Simulation Modeling in Decision Making

Most engineering and business forecasts still rely on single-number estimates: one MTBF, one warranty-return rate, one “expected” portfolio return. Monte Carlo simulation flips that mindset by treating every key input as a distribution instead of a constant, then running thousands of virtual futures to see the full range of possible outcomes. Instead of asking “what will happen,” you start asking “what is the probability that we hit our reliability target or our financial goal under realistic variability and uncertainty.” For reliability engineers and decision makers, this becomes a virtual test lab and a virtual market at the same time. You can combine ALT or run-to-failure data, usage variability, and stress profiles to project field failures, while also modeling revenue, cost, or portfolio risk using the same framework. The result is a more honest conversation with stakeholders, framed in probabilities and risk envelopes instead of optimistic point estimates.

𝙒𝙝𝙖𝙩 𝙞𝙛 𝙮𝙤𝙪𝙧 𝙛𝙖𝙘𝙩𝙤𝙧𝙮 𝙤𝙣𝙡𝙮 𝙬𝙤𝙧𝙠𝙨 𝙗𝙚𝙘𝙖𝙪𝙨𝙚 𝙧𝙚𝙖𝙡𝙞𝙩𝙮 𝙝𝙖𝙨𝙣’𝙩 𝙩𝙚𝙨𝙩𝙚𝙙 𝙞𝙩 𝙮𝙚𝙩? Most plants look stable— until demand shifts, a resource slips, or variability shows up where no one expected it. That’s when leaders realize the system wasn’t designed for reality. It was designed for assumptions. This is why simulation-based decision making—especially Discrete Event Simulation (DES)—has become essential for smart plants. Not to predict the future. But to stress-test the system before the system is forced to respond. Here’s what DES actually validates—end to end: 1️⃣ 𝙋𝙧𝙤𝙘𝙚𝙨𝙨 𝙁𝙡𝙤𝙬 𝙊𝙥𝙩𝙞𝙢𝙞𝙯𝙖𝙩𝙞𝙤𝙣 DES shows how material and information truly move—not how the routing sheet claims they do. 2️⃣ 𝙀𝙦𝙪𝙞𝙥𝙢𝙚𝙣𝙩 𝙐𝙩𝙞𝙡𝙞𝙯𝙖𝙩𝙞𝙤𝙣 𝘼𝙣𝙖𝙡𝙮𝙨𝙞𝙨 High utilization can hide starvation and blocking. DES exposes when assets look busy but flow is unhealthy. 3️⃣ 𝘽𝙤𝙩𝙩𝙡𝙚𝙣𝙚𝙘𝙠 𝙄𝙙𝙚𝙣𝙩𝙞𝙛𝙞𝙘𝙖𝙩𝙞𝙤𝙣 Constraints aren’t static. DES reveals where the bottleneck migrates under different conditions. 4️⃣ 𝙋𝙧𝙤𝙙𝙪𝙘𝙩𝙞𝙤𝙣 𝘾𝙖𝙥𝙖𝙘𝙞𝙩𝙮 𝙋𝙡𝙖𝙣𝙣𝙞𝙣𝙜 Capacity isn’t a fixed number. DES models how throughput behaves under variability, downtime, and mix changes. 5️⃣ 𝘽𝙪𝙛𝙛𝙚𝙧 𝙎𝙞𝙯𝙞𝙣𝙜 Too much buffer masks instability. Too little amplifies it. DES finds the point where flow stays resilient. 6️⃣ 𝘾𝙮𝙘𝙡𝙚 𝙏𝙞𝙢𝙚 𝘿𝙞𝙨𝙩𝙧𝙞𝙗𝙪𝙩𝙞𝙤𝙣 Averages lie. DES reveals the spread—and where volatility is introduced. 7️⃣ 𝙍𝙚𝙨𝙤𝙪𝙧𝙘𝙚 𝘼𝙡𝙡𝙤𝙘𝙖𝙩𝙞𝙤𝙣 People, machines, and automation interact as a system. DES tests the balance before locking it in. 8️⃣ 𝘿𝙚𝙢𝙖𝙣𝙙 𝙁𝙡𝙤𝙬 𝙊𝙥𝙩𝙞𝙢𝙞𝙯𝙖𝙩𝙞𝙤𝙣 DES connects demand patterns to execution reality—without overloading the system. 9️⃣ 𝙏𝙧𝙞𝙖𝙡 𝘽𝙪𝙞𝙡𝙙 𝙎𝙘𝙚𝙣𝙖𝙧𝙞𝙤 𝘼𝙣𝙖𝙡𝙮𝙨𝙞𝙨 Instead of learning after launch, DES lets teams explore “what if” scenarios before they become problems. 🔟 𝘿𝙖𝙩𝙖-𝘿𝙧𝙞𝙫𝙚𝙣 𝙄𝙣𝙫𝙚𝙨𝙩𝙢𝙚𝙣𝙩 𝘿𝙚𝙘𝙞𝙨𝙞𝙤𝙣𝙨 Every capex decision is validated against system behavior—not isolated ROI logic. This is the real shift leaders are making: 𝙁𝙧𝙤𝙢 𝙩𝙧𝙞𝙖𝙡 𝙗𝙪𝙞𝙡𝙙𝙨 → 𝙩𝙤 𝙫𝙖𝙡𝙞𝙙𝙖𝙩𝙚𝙙 𝙨𝙘𝙚𝙣𝙖𝙧𝙞𝙤𝙨 𝙁𝙧𝙤𝙢 𝙤𝙥𝙞𝙣𝙞𝙤𝙣𝙨 → 𝙩𝙤 𝙚𝙫𝙞𝙙𝙚𝙣𝙘𝙚 𝙁𝙧𝙤𝙢 𝙛𝙞𝙧𝙚𝙛𝙞𝙜𝙝𝙩𝙞𝙣𝙜 → 𝙩𝙤 𝙙𝙚𝙨𝙞𝙜𝙣𝙚𝙙 𝙨𝙩𝙖𝙗𝙞𝙡𝙞𝙩𝙮 Simulation doesn’t improve factories. It reveals whether the system was ever ready. 𝙄𝙛 𝙮𝙤𝙪’𝙧𝙚 𝙨𝙘𝙖𝙡𝙞𝙣𝙜 𝙥𝙧𝙤𝙙𝙪𝙘𝙩𝙞𝙤𝙣, 𝙞𝙣𝙩𝙧𝙤𝙙𝙪𝙘𝙞𝙣𝙜 𝙖𝙪𝙩𝙤𝙢𝙖𝙩𝙞𝙤𝙣, 𝙤𝙧 𝙧𝙚𝙗𝙖𝙡𝙖𝙣𝙘𝙞𝙣𝙜 𝙘𝙖𝙥𝙖𝙘𝙞𝙩𝙮— 𝙩𝙝𝙚 𝙦𝙪𝙚𝙨𝙩𝙞𝙤𝙣 𝙞𝙨𝙣’𝙩 𝙘𝙖𝙣 𝙩𝙝𝙚 𝙡𝙞𝙣𝙚 𝙧𝙪𝙣?

