Four Types of Data Analytics: How We Move from Understanding the Past to Predicting
the Future and Taking Strategic Action?

The value of data does not lie simply in collecting it, but in the ability to analyze it and transform it into knowledge that helps us make better decisions. This is why four main levels of data analytics have emerged. Each begins by answering a specific question, then builds upon it at the next level until it reaches the point of recommending appropriate actions for the future. The level of value increases as we move from describing what happened, to explaining why it happened, then predicting what will happen, and finally recommending what should be done to achieve the best results.

four types of analysing data

1- What are the four types of data analytics?

Data Analytics has become one of the most important tools used by individuals, organizations, and governments to make decisions in the modern era. Almost every activity generates data, whether in education, healthcare, business, industry, sports, or even everyday life. However, possessing data alone does not guarantee better decisions, because the true value lies not in the amount of data, but in the ability to transform it into understanding, then into decisions, and finally into actions that achieve better results.

This is why the concept of Data Analytics emerged. It is an organized process aimed at studying and interpreting data, and extracting patterns, relationships, and indicators that help people understand reality, explain its causes, anticipate its future, and then choose the best possible decisions.

Data alone does not make decisions; analysis is what transforms data into knowledge that can be relied upon.

With the development of data science, artificial intelligence, and machine learning, data analytics is no longer limited to knowing what happened in the past. It has become capable of explaining the causes, predicting what may happen in the future, suggesting the best solutions, and even anticipating problems before they appear.

For this reason, data analytics is divided into several progressive levels, with each level building upon the one before it. This allows people to gradually move from simply reading numbers to developing a strategic perspective that helps them shape the future.

Data
↓ What happened?
↓ Why did it happen?
↓ What will happen?
↓ What should I do?
↓ How can I create a better future?

This sequence is known as Types of Data Analytics. Each level answers a different question, uses different tools, and provides greater value than the previous level. Therefore, advanced organizations do not stop at analyzing what happened. Instead, they gradually move toward higher levels that help them anticipate the future, improve performance, reduce risks, and discover new opportunities.

- Why is data analytics important?

Today, people live in a world filled with information, but having more information does not necessarily mean having better understanding. A company may possess millions of records about its customers, a doctor may have the results of hundreds of medical tests, or a student may have dozens of books, yet all of them may still struggle to make the right decision if the data is not analyzed systematically.

Data analytics therefore helps transform scattered information into a clear picture that can be understood, interpreted, and used to make decisions that are more accurate, efficient, and objective.

Without Data Analytics. With Data Analytics.
Decisions based on intuition. Decisions based on evidence.
Difficulty understanding the causes. Understanding relationships and causes.
Delayed reactions. Early prediction of problems.
Waste of time and resources. More efficient use of resources.
Difficulty planning for the future. Building better plans and strategies.

- The core idea of the model:

The model is based on a simple but highly important idea: a person cannot make a good decision simply by knowing what happened. They first need to understand the causes, then anticipate the future, choose the best course of action, and finally think proactively in order to prevent problems before they appear and help create new opportunities.

Each level of analysis answers a new question and adds a higher level of understanding and decision quality.

- Levels of data analytics:

Level. Main question.
Descriptive Analytics. What happened?
Diagnostic Analytics. Why did it happen?
Predictive Analytics. What will happen?
Prescriptive Analytics. What should I do?
Proactive Analytics. How can I create a better future?

- Examples from everyday life:

  • A company reviews its sales to understand the reason for declining profits.
  • A doctor analyzes test results to choose the appropriate treatment.
  • A teacher reviews students' results to identify the causes of poor academic performance.
  • An investor studies market data before making a purchase decision.
  • An athlete analyzes their performance in games to improve their level in the future.

- Connection to the next section:

After understanding the general idea of data analytics, we will begin with the first level of this model: Descriptive Analytics, which represents the starting point for understanding data and answers the fundamental question: What happened?

2- Descriptive Analytics

Descriptive Analytics is the first stage and the foundation upon which all other levels of data analytics are built. Before attempting to understand the causes of a particular problem, predict what may happen in the future, or suggest the best decisions, we must first understand the current reality accurately. For this reason, descriptive analytics focuses on describing events as they actually occurred, without attempting to interpret them or predict their outcomes.

