Decision SCIENCE

Let us start with one basic truth.

We make decisions every day.

Starting from the second we open our eyes in the morning, whether to get up or not to pee or should I try and sleep but circumstances make you get up anyway, then the dogs see you up and start whining for you to take them out. 

Then later in the day you may step into work and make some big decisions that may affect a lot of people around you. 

So, basically we are making decisions every second of our lives. Which series to watch, what to buy, which shoes to wear, color code your clothes to match with something. Whether you want to believe it or not, you have been making decisions all your life. 

So some decisions are small

But some decisions are bigger at work.

• Which product should the company launch?
• Which project should get priority?
• How much inventory should be kept?
• Which route should reduce transportation cost?
• Which strategy should be used when competitors are also planning their own drama?

And then there are decisions that look simple from outside but are actually full of confusion, uncertainty, risk, money, people, pressure, ego, and Excel sheets that should have been illegal.

That is where decision science comes in.

Decision science is basically the study of how decisions are made, how they should be made, and how they can be improved.

In dumbass words:

Decision science helps you make better decisions when life, business, data, people and uncertainty are all standing around you and shouting different things.

It does not remove confusion completely.

Nothing does.

But it gives you a structured way to deal with confusion.

And honestly, that itself is a big achievement.

Decisions need science because most decisions are not made in perfect conditions.

If life was simple, decisions would be easy.

• You would have full information.
• You would know the future.
• People would behave logically.
• Competitors would sit quietly.
• Customers would tell the truth.
• Costs would remain stable.
• Machines would not break down.
• Employees would not resign exactly when you need them.
• And every plan would work exactly as written in the PowerPoint presentation.
• But of course, life is not that kind.

In real life, decisions are made with incomplete information, limited resources, uncertainty, risk, pressure, time limits and sometimes one senior person saying, “Let us do it immediately,” without knowing what “it” even means.

Decision science tries to bring some order into this madness.

It uses tools, models, data, logic, probability, economics, statistics, psychology and operations research to help people make better decisions.

That does not mean every decision becomes perfect.

It means the decision becomes more informed.

There is a difference.

A perfect decision is rare.

An informed decision is possible.

A random guess says:

“Let us do this because I feel it will work.”

A decision science approach says:

“Let us identify the options, understand the risks, estimate the possible outcomes, compare the alternatives and then decide.”

Same decision.

Less stupidity.

That is the point.

Decision science is a set of methods and tools used to support decision-making.

Decision science is a set of quantitative tools for informing individual and population-level decision-making. 

It includes areas like operations research, microeconomics, statistical inference, management control, psychology, computer science, decision analysis, risk analysis, cost-benefit analysis, optimization, simulation and behavioural decision theory. 

Now, that sounds very academic.

So let us say it properly.

Decision science is the art and science of making better choices.

• It is not just about data.
• It is not just about mathematics.
• It is not just about psychology.
• It is not just about business experience.
• It is a mixture.

It asks:

• What are the choices?
• What are the constraints?
• What can go wrong?
• What can go right?
• What is the cost?
• What is the benefit?
• What is the risk?
• What does the data say?
• What does human behaviour say?
• What is the best possible decision under the given situation?

So, decision science is not one single subject sitting alone in a corner.

It is more like a team meeting between mathematics, business, economics, psychology, statistics and technology.

Thankfully, unlike most team meetings, this one has a purpose.

Decision science helps you answer this question:

Out of all the options available, which option should I choose, and why?

That is it.

Not very scary now, right?

Suppose a company has three possible suppliers.

• Supplier A is cheap but unreliable.
• Supplier B is expensive but reliable.
• Supplier C is average in everything, which is sometimes more dangerous because average people can hide in plain sight.

Now, how do you choose?

A normal person may say:

“Choose the cheapest.”

A cautious person may say:

“Choose the most reliable.”

A confused person may say:

“Let us form a committee.”

Decision science says:

Let us compare cost, reliability, delay risk, quality, past performance and impact on business.

Then decide.

This is the key.

Decision science does not just ask, “What do you want?”

It asks, “What happens if you choose this?”

That is where real decision-making begins.

• Because every decision has consequences.
• Some are visible.
• Some are hidden.
• Some come later and punch you in the face.

Decision science tries to identify them before the punching starts.

Individuals make decisions.

Groups make decisions.

Organisations make decisions.

But they do not make decisions in the same way.

An individual may decide based on personal experience, habit, emotion, comfort, fear, ambition or pure laziness.

