Four Primary Types Of Data Analytics & Their Application In Maritime Safety Management

With exploding data volumes and more and more data analytics platforms, businesses are able to achieve their goals in a more targeted and faster way.

According to Splunk, companies that have a strategic focus on data and an advanced strategy for extracting business value have seen 83% more revenue and 66% more profit than their peers in the last 12 months. In addition, 93% of these companies believe they tend to make better and faster decisions than their competitors. And 91% believe their company is in a good position to compete and succeed in its markets over the next few years.

Data, Analytics, and Insights

With the development of digitalization, the maritime industry has become a data-rich sector. However, facts and figures are meaningless if no valuable insights that can lead to more informed actions be generated. Though the three words - data, analytics, and insights are often used interchangeably, they have different meanings:

📝      Data is the information collected to describe what happened when, where, how, and with who involved.

🔎     Analytics is the discovery of patterns and trends derived from data.

💡     Insight is the value obtained through the use of analytics.


Four Primary Types Of Data Analytics

Below are the four main types of data analysis that can be used to generate insights for maritime safety management.

Descriptive Analytics: Explains what happened

Descriptive analytics is the most common type of analytics. It juggles raw data from multiple data sources to give insights into what happened in the past. These insights can show the performance of some metrics and signal something is wrong or right. Descriptive analytics can be in the form of data visualizations like graphs, charts, reports, and dashboards.

For example, technical directors can see the overall fleet's deficiencies and health status and identify which vessel has what deficiencies at the moment. Planned maintenance systems are based on this type of analytics.

Diagnostic Analytics: Tells why it happened

Like descriptive analytics, diagnostic analytics also focus on the past. However, diagnostic analytics drill down a step further and provide deeper analysis to answer the question: "Why did this happen?" So, diagnostic analytics is also often called root-cause analysis. This process includes data discovery, data mining, and drill-down and drill-through.

In the fleet health management example mentioned above, diagnostic analytics would explore the data and make correlations. For instance, it may help technical directors determine that the hulls that have more corrosion use the same paint coatings.

Predictive Analytics: Forecasts what might happen

Predictive analytics is about predicting future events. The predictive model uses historical data and feeds it into a machine learning model to determine the probability of an event occurring in the future or to estimate when it might occur. The model is then applied to current data to predict what will happen next. However, with so many different variables that are difficult to control, it is important to remember that no analysis is able to tell exactly what will happen in the future. Predictive analytics is more of a tool that gives the respective probabilities of the examined variables.

For example, the analysis model can detect the rate of deterioration of a particular machine component and suggest when it might fail in the future.

Prescriptive Analytics: Suggests actions based on the forecast

Prescriptive analytics helps users to be proactive. It prescribes what action to take to navigate through a future problem or take full advantage of a trend. Prescriptive analytics uses advanced technologies like machine learning to process all the analytical results above - what happened, why it happened, and what might happen so that it can help users determine what actions to take next. It is not a response to analytics but more of a host of other actions.

In the maintenance case, the prescriptive analytics tool may suggest how many replacement components are required and when they are needed to prevent specific deficiencies in the future. Technical directors can then forecast the maintenance cycle to avoid off-hire and reduce costs.


Kaiko Systems' Approach

Kaiko Systems empowers crews to collect verified vessel health data and translates this data into actionable insights.

With Kaiko Systems:

●  Crews can save 50% of time spent on routine inspections

●  Data is verified and structured automatically so the team ashore can manage more vessels and focus on leveraging their expertise instead of dealing with administrative overhead

●  Crews can have an overview of the vessel health even with no internet connection

●  No more data is lost in ship-to-shore communication

●  Vessel health conditions, deficiencies, and root causes can be visualized and analyzed in the Kaiko Systems Dashboard, and also integrated into the existing ERP system

●  Shipping companies can proactively prevent incidents and off-hire



Furthermore, Kaiko Systems provides every stakeholder with customized data access and decision support. In this way, Kaiko Systems helps to break down data silos in the company and allows a faster decision-making process.

Explore the product

By signing up, I agree to the Kaiko SystemsPrivacy Policy.
Your account is being prepared!
Our team will reach out to you shortly.
Oops! Something went wrong while submitting the form.