorrect and disparate data.  So, while the need for the 3-D Cycle to keep pace grows more ever more intense, some organizations struggle to do anything but watch.  The winners will be those who can capitalize on the opportunities that the data explosion affords by making better decisions faster through advanced analytics (see Figure 2).

The time required just to collect, clean, transform and synchronize data for analysis remains the fundamental barrier to better detection, diagnosis and decisions in the value network.  A consolidated data store that can connect to source systems and on which data can be consolidated, programmatically “wrangled”, and updated into a supra data set forms a solid foundation on which to build better detection, diagnosis, and decision logic that can execute in “relevant time”.  This can seem like an almost insurmountable challenge, but it is not only doable with today’s technology, it’s becoming imperative.  And, it’s now possible to work off of a virtual supra data set, but that’s a discussion for another day.

 

Detect, Diagnose and Direct with Speed, Precision & Advanced Analytics

Detection of incidental challenges (e.g. demand is surging or falling based on local demographics, a shipment is about to arrive late, a production shortfall at a vendor, etc.) in your value network can be significantly automated to take place in almost real-time, or at least, in relevant time.   Detection of systemic challenges will be a bit more gradual and is based on the metrics that matter to your business, such as customer service, days of supply, etc., but it is the speed and, therefore, the scope, that is now possible that drives better visibility from detection.

Diagnosing the causes of incidental problems is only limited by the organization and detail of your transactional data.  Diagnosing systemic challenges requires a hierarchy of metrics with respect to cause and effect (such as the SCOR® model).  Certainly, diagnosis can now happen with new speed, but it is the combination of speed and precision that makes a new level of understanding possible through diagnosis.

With a clean, complete, synchronized data set that is always available and always current, as well as a proactive view of what is happening and why, you need to direct the next best action while it still matters.  You need to optimize your trade-offs and perform scenario and sensitivity analysis.

Figure 3, below, shows both incidental/operational and systemic/strategic examples for all three dimensions of the 3-D Cycle.

Figure 3

Speed in detection, speed and precision in diagnosis, and the culmination of speed, precision and advanced analytics in decision-making give you the power to transpose the performance of your value network to levels not previously possible.  Much of the entire 3-D Cycle and the prerequisite data synchronization can be, and will be, automated by industry leaders.  Just how “autonomous” those decisions become remains to be seen.

Fortunately, you don’t need Ava Ex Machina, but your ability to develop a faster and better (and, I will even say more autonomous) 3-D Cycle is fundamental to your journey toward the digital transformation of your value network.

The basic ideas of detecting, diagnosing and directing are not novel to supply chain professionals and other business executives.   However, the level of transparency, speed, precision and advanced analytics that are now available mandate a new approach and promise dramatic results.  Some will gradually evolve toward a better, faster 3-D cycle.  The greatest rewards will accrue to enterprises that climb each hill with a vision of the pinnacle, adjusting as they learn.  These organizations will attract more revenue and investment.  Companies that don’t capitalize on the possibilities will be relegated to hoping for acquisition by those that do.

Admittedly, I’m pretty bad at communicating graphically, but I’ve attempted to draft a rudimentary visual of what the architecture to support a state-of-the-art 3-D Cycle could look like (in Figure 4 below), as a conceptual illustration for facilitating discussion.

The convergence of cloud business intelligence (BI) technology and traditional advanced planning solutions supports my point, and that is definitely happening.

As the unstoppable train of time pulls us into the weekend, I leave you with this thought to ponder: 

“Life is short, so live it well, in gratitude, honesty and hope, and never take it for granted.”

Figure 4

The Potential for Proven Analytics and Planning Tools in Healthcare Delivery

I’ve spent time in a hospital.  I was well cared for, but I didn’t like it, and I worried about the cost and how well I would be able to recover (pretty well, so far!)  Also, my daughter is a doctor (obviously takes after her mom!), so healthcare is obviously an area of high interest for me.