Running simulations: base model vs. lookahead model I see people posting on the use of “simulations” for planning inventory policies. If you are using a lookahead model (which is typical for most real-world inventory problems), there are two models where simulation can be used:   1.    The base model, which can be a simulator or the real world. 2.    The lookahead model, which is used in the policy for planning the future to make a decision now. See the figure below - I use the same notational style for both models, but the lookahead model uses tildes on each variables, which also carry two time subscripts: the point in time we are making the decision, and the time period within the lookahead model.   The base model is used to evaluate the policy, and is needed to perform any parameter tuning. The base model can be based on history or a simulation of what you think the future can be.   When simulating inventory policies, special care has to be used because we do not have historical data on market demand – we typically just have sales, which can be “censored” (a topic that has been recognized in the inventory literature for over 60 years). For example, if we run out of product (and there is no back ordering), we lose the sales, which typically means that we do not see (or record) them.   I find it is generally best to run simulations using mathematical models of uncertainty so that we can run many simulations, testing different policies. Stockouts depend on properly simulating the tails of distributions, along with market shifts, price changes and supply chain disruptions. There are, of course, settings where you have no choice but to test your ideas in the field. It is expensive, risky, and slow, but sometimes you just have no choice, especially when you have to capture human behavior.   If your policy requires planning into the future, you really need to be using a stochastic (probabilistic) model of the future which properly captures the tails of distributions. With long lead times, you should also plan for the possibility of significant disruptions, which can mean that you also have to capture the decisions you might make in the future. See chapter 19 of:   https://lnkd.in/dB99tHtM (“tinyurl.com/” with “RLandSO”)   for an in-depth treatment of direct lookahead policies. #supplychain #inventory  Nicolas Vandeput Joannes Vermorel

