Analysis to Action: Decision-Making Models

All of us, except for newborns, have to make decisions. When I go to the store, I have to make decisions. As I drive, I have to make decisions. Many of these decisions come naturally; but what if the analysis is more complex? As an engineer, at work, I often have several choices to make – but the key to making effective decisions (and keeping the corporate overlords happy) is building models. I’ve personally seen the amazing impact of using analytical models to generally achieve better outcomes. In this article, I’d like to share some of my thoughts and my approach to decision making.

Understanding Decision-Making Models: An Overview

When faced with several options, we use various approaches to making decisions. For instance, when we go to a grocery store to buy pasta, we may come across a few brands that are priced differently. While looking at the brands, we may notice the colour of the pasta, we may notice whether it was made of organic flour or not and several other factors. Eventually, we choose a pasta brand, go to the check out, pay and leave. Several factors went into making that decision. But this was an example of a low stake situation. What about when something is more complex? For instance, if your 10 year old car got into a fender bender and you had the choice between repairing the car for $4000 or to buy another car. How would you make that decision?

After observing myself (and some close friends and family) make decisions, I think we can boil decision-making down to three approaches:

Intuitive Decision Making Models: This is all about trusting your instincts. Sometimes, we just have a hunch that something is either right or wrong, and we act accordingly. For example, imagine you’re on a date with someone who seems perfect on the surface, but there’s just something that doesn’t sit right with you. You decide to block their number, and then a week later, you stumble upon their name in the newspaper, arrested for animal abuse. (True story, unfortunately!)
Rational Decision-Making Model: This model follows a logical, step-by-step process to identify the problem, gather information, evaluate alternatives, and select the best option. For example, with the fender bender example – you might want to jot down the pros and cons of fixing the fender bender and the pros and cons of buying another car. It could be helpful to crunch the numbers and see how much each option would cost in the long run. And then make that decision.
Pattern Recognition Decision Model: This model relies on pattern recognition and rapid assessment of situations. I have a colleague at work, let’s call him Jim, who has about 25 years of experience, someone I really admire and I know to be a total genius. Once I was on a Teams call and was trying to troubleshoot a problem for a customer (this was during Covid, when travel was kept at a minimum), and Jim overhears my conversation, walks up to me and says, “I think I had a similar problem 17 years ago. This may be because they are at an altitude which results in a lower atmospheric pressure. Ask them to change xyz parameters”. And guess what? That was the problem. Another example I can think of is when you have played chess long enough, the positional arrangement of the chess pieces becomes second nature to you, and you can generally recognize the patterns and guess the next move, especially when time is limited. One thing to note here is if you practice something a ton of times, then you start recognizing patterns and this becomes an intuitive process for you. The difference between the first model and this model is that this came about through practice.

By understanding these different models, we can choose the most appropriate approach for each unique decision-making scenario we encounter. Generally however, the second and third options or a combination of the two are the best ways of going about making decisions.

The Power of Quantitative Decision Analysis

Quantitative decision analysis is a powerful tool that brings mathematical rigor to the decision-making process. By utilizing numerical data and statistical techniques, we can objectively evaluate different options and predict potential outcomes with greater accuracy.

In my experience, the benefits of quantitative decision analysis extend far beyond the work. Here are some key advantages:

Objectivity: By relying on hard data rather than subjective opinions, we can minimize personal biases and make more impartial decisions.
Consistency: Quantitative methods provide a standardized approach, ensuring that similar decisions are made consistently across different situations or team members.
Scalability: These techniques can be applied to both small-scale personal choices and large-scale business decisions, making them versatile tools in our decision-making toolkit.

To illustrate the power of quantitative decision analysis, consider the following table comparing two phones. In this example, we’re only looking at a couple of factors, although, in real life, we may be looking at multiple factors that go into making that decision:

Phone	Cost	Storage Space	Security Updates
Option A	$500	64 GB	5 years
Option B	$700	128 GB	3 years

How would you go about making your decision here? The more expensive option does not give you security updates for as long as the cheaper option; but you don’t have as much storage in the cheaper option? Which would you choose? Putting things down in a tabular form (or a spreadsheet) becomes a pretty useful tool in decision making. I can now start ranking what I need of my phone – perhaps, I don’t really care about storage as much as I care about security updates. Or perhaps, the price is the greatest factor in my decision making process. Maybe there are other features that I will need to start considering – but regardless, tabulating these things become an important, data-driven method of making decisions.

Embracing Data-Driven Decision Making: Why It Matters

Data-driven decision making has become more critical than ever. By harnessing the power of data and analytics, we can uncover valuable insights that drive better outcomes across all aspects of our lives and businesses.

Here are some compelling reasons why embracing data-driven decision making is crucial:

Improved Accuracy: Data-driven decisions are based on factual evidence rather than intuition or guesswork, leading to more accurate and reliable outcomes.
Enhanced Efficiency: By identifying patterns and trends in data, we can streamline processes and allocate resources more effectively.
Increased Agility: Real-time data analysis allows us to respond quickly to changing market conditions or emerging opportunities.
Better Risk Management: Data-driven approaches help us identify potential risks and develop mitigation strategies proactively.

To fully embrace data-driven decision making, we can make more effective decisions; and more importantly, communicate the reasons why we made those decisions more effectively.