To say that managing a large, disaggregated system such as healthcare delivery with its multitude of individual parts, including patients, physicians, clinics, hospitals, pharmacies, rehabilitation services, home nurses, and more is a daunting task would be an understatement.

Like other service or manufacturing systems, different stakeholders have different goals, making the task even more challenging.

Patients want safe, effective care with low insurance premiums. 

Payers, usually not the patient, want low cost. 

Health care providers want improved outcomes, but also efficiency.

The Institute of Medicine has identified six quality aims for twenty-first century healthcare:  safety, effectiveness, timeliness, patient-centeredness, efficiency, and equity.  Achieving these goals in a complex system will require an holistic understanding of the needs and goals of all stakeholders and simultaneously optimizing the tradeoffs among them.

This, in turn, cannot be achieved without leveraging the tools that have been developed in other industries.  These have been well-known and are summarized in the table below.

While the bulk of the work and benefits related to these tools will lie at the organization level, such techniques can be applied directly to healthcare systems, beginning at the environmental level and working back left down to the patient, as indicated by the check marks in the table.

A few examples of specific challenges that can be addressed through systems analysis and planning solutions include the following:

1 – Optimal allocation of funding

2 – Improving patient flow through rooms and other resources

3 – Capacity management and planning

4 – Staff scheduling

5 – Forecasting, distributing and balancing inventories, both medical/surgical and pharmaceuticals

6 – Evaluation of blood supply networks

Expanding on example #5 (above), supply chain management solutions help forecast demand for services and supplies and plan to meet the demand with people, equipment and inventory.  Longer term mismatches can be minimized through sales and operations planning, while short-term challenges are addressed with inventory rebalancing, and scheduling.

Systems analysis techniques have been developed over many years and are based on a large body of knowledge.  These types of analytical approaches, while very powerful, require appropriate tools and expertise to apply them efficiently and effectively.  Many healthcare delivery organizations have invested in staff who have experience with some of these tools, including lean thinking in process design and six-sigma in supply chain management.  There are also instances where some of the techniques under “Optimizing Results” are being applied, as well as predictive modeling and artificial intelligence.  But, more remains to be done, even in the crucial, but less hyped, areas like inventory management.  Some healthcare providers may initially need to depend on resources external to their own organizations as they build their internal capabilities.

I leave you with a thought for the weekend – “Life is full of tradeoffs.  Choose wisely!”

Metrics, Symptoms and Cash Flow

Metrics can tell us if we are moving in the right or wrong direction and that, in itself, is useful.  However, metrics by themselves do not help us assess our competitive position or aid us in prioritizing our efforts to improve.

To understand our competitive position, metrics need to be benchmarked against comparable peers. Benchmarking studies are available, some of them free.  They tell us where we stand relative to others in the industry, provided the study in question has sufficient other data points from your industry (or sub-industry segment).

Many times, getting relevant benchmarks proves challenging.  But once we have the benchmarks, then what?

Does it matter if we do not perform as well as the benchmark of a particular metric?  If that metric affects revenue growth, margins, return on assets, or available capital, it may matter significantly.

But, we are left to determine how to improve the metrics and with which metrics to start.  

Consider an alternative path.  Begin with the undesirable business symptoms that keep you up at night and give you that bad feeling in the pit of your stomach.

Relate business processes to symptoms and map potential root causes within each business process to undesirable business symptoms.

Multiple root causes in multiple business processes can relate to a single symptom.  On the other hand, a single root cause may be causing multiple undesirable symptoms.  Consequently, we must quantify and prioritize the root causes.

“Finding the Value in Your Value Network” outlines a straightforward, systematic approach to prioritizing and accelerating process improvements.  I hope you will take a look at that article and let me know your thoughts.

Thanks for having a read.  Remember that “You cannot do a kindness too soon, for you never know how soon it will be too late.”

Have a wonderful weekend!