Many businesses believe great analytics starts with great data. Sure, data is important, but the best analytics actually start with asking the right questions. This is because each type of data analytics answers a specific question, giving you unique insights into your data.
There are four types of data analytics. Descriptive analytics looks at past data and tells you what happened. Diagnostic analytics goes a step further to explain why it happened. Predictive analytics uses patterns in the data to show what is likely to happen next. Prescriptive analytics suggests what actions you should take to get the best outcome.
Despite serving different purposes, each type has one thing in common. They help you make informed decisions based on what your data says. In the coming sections, we’ll look at each of these analytics types in more detail, along with examples.
Descriptive Analytics
Descriptive analytics is the simplest among the various types. As the name suggests, it simply describes what is happening now or what has happened in the past. It gives you a clear picture of the current state of things: a summarized view of your data through charts, dashboards, or business intelligence (BI) tools.
Descriptive analytics may be enough if all you want to do is monitor key performance indicators (KPIs) and targets like the number of customers, the amount of revenue generated, website visits, or even machine logs in more technical cases. It provides you with just enough insight to observe trends, catch anomalies, and track the metrics needed to make informed day-to-day decisions.
This dashboard summarizes hiring metrics, such as the total number of applicants, cost of hiring, revenue generated, and return on investment (ROI) for a recruitment company. It also shows the original source of each applicant (i.e., LinkedIn, referrals, or job boards). This lets the company easily see which sources bring in the most applicants and which ones actually lead to placements and returns.
If the company wants to determine which recruitment channels to keep or stop using, this dashboard gives them just enough insight to make the right decision.
Diagnostic Analytics
Whereas descriptive analytics summarizes events that happened, diagnostic analytics builds on this foundation by revealing the motivations behind those results. Diagnostic analytics explains all the trends, anomalies, and metrics that descriptive analytics brings to light. So, instead of just showing you what happened (e.g., telling you more people than usual visited your website this week), diagnostic analytics digs deeper to show you why it happened.
Data analytics reports often combine both descriptive and diagnostic analytics. Descriptive analytics is used to identify that a problem exists, and diagnostic analytics is used to evaluate the root cause of it.
Diagnostic analytics also involves a lot more one-off analysis because it often answers the question “what changed?”. As a result, analysts have to come up with hypotheses for why the change happened. They do this by collecting the data before and after the change happened, comparing the data, and drawing conclusions.
To get the depth of insight that diagnostic analysis can provide, analysts must use more advanced techniques like drill-downs, correlations, and root-cause analysis (RCA). Businesses use diagnostic analysis to find the source of a problem in order to fix it or to understand what is driving performance so they can double down on what works for their business.
In the example, a real estate company used descriptive analytics to identify that its revenue and profit decreased in February. Their next step was to use diagnostic analytics to uncover what caused this decrease.
After digging in, they found that the following properties caused a decrease in collected rent because some tenants moved out.
Similarly, if you saw that expenses increased, the diagnostic analytics would involve looking at individual expense groups and transactions. Management could then either deem those expenses necessary or look for ways to avoid them in the future.
Predictive Analytics
Once underlying drivers are understood, it’s common for organizations to look ahead. Predictive analytics responds to this need by utilizing patterns to estimate events likely to happen next. Predictive analytics uses patterns in your data to forecast future events. For example, if a store manager wants to know how many sales to expect within a particular month, predictive analytics can give a good guess based on historical data. Predictive analytics involves more advanced techniques like statistical modeling, machine learning, and historical trend analysis.
Businesses use predictive analytics to prepare for the future, mitigate risks, and capitalize on opportunities before their competitors.
Figure 4. Forecasting Sales Trends Using Predictive Analytics | Source: Created by the Author
Apart from forecasting future trends, predictive analytics can be used to predict the likelihood of an event (e.g., customer churn).
The most common predictive analytics techniques are:
Linear Regression: This assumes a linear relationship between two or more variables and is often used for time-series forecasting.
Logistic Regression: This returns a value between 0 and 1, which is perfect for predicting the likelihood of events.
Decision Trees: Used mainly for classification problems, these often consist of a list of yes/no branches that lead to certain outcomes. They are typically used to predict the outcome of a scenario based on multiple variables.
Neural Networks: These are computing systems inspired by the human brain, which consists of interconnected nodes (neurons) that try to identify patterns and derive a relationship from raw data. Often used when there is no linear relationship between the variables or to check the performance of other predictive models.
Prescriptive Analytics
Prescriptive analytics leverages all the insights from the other types of analytics to recommend the best course of action. It answers the question “Based on everything the data has revealed, what specific steps should we take to achieve the best outcomes?” Prescriptive analytics guides you through the use of optimization models, simulations, and AI-driven recommendations.