This level answers the fundamental question: What happened? It does not search for causes or provide solutions. Instead, it provides a clear, organized, and accurate picture of the available data so that it can serve as a reliable foundation for the next stages of analysis.

We cannot interpret or improve reality before we understand it as it is.

- What is Descriptive Analytics?

Descriptive Analytics is the process of collecting, organizing, summarizing, and presenting data in a way that makes it easy to understand. This includes the use of tables, statistics, charts, and dashboards, allowing decision-makers to see the current picture quickly and clearly.

It can be considered a "mirror" that reflects the current reality without adding interpretation or prediction. It tells us what happened, how much happened, when it happened, and where it happened, but it does not yet answer why it happened.

Data Collection
↓ Organization
↓ Summarization
↓ Clear Presentation

- Questions it answers:

  • What happened?
  • How many times did it happen?
  • When did it happen?
  • Where did it happen?
  • What is the scale of the phenomenon?
  • How did the numbers change over time?

- Main outputs of Descriptive Analytics:

Output. Purpose.
Tables. Organizing data.
Statistics. Summarizing information numerically.
Charts. Visually highlighting patterns.
Dashboards. Continuously monitoring performance.
Reports. Presenting findings to decision-makers.

- What does Descriptive Analytics not do?

A common misconception is that descriptive analytics explains events, but in reality, it does not. If the data shows that sales decreased by 15%, descriptive analytics simply reports this result. It does not identify the reason for the decline, predict what will happen next, or suggest a way to address the problem.

For this reason, descriptive analytics is only the starting point, while the following stages move toward answering more complex questions.

Knowing what happened is not the end; it is the beginning of the journey toward understanding.

- Examples of Descriptive Analytics:

Field. Example.
Business. This month's sales reached 250,000 dirhams.
Education. 85% of students passed the test.
Healthcare. The hospital received 420 patients this week.
Websites. The website received 30,000 visitors during the month.
Sports. The team achieved 62% possession.

- Benefits of Descriptive Analytics:

  • Providing a clear picture of the current situation.
  • Simplifying large amounts of data.
  • Identifying general patterns.
  • Measuring performance objectively.
  • Supporting the preparation of periodic reports.
  • Providing a foundation for the next analytical stages.

- Examples from everyday life:

  • A mobile app shows the number of steps you walked today.
  • A bank statement shows your total expenses during the month.
  • A teacher calculates the class average.
  • A store manager reviews the number of customers who visited the store this week.
  • A weather app displays the average temperatures over the past few days.

- Connection to the next section:

Once we have an accurate description of what happened, the next question naturally arises: Why did it happen? This is where Diagnostic Analytics comes in. It moves from presenting facts to investigating the causes, relationships, and factors that led to the results revealed by descriptive analytics.

3- Diagnostic Analytics

After descriptive analytics shows us what actually happened, we need to understand the real reason behind those results. Knowing that sales declined, the number of errors increased, or the success rate decreased is not enough to make the right decision, because numbers alone do not explain their causes. This is where Diagnostic Analytics comes in, representing the second stage in the data analytics journey.

This level focuses on answering the fundamental question: Why did it happen? It attempts to discover the causes, relationships, and factors that led to the results revealed by descriptive analytics, so that decision-making does not remain limited to observing symptoms, but extends to understanding the root causes of the problem.

Numbers tell us what happened, while diagnostic analytics reveals why it happened.

- What is Diagnostic Analytics?

Diagnostic Analytics is the process of studying data more deeply to search for the underlying causes that led to a particular result. It uses comparisons, relationship analysis, pattern analysis, and root cause analysis to explain events rather than merely describe them.

When an organization notices declining profits, increasing customer complaints, or rising production costs, diagnostic analytics begins by asking a series of questions to understand the real cause instead of simply presenting the numbers.

Result
↓ Gathering Evidence
↓ Analyzing Relationships
↓ Identifying Causes
↓ Understanding the Problem

- Questions it answers:

  • Why did this change occur?
  • What is the main cause?
  • What factors influenced the outcome?
  • Is there a relationship between several variables?
  • What changed compared with the previous period?
  • Are there direct and indirect causes?

