Different Types of Analysis

In a technical sense, data analytics can be described as the process of using data to answer questions, identify trends, and extract insights. There are multiple types of analytics that can generate information to drive innovation, improve efficiency, and mitigate risk.

There are four key types of data analytics, and each answers a different type of question:

• Descriptive analytics asks, “What happened?”
• Predictive analytics asks, “What might happen in the future?”
• Prescriptive analytics asks, “What should be done next?”
• Diagnostic analytics asks, “Why did this happen?”

Each of the above types has its own unique insights, advantages, and disadvantages. Used in combination they provide a more complete understanding of the business's needs and opportunities.

Descriptive Analytics

Descriptive analytics primarily uses observed data to identify key characteristics of a data set. It relies solely on historical data to provide reports on past events. This type of analysis is also used to generate ad hoc (as needed) reports that summarize large amounts of data to answer simple questions like “how much?” or “how many?” It can also be used to ask deeper questions about a specific problem. Descriptive analytics is not used to draw inferences or predictions from its findings; it is just a starting point used to inform decisions or to prepare data for further analysis.

The descriptive analytics process is as follows:

1. Ask a historical question that needs an answer, such as “How much of product X did we sell last year?”
2. Identify required data to answer the question
3. Collect and prepare data
4. Analyze data
5. Present results

Examples of descriptive analytics include:

• Summarizing historical events such as sales, inventory, or operations data
• Understanding engagement data such as likes and dislikes or volume of page views over time
• Reporting general trends like revenue growth or employee injuries
• Collating survey results

Predictive Analytics

Predictive analytics utilizes real-time and/or past data to make predictions based on probabilities. It can also be used to infer missing data or establish a predicted future trend. Predictive analytics uses simulation models and forecasting to suggest what could happen going forward, which can guide realistic goal setting, effective planning, management of performance expectations, and avoiding risks. This information can empower executives and managers to take a proactive and fact-based approach to strategy and decision making.

The predictive analytics process is as follows:

1. Ask a forward-thinking question, such as “Can we predict how much product X we will sell next year?”
2. Collect and prepare data
3. Develop predictive analytics models
4. Apply models to the prepared data
5. Review models and present results

Examples of predictive analytics include:

• Forecasting customer behavior, purchasing patterns, and identifying sales trends
• Predicting customer preferences and recommending products to customers based on past purchases and search history
• Predicting the likelihood that a given customer will purchase another product or leave the store
• Identifying possible security breaches that require further investigation
• Predicting staffing and resourcing needs

Prescriptive Analytics

Prescriptive analytics builds on descriptive and predictive analysis by recommending courses of action that will reap the greatest benefit for the organization. In short, prescriptive analytics tells you what should be done in a given situation. It helps executives, managers, and employees make the best decisions based on available data.

• A good example of prescriptive analytics is the field of GPS-based map and direction applications. These applications provide route options to a destination based on traffic volume, road conditions, and maximum speed. It can then prescribe the best route based on user-defined objectives such as shortest distance or quickest time.

Diagnostic Analytics

Diagnostic analytics enhances the descriptive analytics process by digging in deeper and attempting to discover the cause(s).

The diagnostic analytics process is as follows:

• Identify anomalies (inconsistencies) in data sets
• Collect data related to the anomalies
• Use statistical techniques to uncover relationships and trends that could explain the anomalies
• Present possible causes

An example of diagnostic analytics is using subscription cancellations, correlated with customer comments and ratings, to determine the most common reasons why users cancel subscriptions. Another example would be determining whether there is a correlation between the demographics of consumers and their purchasing patterns at specific times of year.