A "sampled success metric" is a performance measure or evaluation criterion calculated from a sample or subset of data rather than the entire population. Its calculation often involves higher costs per sample, such as manual review, leading to a trade-off between sample size and metric accuracy/sensitivity. In this tech blog, written by the data science team from Shopify, the discussion revolves around how the team leverages Monte Carlo simulation to understand metric variability under various scenarios to help the team make the right trade-offs. Initially, the team defines simulation metrics to describe the variability of the sampled success metric. For instance, if the actual success metric is decreasing over time, the metric could indicate how many months of sampled success metric would show a decrease, termed as "1-month decreases observed". Then, the team defines the distribution to run the Monte Carlo simulation. Monte Carlo simulation, a computational technique using random sampling to estimate outcomes of complex systems or processes with uncertain inputs, draws samples from a dedicated distribution that matches business needs. Based on past observations, the team’s application follows a Poisson distribution. Next comes the massive simulation phase, where the team runs multiple simulations for one parameter and then changes various parameters to simulate different scenarios. The goal is to quantify how much the sample mean will differ from the underlying population mean given realistic assumptions. The final result provides a clear statistical distribution of how much extra sample size could lead to metrics variability decrease and increased accuracy. This case study demonstrates that Monte Carlo simulation could be a valuable toolkit to add to your decision-making and data science knowledge. #datascience #analytics #metrics #algorithms #simulation #montecarlo #decisionmaking – – –  Check out the "Snacks Weekly on Data Science" podcast and subscribe, where I explain in more detail the concepts discussed in this and future posts:    -- Spotify: https://lnkd.in/gKgaMvbh   -- Apple Podcast: https://lnkd.in/gj6aPBBY    -- Youtube: https://lnkd.in/gcwPeBmR https://lnkd.in/dKnrZzzV 

Which heatmap methodology makes more sense 3x3 or 5x5? RAW@AI: Great question—choosing between a 3x3 or a 5x5 heatmap is something risk managers often debate. Let's first explore your context briefly: Are you using heatmaps because stakeholders or auditors expect something visual and colorful once a year, or are your executives actively making decisions based on these outputs? If it's the former—simply providing a colorful visual to tick an audit or compliance box—either 3x3 or 5x5 can serve that purpose, though a 3x3 is typically simpler and quicker for stakeholders to grasp. If your risk assessment is used for genuine strategic decisions, however, neither approach is ideal. Here's why: The core issue with qualitative matrices like 3x3 or 5x5 heatmaps is that they suffer from subjectivity and inconsistency. Different people interpret "high" or "medium" differently, and there's little meaningful difference between a risk rated as "4" versus one rated as "3". In practice, these ratings seldom translate directly into actionable insights or inform critical decisions clearly. A better approach—and here's where the evolution of your risk management practice comes into play—is to gradually shift towards more quantitative methods that directly integrate into decision-making. For example, rather than trying to fit a complex reality into arbitrary categories, you could use a decision tree or Monte Carlo simulation to quantitatively evaluate actual outcomes and their probabilities. This approach provides clearer insight into how uncertainties directly affect your objectives and shows decision-makers the real-world implications of their choices. Consider this practical example: Imagine you're evaluating the risk of operational downtime in your supply chain. Rather than rating it as "medium likelihood, high impact" on a heatmap, you could model potential downtime scenarios using Monte Carlo simulations. You'd quantify how often downtime might occur, how long it would last, and what its financial impact would be. Decision-makers then receive clear, numeric outputs such as "there's a 40% chance annual losses will exceed $500,000 under our current maintenance schedule." That kind of insight directly informs whether investing more in preventive maintenance is justified. I recall from our previous exchanges that you mentioned the importance of clearly communicating risks to executives and stakeholders. Decision trees, tornado diagrams, and simulations don't just provide clarity—they communicate risk information in the language that executives speak: dollars, timeline impacts, and strategic trade-offs. But I know switching entirely overnight might be challenging. So, perhaps consider a hybrid approach: continue briefly using your heatmap (3x3 for simplicity), while gradually introducing these more quantitative methods on a key project or decision. Over time, stakeholders will start experiencing firsthand the value of more precise and actionable data.

In recent conversations from New York to Belém, the global business leaders I’ve met with have asked the same type of question: How do we build value chains that withstand disruption, meet evolving regulations, and even achieve a green margin?   The answer is data visibility and scenario simulation, with AI as your scalability engine. Step 1️⃣: Gain real visibility, which is your backbone of resilience. 🔹You need to understand the natural resource inputs you rely on, your environmental footprint down to the SKU level, and the climate-related risks in your suppliers’ and distributors’ locations.   Step 2️⃣: Turn to digital simulation and modeling to replace guesswork. 🔹When you test possible trade-offs (think cost, quality, recycled content, and regulatory impact) at the design stage, you can optimize products and processes before you invest in production.   Step 3️⃣: Close the visibility-to-action gap by investing in AI resources for sustainability. 🔹By connecting sustainability, operational, and financial data within the ERP, AI can pull the information you need and recommend next steps directly within the systems where decisions are already made.   González Byass is putting these steps into action. With SAP Responsible Design and Production, they've increased recycled content and put the focus back on their actual product: wine, not packaging.