Optimization Techniques: Maximizing Results in Complex Scenarios

Optimization techniques are mathematical methods designed to find the best possible solution among a set of alternatives, given certain constraints. These techniques are particularly useful when dealing with complex scenarios involving multiple variables and conflicting objectives.

Some common optimization techniques include:

Linear Programming: Used to optimize linear objective functions subject to linear constraints.
Integer Programming: Deals with optimization problems where some or all variables must be integers.
Nonlinear Programming: Addresses optimization problems with nonlinear objective functions or constraints.

In my work and life, I’ve found that optimization techniques can be applied to a wide range of decision-making challenges, such as:

Resource Allocation: Determining the most efficient way to distribute limited resources across various projects or departments.
Throughput Management: Optimizing process times, routes, and production schedules.
Portfolio Management: Balancing risk and return in investment portfolios.

By leveraging these powerful optimization techniques, we can tackle complex decision-making scenarios with greater confidence and achieve superior results.

Cognitive Biases: Recognizing and Overcoming Mental Pitfalls

As human decision-makers, we are all susceptible to cognitive biases – systematic errors in thinking that can affect our judgment and decision-making processes. Recognizing and overcoming these biases is crucial for making more rational and effective decisions.

Some common cognitive biases to be aware of include:

Confirmation Bias: The tendency to seek out information that confirms our existing beliefs while ignoring contradictory evidence.
Anchoring Bias: Relying too heavily on the first piece of information encountered when making decisions.
Sunk Cost Fallacy: Continuing to invest in a failing project or decision due to past investments, rather than cutting losses.
Availability Heuristic: Overestimating the likelihood of events based on how easily they come to mind.

To overcome these biases, we can employ several strategies:

Seek Diverse Perspectives: Actively seek out opinions and information that challenge our existing beliefs.
Use Structured Decision-Making Processes: Implement formal decision-making models to reduce the impact of personal biases.
Practice Metacognition: Regularly reflect on our thought processes and decision-making patterns.

By acknowledging and addressing our cognitive biases, we can significantly improve the quality of our decisions and achieve better outcomes.

From Theory to Practice: Implementing Decision-Making Models

While understanding decision-making models is crucial, the real value lies in their practical application. Implementing these models effectively requires a systematic approach and a commitment to continuous improvement.

Here are some key steps to successfully implement decision-making models in your organization or personal life:

Identify Suitable Decisions: Not all decisions require complex models. Focus on high-impact, recurring decisions that would benefit from a structured approach.
Choose the Right Model: Select a decision-making model that aligns with the nature of the decision and your organizational culture.
Gather Relevant Data: Ensure you have access to accurate and timely data to inform your decision-making process.
Train and Educate: Invest in training programs to help team members understand and apply decision-making models effectively.
Iterate and Refine: Continuously evaluate the effectiveness of your decision-making processes and refine them based on outcomes and feedback.

Remember, implementing decision-making models is an ongoing process that requires patience and persistence. The rewards, however, are well worth the effort.

Decisions and Outcomes

One may be mistaken at this point into thinking that good decisions lead to good outcomes. I really wish this were true, but life is, in general, uncertain. And a good decision is essentially an attempt to increase the chances of a positive outcome based on the variables we have control over. In general, we can consider the following four scenarios:

Good Decision leading to Good Outcome: This is the ideal situation and more often than not, it means you have minimized the uncertainty in your calculations.
Good Decision leading to Bad Outcome: This is not what you expected, but you can be certain that you gave it your best effort. There is uncertainty in your calculations, but in the next iteration, when you take into account some unknown variable, you may achieve a better result. This is simply bad luck at this moment.
Bad Decision leading to a Good Outcome: Pure luck. This is not a replicable process and it is more likely than not that if you make this decision again, you will end up with a negative outcome.
Bad Decision leading to a Bad Outcome: Well, you brought it upon yourself.

Spreadsheets for Decision-Making Processes

Spreadsheets are amazing tools that can greatly enhance our decision-making processes. They provide a flexible and user-friendly platform for organizing data, performing calculations, and visualizing results. Let me show you how we can make the most out of spreadsheets:

Data Organization: Use spreadsheets to collect and structure relevant data in a clear and easily accessible format.
Scenario Analysis: Create multiple scenarios by adjusting key variables and instantly see how they impact the outcomes.
Decision Trees: Build simple decision trees to map out different choices and their potential consequences.
Weighted Decision Matrices: Develop matrices that assign weights to various decision criteria and calculate overall scores for different options.
Monte Carlo Simulations: Utilize spreadsheet functions to run basic Monte Carlo simulations for risk analysis.

To take your decision-making skills to the next level, I strongly encourage you to start using spreadsheets today. Begin by creating a template for a decision you frequently face, incorporating relevant data and decision criteria. As you become more comfortable with spreadsheet-based decision-making, you’ll notice yourself making more informed and efficient choices in both your personal and professional life.

Conclusion: Empowering Aspects of Your Life with Effective Decision-Making

As I’ve explored in this article, leveraging decision-making models can dramatically improve our ability to make informed choices and achieve optimal results. From quantitative analysis and data-driven approaches to predictive modeling and optimization techniques, these tools empower us to navigate complex decisions with greater confidence and precision.

By recognizing and overcoming cognitive biases, implementing structured decision-making processes, and continuously measuring and refining our approaches, we can elevate the quality of our decisions across all aspects of life. And perhaps, spreadsheets are among the most accessible tools available to us to make more informed decisions. In future blog posts, I’ll explore more on decision making with spreadsheets.