Here’s an example of how this type of analytics is used in the real world. A retail company used predictive analytics to find out that demand is going to go up next month. That’s useful, but what do they do about it? That’s where prescriptive analytics comes in. Instead of leaving the manager to guess, prescriptive analytics can tell you:
How many staff to schedule
How much stock to order and when
How much of the budget should be allocated to marketing
In summation, prescriptive analytics gives you clear, calculated, and optimized actions to take so that your data analytics don’t just end at gaining insight but instead lead to tangible business outcomes.
Figure 5. Overview of the Four Types of Data Analytics | Source: Adapted From the Author
Conclusion
These four types of data analytics are not mutually exclusive. Rather, they complement each other. For example, you can use descriptive analytics for explorative data analysis to form your hypothesis. You can then use predictive analytics to test your hypothesis and confirm correlation.
The most effective data analytics teams combine all four types, but this requires a special mix of skills and technology.
Companies that want to invest in descriptive or diagnostic analytics should focus on nurturing spreadsheet data visualizations and BI skills. Those who want to invest in predictive or prescriptive analytics require knowledge of statistics and statistical modelling tools such as R, SPSS, and Stata.
For anyone interested in a more holistic approach, knowledge of data governance and business intelligence infrastructure would make investing in all types of data analytics more effective.
**********
About the Author:
This article was written by Eugene Lebedev, managing director of Vidi Corp, a UK-based data analytics consultancy. He has delivered over 1000 data analytics solutions for more than 600 international clients, including Google, Teleperformance, and Delta Air Lines.
Despite the continuous hype around data analytics and the rapid acceleration of data technologies such as machine learning (ML) and artificial intelligence (AI), most companies are lagging behind with low data capabilities and no in-house data team in place. These companies have their data either fully unleveraged or marginally analyzed by executives on the side of their jobs to produce limited reports.
In such a situation, pushing the organization up the hill of data maturity would require building a team of data-specialized personnel. Building such a team can be daunting, as every company would have different conditions and no one way can fit all cases. However, covering the following main grounds can help cut miles on the road to building a data team from the ground up.
First, nurture the environment and plant the seeds. Data teams cannot grow in a vacuum. To prepare the organization to become data-driven with a data team, enhancing the organizational data culture is a good starting point. Having employees at all levels with a data-driven mentality and an understanding of the role of data analytics can significantly prepare the room for the planned team.
Second, connect with stakeholders and recognize priority needs. Carrying out data culture programs inside the organization can open up opportunities to have meaningful discussions with stakeholders on different levels about their data needs, what they already do with data, and what they want to achieve, in addition to having better insights into the pre-existing data assets. This is a good stage to recognize the organization’s data pain points, which would then be the immediate and strategic objectives of the future data team.
Third, define the initial structure of the team. According to the scale of the organization and the identified needs, data teams can have one of three main structures:
Centralized: This involves having all data roles within one team reporting to one head, chief data officer (CDO), or a similar role. All departments in the organization would request their needs from the team. This is a straightforward approach, especially for small-size companies, but can end up in a bottleneck if not scaled up continuously to meet the organization’s growing needs.
Decentralized: This requires disseminating all data roles and infusing them into departmental teams. This mainly aims to close the gap between technical analysis and business benefits as analysts in every team would be experts in their functional areas. However, the approach may lead to inconsistencies in data management and fragile data governance.
Hybrid: This consists of having governance, infrastructure, and data engineering roles within a core team, along with embedding data analysts, business analysts, and data scientists in departmental teams. The allocated personnel would report to the respective department head as well as the data team head. This approach combines the benefits of both centralized and decentralized structures and is usually applicable in large organizations as they require more headcount in their data teams.
Fourth, map the necessary tech stack and data roles. As the previous stages have uncovered the current uses and needs of data in an organization, it should be easier to start figuring out the tech tools that the team would be initially working with. Mapping the needed tech stack would be the first pillar before moving on to the hiring process. The second pillar would involve defining the roles that the team would need in its nascent stage to meet the prioritized objectives.
Several data job titles can be combined in a data team, with many of them having specializations that intersect with or bisect each other. However, there are three main role areas that should be considered for starting data teams:
Data engineering: implementing and managing data storage systems, integrating scattered datasets, and building pipelines to prepare data for analysis and reporting
Data analysis: performing final data preparation and extracting main insights to inform decision-making
Data science: building automated analysis and reporting systems, usually concerned with predictive and prescriptive machine learning models
Fifth, follow step-by-step team recruitment. Hiring new employees for the data team is one option. The other option can be upskilling existing employees with an interest in a data career and with minimum required skills. Even employees with just interest and no minimum required skills can be reskilled to fill some roles, especially within an initial data team.