If Your Risk Reports Still Show One Outcome… You’re Not Managing Uncertainty. You’re Just Guessing. Most risk reports still show a single number. One forecast. One “best guess.” One illusion of certainty. But real-world risk isn’t a straight line. It’s a messy cloud of possibilities. And pretending otherwise? That’s not leadership. That’s comfort disguised as control. That’s where Monte Carlo Simulation changes everything. It doesn’t just show you what might happen. It shows you how often it might happen, how bad it could get, and what’s really driving the uncertainty. It lets you: • Model thousands of scenarios, not just one • Understand the range of outcomes—not just the average • See the probability distribution behind your deadlines, costs, and assumptions • And most importantly—help make smarter decisions when it matters most But let’s be clear: We’re not saying Monte Carlo is for every risk. It’s not for everything. It’s for the critical, the strategic, and the high-stakes—where the cost of being wrong is just too high. And no—I’m not against qualitative risk analysis. It has its place. It’s respected. Especially when data is limited or the situation is still evolving. But we need to be honest: You can’t just say a risk has a “4” probability and a “High” impact and expect that to drive a decision. How high is high? What does a “4” even mean? What’s the actual cost, delay, or disruption? I was once asked: “How do you quantify a reputation risk?” I said—don’t try to quantify the label. Reputation risk is an outcome. Let’s analyze the real drivers—a data breach, a safety failure, a governance lapse. That’s where quantification begins—and clarity emerges. Now, will AI and predictive models replace Monte Carlo? They’re powerful. They’re advancing. But right now—AI still struggles with explainability, transparency, and buy-in at the leadership level. Monte Carlo remains one of the few tools that brings probabilistic thinking to the table in a way executives can understand and trust. We just released a new infographic that breaks down Monte Carlo Simulation— not just what it is, but how it actually works, step by step. Bottom line: If you’re still using fixed estimates in a variable world, you’re not managing risk. You’re just simplifying it. As risk leaders and professionals, we need tools in our toolbox. Because your value is in how you tailor those tools to serve your organization’s reality. Let’s keep building our knowledge together. Let’s help each other navigate this VUCAD world. Let’s share mistakes—and celebrate winnings. What’s your take—have you used Monte Carlo or other probabilistic models to shape real decisions? Share your experience in the comments ⤵ ♻ Found this useful? Share it with your team. 💡 Follow Fayadh Alenezi, PhD for more insights. 📌 Save this post for future reference.

BHA Optimization Through Advanced Simulation Today, designing a BHA without advanced simulation is no longer a technical decision it is a gamble. The complexity of modern wells does not allow us to rely solely on past experience or empirical rules when proven tools exist to predict actual BHA behavior before running in hole. Advanced simulation provides a quantitative, objective understanding of BHA directional response, including build, hold, or drop tendency, expected dogleg severity, and sensitivity to changes in WOB, RPM, and flow rate. This removes assumptions and significantly reduces reactive corrections while drilling, which typically result in lower ROP, increased tool wear, and unnecessary non-productive time. From a mechanical standpoint, ignoring dynamic simulation means accepting the risk of destructive vibrations such as stick-slip, whirl, and bit bounce. These conditions directly impact drilling performance and drastically shorten the life of motors, MWD, and LWD tools. Simulation allows unstable operating windows to be identified in advance and clear, safe parameter limits to be defined before downhole failures occur. Equally critical is BHA. wellbore contact modeling. Advanced simulation helps control lateral forces, torque and drag, and the development of micro doglegs that lead to poor wellbore quality. A poorly constructed well has a direct and lasting impact on casing runs, completions, and overall well cost. These issues cannot be fixed later they are created during drilling. Operationally, advanced simulation shifts the workflow from correcting while drilling to drilling it right the first time. It reduces corrective trips, improves ROP consistency, and delivers higher quality wells, particularly in long sections, hard formations, or directionally sensitive intervals. In my experience, when a BHA decision is not supported by simulation, the risk is transferred directly to the well. Advanced simulation is not a luxury or a value added option it is a minimum technical requirement for efficient, controlled, and economically responsible drilling.