- How does Diagnostic Analytics work?

This type of analysis does not rely on guessing. Instead, it relies on comparing data, studying the relationships between variables, and testing different hypotheses until the most logical explanation supported by evidence is reached.

Step. Objective.
Reviewing the results. Precisely identifying the problem.
Collecting additional data. Obtaining supporting information.
Analyzing relationships. Discovering relationships between variables.
Testing hypotheses. Verifying the validity of potential causes.
Identifying the root cause. Reaching the most accurate explanation.

- Main tools used:

  • Root Cause Analysis.
  • Correlation Analysis.
  • Comparison across time periods.
  • Comparison between branches or departments.
  • Trend Analysis.
  • Variance Analysis.

- Practical example:

Suppose an online store notices a 20% decline in sales.

Descriptive analytics only tells us that sales have decreased, but diagnostic analytics begins searching for the causes:

  • Did prices increase?
  • Did the number of visitors decrease?
  • Did new competition emerge?
  • Did the purchasing process become more complicated?
  • Did the quality of the advertisements decline?

After analyzing the data, it may become clear that the real cause is not the price, but the slow website, which caused a large number of customers to leave before completing their purchases.

Treating symptoms may solve a problem temporarily, but addressing the root cause prevents it from recurring.

- Benefits of Diagnostic Analytics:

  • Understanding the real causes instead of guessing.
  • Reducing the recurrence of problems.
  • Improving decision quality.
  • Identifying improvement priorities.
  • Making optimal use of resources.
  • Increasing the accuracy of future plans.

- Examples from everyday life:

  • A student analyzes the reason for declining grades and discovers that the problem is not the difficulty of the subject, but poor time management.
  • A doctor searches for the underlying cause of symptoms instead of treating only the pain.
  • A company discovers that the increase in complaints is caused by delivery delays, not product quality.
  • A sports coach discovers that declining performance is caused by fatigue, not lack of skill.
  • A family reviews the reasons for increased monthly expenses to identify the true source of spending.

- Connection to the next section:

After understanding why the current results occurred, the natural question becomes: What will happen in the future if the current conditions continue? This is where Predictive Analytics begins. It uses current and historical data to predict trends and future outcomes.

4- Predictive Analytics

After knowing what happened and why it happened, we reach the third level of data analytics, which is Predictive Analytics. At this stage, the analyst no longer focuses only on studying the past, but begins using historical and current data to build logical expectations about what may happen in the future.

This type of analysis is based on a simple principle: events do not occur in a completely random manner, but often follow patterns that can be discovered. If the same conditions are repeated, or if the factors influencing the outcome remain unchanged, future results will often be similar to previous results. Therefore, predictive analytics uses historical data to discover these patterns and then builds predictions from them to help prepare for the future.

The past does not tell us the future with certainty, but it provides the best available evidence for predicting what may happen.

- What is Predictive Analytics?

Predictive Analytics is the process of using data, statistical models, mathematical algorithms, and Machine Learning techniques to estimate future probabilities and predict outcomes before they occur. Its purpose is not to know the future with certainty, but to provide evidence-based predictions that help people make better decisions.

Therefore, the outputs of this type of analysis often take the form of probabilities, future scenarios, growth or decline forecasts, potential risks, changes in customer behavior, or market developments.

Historical Data
↓ Pattern Analysis
↓ Model Building
↓ Predicting the Future

- What question does it answer?

  • What will happen in the future?
  • What is the probability that this event will occur?
  • Will demand increase or decrease?
  • What is the expected trend?
  • What are the potential risks?
  • What is the most likely scenario?

- How does Predictive Analytics work?

Predictive Analytics begins by collecting a large amount of historical data, then searches for recurring patterns within it. After that, it builds a mathematical model capable of using those patterns to produce future predictions. The more accurate, diverse, and high-quality the data, the more reliable the predictions become.

Step. Purpose.
Data Collection. Obtain sufficient historical data.
Pattern Analysis. Identify recurring relationships.
Model Building. Create a predictive model.
Model Testing. Measure the accuracy of predictions.
Generating Predictions. Predict future outcomes.