For example:

“I will not change the vendor because I have worked with him for years.”

That may be loyalty.

It may also be stupidity with emotional branding.

A group decision is different.

In a group, many people are involved. Everyone has opinions. Some have data. Some have ego. Some have fear. Some have already decided but are pretending to discuss.

Group decisions can be better because more knowledge is available.

But they can also become worse because everyone tries to protect their department, position or backside.

Organisational decisions are even more complicated.

An organisation must think about money, people, customers, operations, law, reputation, risk, time and long-term impact.

A decision that looks good for one department may be bad for the organisation.

For example, 

• Finance may want to reduce cost
• Operations may want better machines
• Marketing may want a bigger campaign
• HR may want more people
• IT may want everyone to stop clicking suspicious links

All of them may be right from their own angle.

Decision science helps bring these angles together.

It gives a structured way to compare options and consequences.

It does not guarantee that everyone will become wise.

But at least it reduces the chances of full-scale decision-making circus.

Normative decision-making is about how decisions should be made.

This is the ideal world version.

It asks:

• What would a rational person do?
• What is the logically correct decision?
• What decision gives the best result if the objective is clear?

For example, suppose a company wants to minimize transportation cost.

There are different warehouses, different markets and different transport costs.

The normative approach says:

Let us calculate the best allocation so that total cost is minimized.

No emotion.

No “I like this route.”

No “This transporter is my old contact.”

No “This looks fine.”

Just logic.

Normative decision-making is like that strict teacher who does not care about excuses.

It says:

• Define the objective.
• List the alternatives.
• Understand the constraints.
• Evaluate outcomes.
• Choose the best option.

In simple words:

Normative decision-making tells you how a decision should be made if everyone behaved rationally.

Which is beautiful.

Also rare.

Because people are people.

And people do not always behave like Excel formulas.

Descriptive decision-making is about how people actually make decisions.

This is where things become more human.

And more embarrassing.

Because in real life, people often do not decide rationally.

They decide based on habit, fear, pressure, bias, limited information, overconfidence, past experience, office politics or because the meeting has already gone on for two hours and everyone wants lunch.

Descriptive decision-making studies real behaviour.

It asks:

• How do people actually choose?
• Why do they ignore data?
• Why do they take risks?
• Why do they avoid risks?
• Why do they follow the crowd?
• Why do they stick to bad decisions?
• Why do they trust one number and ignore ten others?

This is where psychology becomes important.

• A person may know the correct decision but still avoid it because it is uncomfortable. 
• A manager may continue a failing project because a lot of money has already been spent.
• A company may reject a new idea because “we have always done it this way.” That sentence has killed more innovation than budget shortage.

Descriptive decision-making does not assume people are perfect.

It studies people as they are.

• Confused.
• Biased.
• Emotional.
• Overconfident.
• Sometimes brilliant.
• Sometimes deeply committed to bad judgment.

In dumbass words:

Normative decision-making is how people should decide.

Descriptive decision-making is how people actually decide after panic, ego and tea enter the room.

Prescriptive decision-making is the practical one.

It asks:

How can we help people make better decisions?

This is where decision science becomes useful for managers. Because just knowing that people make bad decisions is not enough.

We already knew that.

Look at any office file movement system.

The real question is:

How do we improve decisions?

Prescriptive decision-making gives tools, techniques, models and methods to support better choices. It does not expect people to become perfectly rational robots. It helps them make better decisions despite being human.

For example:

• Use a payoff table to compare alternatives.
• Use expected monetary value to decide under risk.
• Use linear programming to optimize resources.
• Use transportation models to reduce cost.
• Use queuing theory to reduce waiting time.
• Use simulation to test possible outcomes.
• Use CPM and PERT to plan projects.
• Use game theory when competitors are also making moves.

Basically, prescriptive decision-making says:

“Fine, humans are messy. Let us at least give them a calculator, a model and some structure before they cause damage.”

And that is a noble mission.

Decision science is interdisciplinary.

That is a fancy way of saying it borrows from many subjects because one subject alone cannot handle the full drama of decision-making.

From economics, it takes the idea of cost, benefit, trade-offs, scarcity and rational choice. Because every decision has a cost. Even doing nothing has a cost. Sometimes a very expensive one.

From statistics, it takes probability, data analysis, uncertainty and inference.

Because decisions are often made without complete certainty. Statistics helps us understand patterns, risks and likelihoods.