The team does not need to take off with full wings. It can start small and gradually grow. Typically, data teams would start with data analysts who have extra skills in data engineering, data engineers who have experience with ad-hoc analyses and reporting, or a limited combination of both. In later stages, other titles can join onboard.
The baby-step-building approach is more convincing for stakeholders as it can be more efficient from a return-on-investment (ROI) perspective. Starting with a full-capacity team may end up being too costly for the organization, which could lead to the budding project being cut off in its prime.
Sixth, deliver ad-hoc analyses, heading towards long-term projects. In the beginning, data analytics experts at the organization would be expected to answer random requests and solve urgent data-related problems, like developing quick reports and reporting on-spot metrics. This is a good point to prove how data personnel can be of direct benefit to the organization.
However, along with delivering said ad-hoc requests, the data team should have strategic goals to enhance and develop the overall data maturity of the organization, like organizing, integrating, and automating the analytics processes and installing advanced predictive models. These long-term projects should foster the organization’s data maturity, which should result in ad-hoc requests being less frequent as all executives should be self-sufficient in using the installed automated reports and systems. In such a data-mature environment, the team would have time to advance their data products continuously, opening up new benefit opportunities.
Seventh, fortify the team’s presence. Strategic projects with shorter implementation periods and more immediate impact should be prioritized over longer ones, especially in the beginning. That would help continuously prove the benefits of the data team and the point of its foundation. Owning the products of the data team by having its name on it can help remind decision-makers of the team’s benefit. In addition, it is highly useful for the data team’s head to have access to top managerial levels to keep promoting the team’s presence and expansion.
Building a data team from scratch requires careful planning, investment, and commitment from organizational leadership. By following these guidelines and adapting them to their specific needs, organizations without prior data capabilities can establish a robust data team capable of driving innovation and offering a competitive advantage through data-driven insights.
Islam Salahuddin is a data analyst with a strong focus on storytelling and data visualization, growing statistical knowledge, and developing a set of technical skills and tools. As an expert in data analysis at The KPI Institute, Islam leads the generation of research on the domain of data analytics and the development of business analytics toolkits.
Jino Noel is a data science and technology leader with extensive experience in building data teams and practices across different organizations. His experience ranges from working in startups to large conglomerates across both Australia and the Philippines. At the time of this interview, he was the Chief Data Officer at Data Analytics Ventures, Inc. (DAVI). Currently, he is the Chief Data Officer at Angkas.
What are the key skills that a Chief Data Officer should possess nowadays?
A Chief Data Officer should have both data-related technical expertise as well as people leadership skills. Leading will always be part of the job, particularly for highly specialized technical people such as data engineers and data scientists. To be able to lead them properly, I believe it is better to be a technical person myself, so I can discuss technical matters fluently, which helps me gain their trust.
What data-related challenges have you faced as the Chief Data Officer of DAVI? How did you overcome these challenges?
Our data-related challenges are the same as any company. Being able to trust our data, cleaning up data from our sources, data latencies, and other related issues. DAVI overcame these by investing in people—hiring high-quality experts in our data engineering, data governance, and analytics teams to help us make sense of the data coming in—and building robust data pipelines that have increased the standard of quality of the data in our data lake.
How does DAVI make use of advancements in artificial intelligence (AI) and machine learning to help its clients understand their customers’ needs and buying patterns?
DAVI has recently started using machine learning to model our users’ propensity to buy certain products. This helps us create more accurate target audiences for our precision marketing campaigns. We are also moving forward with a recommendation engine project, with the goal of improving user engagement with our retail partners and with our promos and campaigns. On top of this, we are improving our machine learning operations expertise to make our model deployments repeatable and robust.
In the digital marketplace, data analytics acts as a guiding compass for app developers, enabling the creation of personalized, high-performing applications that align with user preferences. By leveraging data, developers can understand nuanced user behaviors and preferences, allowing them to tailor apps to meet specific user needs and aspirations.
Dive deeper into these discussions by reading Jino Noel’s full interview with The KPI Institute. Download the free digital copy of PERFORMANCE Magazine Issue No. 26, 2023 – Data Analytics on the TKI Marketplace. You can also purchase a physical copy via Amazon.
Harry Patria, the CEO of Patria & Co., is a data strategist and lecturer who founded a company that serves over 100 corporate clients, 200 analytical platforms, and 500 professionals. He is a Data Hackathon winner in the UK and graduated with distinction from his master’s degree to a PhD program with a fully-funded scholarship. Harry is a subject matter expert in several fields.
Islam Salahuddin is a data analyst with a strong focus on storytelling and data visualization, growing statistical knowledge, and developing a set of technical skills and tools. As an expert in data analysis at The KPI Institute, Islam leads the generation of research on the domain of data analytics and the development of business analytics toolkits.
Jino Noel