- Main tools used:

  • Statistics.
  • Trend Analysis.
  • Time Series Analysis.
  • Machine Learning.
  • Regression Models.
  • Artificial Intelligence.

- Practical examples:

Field. Prediction Example.
Commerce. Predicting an increase in demand for a particular product during the summer.
Healthcare. Predicting the probability that a patient will develop certain complications.
Banking. Predicting the probability that a customer will default on a loan.
Education. Predicting the probability of a student's success or need for additional support.
Sports. Predicting the probability of a team's victory based on previous match performance.

- Are predictions always accurate?

No. Prediction does not provide absolute certainty because the future is influenced by many factors that can change at any moment. Therefore, Predictive Analytics does not tell us what will definitely happen; rather, it tells us what is most likely to happen if current conditions remain the same.

For this reason, organizations usually use more than one scenario, such as an optimistic scenario, a realistic scenario, and a pessimistic scenario, so that they are prepared for different possibilities.

Good prediction does not eliminate uncertainty, but it reduces it to a level that helps us make better decisions.

- Benefits of Predictive Analytics:

  • Preparing for the future.
  • Reducing risks.
  • Improving planning.
  • Increasing the efficiency of resource allocation.
  • Discovering opportunities early.
  • Improving the quality of strategic decisions.

- Examples from everyday life:

  • A weather application predicts temperatures for the coming days.
  • An online store recommends products you may want to purchase.
  • A navigation application predicts travel time based on traffic conditions.
  • An electricity company predicts increased consumption during the summer.
  • A student predicts their exam result based on previous grades.

- Relationship with the next section:

Once we can predict what may happen in the future, a more important question emerges: What is the best decision we can make to achieve the best possible outcome? This is where Prescriptive Analytics comes in. It does not merely make predictions, but recommends the best possible actions to achieve the desired objectives.

5- Prescriptive Analytics

After gaining an understanding of what happened, knowing the causes behind it, and predicting what may happen in the future, we reach the fourth level of data analytics: Prescriptive Analytics. This is one of the most valuable levels of analysis because it does not merely present information, interpret it, or predict it. Instead, it moves toward recommending the best actions that should be taken to achieve the best possible outcomes.

Predictive Analytics may tell an organization that demand for one of its products is likely to increase over the coming months, but Prescriptive Analytics answers the more important question: What should we do now to take advantage of this prediction?

Knowing the future is useful, but knowing the best decision for dealing with it is even more valuable.

- What is Prescriptive Analytics?

Prescriptive Analytics is the process of using the results of descriptive, diagnostic, and predictive analytics, then combining them with mathematical models, Artificial Intelligence, and decision-making rules to recommend the optimal action that achieves the greatest benefit, lowest cost, or lowest risk, according to defined objectives.

For this reason, this level of analysis is a powerful tool for supporting managers, leaders, and decision-makers because it does not merely tell them what may happen, but provides them with practical options based on data.

Describe the Reality
↓ Understand the Causes
↓ Predict the Future
↓ Choose the Best Decision

- What question does it answer?

  • What should I do?
  • What is the best decision?
  • Which option provides the greatest benefit?
  • How can I reduce risks?
  • How can I use resources most efficiently?
  • What strategy is most appropriate in this situation?

- How does Prescriptive Analytics work?

Prescriptive Analytics begins by gathering the results of the previous levels, then uses mathematical models, simulation techniques, Artificial Intelligence, and Optimization Algorithms to compare a large number of possible alternatives until it identifies the option that produces the best outcome according to the required criteria.

Step. Purpose.
Data Analysis. Understand the current reality.
Predicting the Future. Identify possible scenarios.
Identifying Alternatives. List all possible options.
Comparing Alternatives. Measure benefits, costs, and risks.
Choosing the Optimal Decision. Achieve the best possible outcome.

- Main tools used:

  • Optimization Algorithms.
  • Simulation.
  • Artificial Intelligence.
  • Decision Support Systems.
  • Scenario Analysis.
  • Business Rules.