From psychology, it takes human behaviour. Because decisions are not made by machines alone. They are made by people. And people come with bias, fear, ego, confidence, doubt, memory, habits and mood swings.

From operations research, it takes models for optimization, allocation, scheduling, queuing, transportation, assignment and project planning. This is the more technical side. 

It helps answer practical questions like:

• Who should do which job?
• How should goods be transported?
• How should resources be allocated?
• Which project activity is critical?
• How can waiting time be reduced?
• How can profit be maximized or cost minimized?

So decision science is not one subject.

It is a toolkit.

And like any toolkit, the real skill is knowing which tool to use when.

You do not use a hammer to fix everything.

Unless its your......

Buddy, did you just think that?!

Decision science is used almost everywhere decisions are important.

And since decisions are important almost everywhere, decision science has a wide field.

It is used  in business and management, law and education, environmental regulation, military science, public health and public policy. 

Let us understand this simply.

In business, decision science helps in production planning, pricing, marketing, finance, inventory, transport, manpower planning and project management.

In public policy, it helps governments decide how to allocate resources, design programmes and evaluate outcomes.

In healthcare, it can help decide treatment strategies, hospital capacity, waiting time, cost-effectiveness and risk.

In law and regulation, it can help evaluate consequences of rules and policies.

In military planning, it can support strategy, logistics and risk-based decisions.

In education, it can help with planning, resource allocation and performance analysis.

In short, wherever there are limited resources and multiple choices, decision science becomes useful.

And let us be honest, limited resources and multiple choices are basically the permanent condition of life.

• Money is limited
• Time is limited
• People are limited
• Patience is limited
• Common sense is extremely limited

Decision science helps you work within limits.

Business is basically a continuous series of decisions.

• What to produce?
• How much to produce?
• Where to sell?
• Whom to hire?
• How much stock to keep?
• Which machine to use?
• Which project to fund?
• Which market to enter?
• Which customer to focus on?
• Which cost to reduce?
• Which risk to accept?
• Which risk to avoid?

Every business decision affects money, time, resources and people.

A bad decision does not just stay on paper.

• It becomes excess inventory.
• Delayed projects.
• Higher costs.
• Unhappy customers.
• Idle machines.
• Overworked employees.
• Lost profit.

And then someone makes a review presentation called “Way Forward.”

Decision science matters because it gives managers a structured way to think.

It helps them move from:

“I think this is right”

to

“Based on the available data, constraints, alternatives and expected outcomes, this is the better option.”

That sentence may not sound exciting.

But it can save money.

And in business, saving money is also a form of poetry.

That decision science helps identify risks and rewards related to business decisions and uses a rational, objective framework to evaluate possible outcomes. Decision-makers can use analysis and then apply judgment and experience to make better decisions. 

That last part is important.

Decision science does not replace the manager.

It supports the manager.

The model gives insight.

The manager gives judgment.

A model may say Option A is best.

But the manager may know that Option A depends on a supplier who has the reliability of a wet cardboard box.

So the final decision still needs human judgment.

Decision science is not a substitute for thinking.

It is support for better thinking.

Business is basically a continuous series of decisions.

• What to produce?
• How much to produce?
• Where to sell?
• Whom to hire?
• How much stock to keep?
• Which machine to use?
• Which project to fund?
• Which market to enter?
• Which customer to focus on?
• Which cost to reduce?
• Which risk to accept?
• Which risk to avoid?

Every business decision affects money, time, resources and people.

A bad decision does not just stay on paper.

• It becomes excess inventory.
• Delayed projects.
• Higher costs.
• Unhappy customers.
• Idle machines.
• Overworked employees.
• Lost profit.

And then someone makes a review presentation called “Way Forward.”

Decision science matters because it gives managers a structured way to think.

It helps them move from:

“I think this is right”

to

“Based on the available data, constraints, alternatives and expected outcomes, this is the better option.”

That sentence may not sound exciting.

But it can save money.

And in business, saving money is also a form of poetry.

That decision science helps identify risks and rewards related to business decisions and uses a rational, objective framework to evaluate possible outcomes. Decision-makers can use analysis and then apply judgment and experience to make better decisions. 

That last part is important.

Decision science does not replace the manager.

It supports the manager.

The model gives insight.

The manager gives judgment.

A model may say Option A is best.

But the manager may know that Option A depends on a supplier who has the reliability of a wet cardboard box.

So the final decision still needs human judgment.

Decision science is not a substitute for thinking.

It is support for better thinking.