- Practical examples:

Field. Example.
Commerce. Recommending the best price to achieve the highest profit.
Transportation. Choosing the shortest route to reduce fuel consumption and travel time.
Healthcare. Recommending the treatment plan most appropriate for the patient.
Manufacturing. Determining the optimal production schedule.
Marketing. Determining the optimal advertising budget.

- Why is it more valuable than prediction?

Because prediction alone is not enough to make a decision. A company may predict that sales will decline over the coming months, but the question remains: What should it do? Should it lower prices? Increase advertising? Improve the product? Enter a new market?

Prescriptive Analytics helps compare all the alternatives and then select the option that achieves the best balance between profit, cost, risk, and time.

The best decision is not always the fastest decision, but the one that delivers the greatest value at the lowest possible cost.

- Benefits of Prescriptive Analytics:

  • Improving decision quality.
  • Reducing risks.
  • Increasing the efficiency of resource use.
  • Achieving the highest possible return.
  • Reducing waste.
  • Accelerating the decision-making process.

- Examples from everyday life:

  • A navigation application recommends the fastest route to your destination.
  • Shopping applications recommend the product most suitable for your needs.
  • A bank recommends the financing plan that best fits your income.
  • A fitness application recommends a training program suited to your current level.
  • Travel applications recommend the best time to book in order to obtain the lowest price.

- Relationship with the next section:

Although Prescriptive Analytics helps select the best decision, the most successful organizations do not wait for problems to appear. Instead, they work to prevent them before they occur and create opportunities before others notice them. This leads us to the highest level in the data analytics hierarchy: Proactive Analytics.

6- Proactive Analytics

Proactive Analytics represents the highest level of data analytics because it does not merely describe the past, explain it, predict the future, or even recommend the best decisions. Instead, it focuses on shaping the future before it imposes itself upon us. At this level, the goal is not merely to solve problems, but to prevent them from appearing in the first place and to search for new opportunities before they become obvious to everyone.

This is why proactive thinking differs from traditional thinking. Instead of waiting for a problem and then searching for a solution, a proactive person asks: How can I prevent this problem before it happens? Instead of waiting for the market to change, they ask: How can I prepare for this change now?

Leaders do not wait for the future; they work to shape it.

- What is Proactive Analytics?

Proactive Analytics is the process of using all the results of previous analyses and combining them with strategic thinking, risk management, and innovation to prepare for future changes before they occur, transform risks into opportunities, and turn opportunities into achievements.

Therefore, this level does not focus on a single question. Instead, it considers the bigger picture and seeks to build a future that is more stable, resilient, and successful.

Understanding the Past
↓ Interpreting the Present
↓ Predicting the Future
↓ Making the Decision
↓ Shaping the Future

- What question does it answer?

  • How can I prepare for the future?
  • How can I prevent a problem before it appears?
  • How can I create new opportunities?
  • How can I increase organizational resilience?
  • How can I continuously improve performance?
  • How can I stay ahead of competitors?

- Characteristics of proactive thinking:

Traditional Thinking. Proactive Thinking.
Addresses the problem after it occurs. Prevents the problem before it happens.
Focuses on the present. Focuses on the future.
Waits for change. Creates change.
Reacts to events. Leads events.
Thinks in the short term. Thinks in the long term.

- How does Proactive Analytics work?

This level relies on continuous data monitoring and tracking changes in the surrounding environment, then uses predictions, scenarios, risk management, and innovation to develop plans that prevent crises before they occur or take advantage of opportunities before competitors.

This is why major global organizations invest a significant portion of their resources in research, development, training, and innovation. They understand that prevention is far less costly than dealing with crises after they occur.

The best way to solve a problem is to prevent it from happening in the first place.

- Practical examples:

Field. Example.
Healthcare. Launching preventive programs before diseases spread.
Business. Developing new products before the market changes.
Cybersecurity. Identifying vulnerabilities before the system is breached.
Education. Designing support programs for students before their performance declines.
Human Resources. Training employees in future skills before they are needed.

- Benefits of Proactive Analytics:

  • Reducing risks before they occur.
  • Increasing the ability to adapt to change.
  • Improving long-term planning.
  • Discovering new opportunities early.
  • Increasing innovation.
  • Achieving a sustainable competitive advantage.
  • Increasing organizational readiness for crises.

- Difference between Prescriptive Analytics and Proactive Analytics:

Prescriptive Analytics. Proactive Analytics.
Chooses the best decision for the current situation. Creates a better future before the need arises.
Focuses on solving problems. Focuses on preventing problems.
Relies on current predictions. Relies on a long-term vision.
Improves performance. Develops the entire system.

- Examples from everyday life:

  • Saving money for emergencies before the need arises.
  • Exercising to maintain good health before illness appears.
  • Learning a new skill before it becomes required in the job market.
  • Backing up files before losing them.
  • Preparing an emergency plan before traveling.

- Relationship with the next section:

After understanding the five levels of data analytics, it becomes easy to see that each level adds new value and builds upon the level before it. In the next section, we will compare these levels together and explain how the thinking process moves from simply describing the past to shaping the future.

- Conclusion:

The five types of data analytics represent an integrated journey that begins with understanding reality, then interpreting it, predicting its future, choosing the best decisions, and finally preparing for what has not yet happened. Each level depends on the level before it, meaning that intelligent decisions and successful strategies cannot be achieved without first moving through the stages of understanding, analysis, and insight.

The journey begins with Descriptive Analytics, which answers the question "What happened?" by organizing data, summarizing it, and presenting it through reports, charts, and performance indicators. It provides the factual picture on which every subsequent analysis depends.

Next comes Diagnostic Analytics, which answers the question "Why did it happen?" by searching for root causes and relationships between variables, so that results are not treated as mere numbers but become understandable events that can be interpreted systematically.

Analysis then moves toward the future through Predictive Analytics, which uses historical data, statistical models, and Machine Learning techniques to predict what may happen in the future, while recognizing that these predictions represent probabilities rather than certain facts.

After identifying what may happen, Prescriptive Analytics comes into play. It compares different alternatives and recommends the best decision that can be taken to achieve the greatest benefit, lowest cost, or lowest risk, based on data, mathematical models, and Artificial Intelligence.

Finally, analytics reaches its highest level through Proactive Analytics, which does not merely solve problems but works to prevent them before they appear, create opportunities before they become obvious, and build long-term strategies that make individuals and organizations more capable of adapting, innovating, and sustaining their success.

The higher you rise through the levels of data analytics, the more you move from understanding the past to leading the future.

- Comparison of Data Analytics Levels:

Level. Main Question. Goal.
Descriptive Analytics. What happened? Describe the current reality.
Diagnostic Analytics. Why did it happen? Identify the causes.
Predictive Analytics. What will happen? Predict the future.
Prescriptive Analytics. What should I do? Choose the best decision.
Proactive Analytics. How can I create a better future? Prevent problems and create opportunities.

- Key Points:

  • Data analytics is not limited to reading numbers; it aims to transform data into decisions that create value.
  • Each level of analytics depends on the level before it and adds deeper understanding.
  • Descriptive Analytics describes reality but does not explain it.
  • Diagnostic Analytics searches for the root causes of problems.
  • Predictive Analytics uses the past to estimate the future.
  • Prescriptive Analytics recommends the best possible options.
  • Proactive Analytics focuses on prevention, innovation, and preparation for the future.
  • The higher you move through the levels of analytics, the better the quality of decisions becomes and the lower the degree of uncertainty.
  • Data alone does not create value; value is created when data is transformed into understanding, then into decisions, and finally into deliberate actions.

The ability to use these levels correctly is not merely a technical skill. It is a way of thinking that helps people see reality more clearly, interpret events more accurately, prepare for the future more effectively, and make wiser decisions in their personal, professional, and leadership lives.

Are you ready to reclaim your personal sovereignty?

True development begins when you stop adapting to other people's expectations and start setting your own rules. Through our training packages, we focus on liberating you from limiting patterns, boosting confidence in your decisions, and building a confident personal presence that positively impacts all areas of your life. Invest in your awareness, and turn your potential into tangible results.

Start Your Journey of Change Now
you need help?